@inproceedings{szekely2007, vgclass = {refpap}, vgproject = {viper}, author = { Eniko Szekely and {\'E}ric Bruno and St{\'e}phane Marchand-Maillet}, title = {Clustered multidimensional scaling for exploration in information retrieval }, booktitle = { 1st International Conference on the Theory of Information Retrieval (ICTIR'07) }, address = {Budapest, Hungary}, pages = {95-104}, month = {October 18-20}, year = {2007}, url = {http://cvml.unige.ch/publications/postscript/2007/EnikoSzekely_ICTIR.pdf} } @inproceedings { morrison08-semantic, vgclass = {refpap}, vgproject = {viper}, author = { Morrison, Donn and Marchand-Maillet, St\'ephane and Bruno, Eric }, title = { Semantic clustering of images using patterns of relevance feedback }, booktitle = { Proceedings of the 6th International Workshop on Content-based Multimedia Indexing}, note = { (accepted) }, address = { London, UK }, month = { June 18-20th }, year = { 2008 } } @inproceedings{Kludas2008, vgclass = {refpap}, vgproject = {viper}, author = { Jana Kludas and Eric Bruno and Stephane Marchand-Maillet }, title = { Study on Feature Interactions and its benefit for Information Fusion }, booktitle = { submitted at 16th European Signal Processing Conference }, note = {(submitted)}, owner = {Kludas}, timestamp = {2008.03.03}, year = {2008} } @inproceedings{Kludas2008b, vgclass = {refpap}, vgproject = {viper}, author = { Jana Kludas and Eric Bruno and Stephane Marchand-Maillet }, title = { Efficient information fusion in high dimensional spaces by exploiting feature interactions }, booktitle = { submitted at 11th International Conference on Information Fusion }, year = { 2008 }, note = {(submitted)}, owner = {Kludas}, timestamp = {2008.03.03} } @inproceedings{Kludas2008c, vgclass = {refpap}, vgproject = {viper}, author = { Jana Kludas and Eric Bruno and Stephane Marchand-Maillet }, title = { Can Feature Information Interaction help for Information Fusion in Multimedia Problems? }, booktitle = { First International Workshop on Metadata Mining for Image Understanding}, location = {Funchal, Madeira}, pages = {23--33}, year = { 2008 }, url = {http://cvml.unige.ch/publications/postscript/2008/KludasBrunoMarchand_Madeira_2008.pdf} } @INPROCEEDINGS{BJanvier:MLMI2005, author = {Bruno Janvier and St{\'e}phane Marchand-Maillet and {\'E}ric Bruno and Thierry Pun}, title = {Semantic segmentation of video collections using boosted random fields}, booktitle = {Proceedings of the 2005 second Workshop on Machine Learning and Multimodal Interaction, {MLMI'05}}, year = {2005}, vgclass = {refpap}, vgproject = {viper}, address = {Edinburgh, UK}, month = {July}, } @MISC{VG:Laskowski06, vgclass = {diploma}, vgproject = {unspecified}, author = {Michel Laskowski}, title = {Optimising interaction in multimedia content description processes using structured knowledge}, howpublished = {maîtrises thesis, University of Geneva}, month = {octobre}, year = {2006} } @MISC{VG:Jordan06, vgclass = {diploma}, vgproject = {unspecified}, author = {Patrick Jordan}, title = {Long term usage of interaction log in content-based retrieval systems via LSI}, howpublished = {maîtrises thesis, University of Geneva}, month = {septembre}, year = {2006} } @MISC{VG:Strumiello05, vgclass = {diploma}, vgproject = {unspecified}, author = {Olivier Strumiello}, title = {VidaView : Interface optimale pour la visualisation multimodale de vidéo segmentée}, howpublished = {maîtrises thesis, University of Geneva}, month = {juillet}, year = {2005} } @MISC{VG:Heuberger04, vgclass = {diploma}, vgproject = {unspecified}, author = {Joris Heuberger}, title = {Descripteur sémantique pour l'indexation de vidéos: détection de visages (Face detection in video sequences)}, howpublished = {maîtrises thesis, University of Geneva}, month = {décembre}, year = {2004} } @MISC{VG:Campelo04, vgclass = {diploma}, vgproject = {unspecified}, author = {Roberto Campelo}, title = {Collection guiding}, howpublished = {maîtrises thesis, University of Geneva}, month = {juillet}, year = {2004} } @MISC{VG:Chekroun04, vgclass = {diploma}, vgproject = {unspecified}, author = {Olivier Chekroun}, title = {Partitionnement d'image robuste pour l'indexation par région (Robust image segmentation)}, howpublished = {maîtrises thesis, University of Geneva}, month = {juillet}, year = {2004} } @MISC{VG:Annen03, vgclass = {diploma}, vgproject = {unspecified}, author = {Florian Annen}, title = {GIFT: Mode'lisation et propositions d'évolution}, howpublished = {diploma thesis, University of Geneva}, month = {mars}, year = {2003} } @MISC{VG:Jelmini02, vgclass = {diploma}, vgproject = {unspecified}, author = {Carlo Jelmini}, title = {DEVA: Un modèle d'annotation flexible pour les collections de documents visuels}, howpublished = {diploma thesis, University of Geneva}, month = {septembre}, year = {2002} } @ARTICLE{VG:ORP1998, author = {Joe J. K. {{\'O}~Ruanaidh} and Thierry Pun}, title = {Rotation, scale and translation invariant spread spectrum digital image watermarking}, journal = {Signal Processing}, year = {1998}, volume = {66}, pages = {303--317}, vgclass = {refpap}, vgproject = {watermarking}, number = {3}, month = {May}, note = {(Special Issue on Copyright Protection and Control, B. Macq and I. Pitas, eds.)}, abstract = {A digital watermark is an invisible mark embedded in a digital image which may be used for a number of different purposes including image captioning and copyright protection. This paper describes how a combination of spread spectrum encoding of the embedded message and transform-based invariants can be used for digital image watermarking. In particular, it is described how a Fourier-Mellin-based approach can be used to construct watermarks which are designed to be unaffected by any combination of rotation and scale transformations. In addition, a novel method of CDMA spread spectrum encoding is introduced which allows one to embed watermark messages of arbitrary length and which need only a secret key for decoding. The paper also describes the usefulness of Reed Solomon error-correcting codes in this scheme.}, url = { http://vision.unige.ch/publications/postscript/98/ORuanaidhPun_sp98.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/ORuanaidhPun_sp98.pdf} } @INPROCEEDINGS{VG:ORP1997, author = {Joe J. K. {{\'O}~Ruanaidh} and Thierry Pun}, title = {Rotation, scale and translation invariant digital image watermarking}, booktitle = {Proceedings of ICIP 97, IEEE International Conference on Image Processing}, year = {1997}, vgclass = {refpap}, vgproject = {watermarking}, pages = {536--539}, address = {Santa Barbara, CA}, month = {October}, abstract = {A digital watermark is an invisible mark embedded in a digital image which may be used for Copyright Protection. This paper describes how Fourier-Mellin transform-based invariants can be used for digital image watermarking. The embedded marks are designed to be unaffected by any combination of rotation, scale and translation transformations. The original image is not required for extracting the embedded mark.}, url = { http://vision.unige.ch/publications/postscript/97/ORuanaidhPun_icip97.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/ORuanaidhPun_icip97.pdf} } @INPROCEEDINGS{Alecu:EUSIPCO2005:DIMOG, author = {Teodor Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Denoising with infinite mixture of Gaussians}, booktitle = {Eusipco 2005, 13th. European Signal Processing Conference, Sept. 4-8, Antalya, Turkey}, year = {2005}, vgclass = {refpap}, vgproject = {bmi} } @INPROCEEDINGS{Alecu:EUSIPCO2005:TGT, author = {Teodor Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {The Gaussian transform}, booktitle = {13th. European Signal Processing Conference}, year = {2005}, vgclass = {refpap}, vgproject = {bmi}, address = {Antalya, Turkey}, month = {September 4--8} } @INPROCEEDINGS{BMI:EUSIPCO2004, author = {Teodor Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Localization properties of an EEG sensor system: lower bounds and optimality}, booktitle = {EUSIPCO 2004, 12th European Signal Processing Conference}, year = {2004}, vgclass = {refpap}, vgproject = {bmi}, address = {Vienna, Austria}, month = {September 6-10}, url = {http://vision.unige.ch/publications/postscript/Alecu_Eusipco2004.pdf} } @INPROCEEDINGS{BMI:ISBI04, author = {Teodor Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {EEG Cortical Imaging: A Vector Field Approach For Laplacian Denoising And Missing Data Estimation}, booktitle = {IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI'04)}, year = {2004}, vgclass = {refpap}, vgproject = {bmi}, address = {Arlington, VA}, month = {April, 15-18}, url = {http://vision.unige.ch/publications/postscript/Alecu2004__EEG_cortical_imaging_a_vector_field_approach.pdf} } @INPROCEEDINGS{BMI:SPIE2004, author = {Teodor Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Regularized two-step brain activity reconstruction from spatio-temporal EEG data}, booktitle = {Image Reconstruction from Incomplete Data III, SPIE International Symposium on Optical Science and Technology}, year = {2004}, vgclass = {refpap}, vgproject = {bmi}, address = {Denver, Colorado, USA}, month = {August 2-6}, url = {http://vision.unige.ch/publications/postscript/Alecu2004_SPIE.pdf} } @PHDTHESIS{Alecu:PhD, author = {Teodor Iulian Alecu}, title = {Robust Focalized Brain Activity Reconstruction using ElectroEncephaloGrams}, school = {University of Geneva}, year = {2005}, url = {http://vision.unige.ch/publications/postscript/2005/phdTeodorAlecu.pdf}, vgclass = {thesis}, vgproject = {bmi} } @MISC{Alecu:SIMILAR2004:ONLEIP, vgclass = {fullconf}, vgproject = {bmi}, author = {Teodor Iulian Alecu}, title = {Overcoming noise limitations in the EEG Inverse Problem}, howpublished = {EU NOE Similar Workshop}, month = {November 8--9}, year = {2004}, note = {Sophia-Antipolis, France}, address = {Sophia-Antipolis, France}, booktitle = {EU NOE Similar Workshop} } @TECHREPORT{BMI:Oct0404, author = {Teodor Iulian Alecu}, title = {Local estimation with global priors}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2004}, vgclass = {report}, vgproject = {bmi}, number = {04.04}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland}, url = {http://vision.unige.ch/publications/postscript/2004/LeGlob.pdf} } @TECHREPORT{BMI:Nov0306, author = {Teodor Iulian Alecu}, title = {Inverse problem solutions and resolutions}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {bmi}, number = {03.06}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland}, url = {http://vision.unige.ch/publications/postscript/2003/SaRotIP.pdf} } @INPROCEEDINGS{Alecu:SSP2005, author = {Teodor Iulian Alecu and P. Missionnier and Sviatoslav Voloshynovskiy and P. Giannakopoulos and Thierry Pun}, title = {Soft/hard focalization in the EEG inverse problem}, booktitle = {IEEE Workshop on Statistical Signal Processing {(SSP'05)}}, year = {2005}, vgclass = {refpap}, vgproject = {BMI}, address = {Bordeaux, France}, month = {July, 17-20}, url = {http://vision.unige.ch/publications/postscript/2005/SoftFocalizationSSP.pdf} } @ARTICLE{Alecu:SP2005:GTD, author = {Teodor Iulian Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {The Gaussian Transform of distributions: definition, computation and application}, journal = {IEEE Transactions on Signal Processing}, year = {2006}, volume = {54}, pages = {2976--2985}, vgclass = {refpap}, vgproject = {bmi}, month = {August}, note = {(accepted October 2005)}, url = {http://vision.unige.ch/publications/postscript/2005/IEEE_GT_DIMG_c1.pdf} } @INPROCEEDINGS{Alecu2:EUSIPCO2005, author = {Teodor Iulian Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Denoising with infinite mixture of Gaussians}, booktitle = { {EUSIPCO} 2005, 13th European Signal Processing Conference}, year = {2005}, vgclass = {refpap}, vgproject = {BMI}, address = {Antalya, Turkey}, month = {September 4-8}, url = {http://vision.unige.ch/publications/postscript/2005/EUSIPCO-DIMG.pdf} } @INPROCEEDINGS{Alecu:AMI2004:RTBARSTED, author = {Teodor Iulian Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Regularized two-step brain activity reconstruction from spatio-temporal EEG data}, booktitle = {Joint AMI - PASCAL - (IM)2 - M4 Workshop on Multimodal Interaction and related machine learning algorithms, Martigny, Switzerland, 21-23 June 2004}, year = {2004}, vgclass = {fullconf}, vgproject = {bmi} } @INPROCEEDINGS{Alecu:IM22003:LPESSEMS, author = {Teodor Iulian Alecu and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Localization properties of an EEG sensor system : electrode misplacement sensitivity}, booktitle = {NCCR (IM)2 Interactive Multimodal Information Management Workshop, MartignyCrans-Montana, Switzerland, October 6-8, 2003}, year = {2003}, vgclass = {fullconf}, vgproject = {bmi} } @MISC{VG:Ami2000, vgclass = {diploma}, vgproject = {external}, author = {Ludovic Amiguet}, title = {Simulation Visuelle 3D Du Vieillissement Du Visage}, howpublished = {Diploma thesis (MSc), University of Geneva}, month = {November}, year = {2000} } @INPROCEEDINGS{Ansari-Asl:2007:EUSIPCO, author = {Karim Ansari-Asl and Guillaume Chanel and Thierry Pun}, title = {A channel selection method for EEG classification in emotion assessment based on synchronization likelihood}, booktitle = {Proceedings of the 15th European Signal Processing Conference}, year = {2007}, vgclass = {refpap}, vgproject = {bmi}, address = {Poznan, Poland}, month = {September 3--7}, owner = {beekhof}, timestamp = {2007.08.29} } @MISC{Ansari-Asl:2007:NOE, vgclass = {fullconf}, vgproject = {bmi}, author = {Karim Ansari-Asl and Guillaume Chanel and Thierry Pun}, title = {A Channel selection method for EEG classification in emotion assessment based on synchronization likelihood}, howpublished = {Similar NOE Workshop}, month = {June 4--5}, year = {2007}, note = {University of Magdeburg, Germany}, address = {University of Magdeburg, Germany}, booktitle = {Similar NOE Workshop}, owner = {beekhof}, timestamp = {2007.08.29} } @INPROCEEDINGS{VG:AHF1988, author = {R. D. Appel and D. F. Hochstrasser and M. Funk and C. Roch and Thierry Pun and Christian Pellegrini}, title = {Automatic classification of two-dimensional gel electrophoresis pictures by heuristic clustering}, booktitle = {Electrophoresis'88, Copenhagen, Denmark}, year = {1988}, vgclass = {fullconf}, vgproject = {unspecified}, month = {July} } @INPROCEEDINGS{VG:BNP1993, author = {C. Baur and E. Natonek and Thierry Pun}, title = {The {P}otato {O}peration: robotic apparatus for handling and testing natural objects}, booktitle = {Proceedings of the 4th International Symposium on Fruit, Nut and Vegetable Production Engineering, Valencia, Spain}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, pages = {1--8}, month = {March} } @INPROCEEDINGS{Beekhof:2008:eForensics, author = {Fokko Beekhof and Oleksiy Koval and Renato Vill\'{a}n and Sviatoslav Voloshynovskiy and Emre Topak}, title = {Document Forensics based on Steganographic Anti-Counterfeiting Markings and Mobile Architectures}, booktitle = {Proceedings of eForensics}, year = {2008}, vgclass = {refpap}, vgproject = {watermarking} } @INPROCEEDINGS{Beekhof:2007:SPIE-RPH, author = {Fokko Beekhof and Sviatoslav Voloshynovskiy and Oleksiy Koval and Renato Vill{\'a}n}, title = {Secure Surface Identification Codes}, booktitle = {SPIE}, year = {2008}, vgclass = {refpap}, vgproject = {watermarking} } @MISC{VG:Bob1988, vgclass = {licence}, vgproject = {unspecified}, author = {Anne Bobillier}, title = {G\'en\'erateur de signaux bidimensionnels}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {February}, year = {1988} } @ARTICLE{Bologna:2007:EJIVP, author = {Guido Bologna and Beno\^{i}t Deville and Thierry Pun and Michel Vinckenbosch}, title = {Transforming 3D coloured pixels into musical instrument notes for vision substitution applications}, journal = {Eurasip Journal of Image and Video Processing, Special Issue: Image and Video Processing for Disability}, year = {2007}, volume = {2007}, pages = {14}, vgclass = {refpap}, vgproject = {bmi}, note = {2007, Article ID 76204, 14 pages (Open access article)}, doi = {doi:10.1155/2007/76204}, url = {http://www.hindawi.com/GetArticle.aspx?doi=10.1155/2007/76204} } @INPROCEEDINGS{Bologna:IWINAC2007:IMCPAEC, author = {Guido Bologna and Beno\^{i}t Deville and Thierry Pun and Michel Vinckenbosch}, title = {Identifying major components of pictures by audio encoding of colors}, booktitle = {IWINAC2007, 2nd. International Work-conference on the Interplay between Natural and Artificial Computation, Murcia, Spain}, year = {2007}, vgclass = {refpap}, vgproject = {seecolor}, month = {June} } @MISC{Bologna:SIMILAR2006:TCBVI, vgclass = {fullconf}, vgproject = {seecolor}, author = {Guido Bologna and Beno\^{i}t Deville and Thierry Pun and Michel Vinckenbosch}, title = {Touching colour when being visually impaired}, howpublished = {Similar NOE Workshop}, month = {June 8--9}, year = {2006}, note = {Heraklion, Greece}, address = {Heraklion, Greece}, booktitle = {Similar NoE Workshop} } @INPROCEEDINGS{VG:BLM1997, author = {Holger Bosch and Abderrahim Labbi and Ruggero Milanese}, title = {Attentional modulation of firing patterns for spiking neurons}, booktitle = {2nd International Conference on Computational Intelligence and Neuroscience}, year = {1997}, vgclass = {refpap}, vgproject = {unspecified}, address = {Research Triangle Park, North Carolina}, month = {March}, url = { http://vision.unige.ch/publications/postscript/97/BoschLabbiMilanese_iccin97.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/BoschLabbiMilanese_iccin97.pdf} } @PHDTHESIS{VG:Bos1993, author = {Jean-Marc Bost}, title = {Active search for visual indexing in cluttered environments: from relevance to delays (``Recherche active pour la reconnaissance primaire d'objets: le concept des d\'elais'')}, school = {University of Geneva}, year = {1993}, type = {{P}h.{D}. {D}issertation {N}o. 2656}, address = {Switzerland}, month = {December}, note = {Thesis Jury: Prof.~James L.~Crowley (LIFIA, Grenoble, FR), Dr.~Frank Ade (ETH-Z\"urich, CH), Prof.~Christian Pellegrini (Geneva, CH), Prof.~Thierry Pun (director, Geneva, CH)}, vgclass = {thesis}, vgproject = {unspecified} } @TECHREPORT{VG:Bos1993a, author = {Jean-Marc Bost}, title = {Temporal precedence in asynchronous visual indexing}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1993}, vgclass = {report}, vgproject = {unspecified}, number = {93.02}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {January} } @TECHREPORT{VG:Bos1993b, author = {Jean-Marc Bost}, title = {Temporal delays for visual indexing in cluttered environments}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1993}, vgclass = {report}, vgproject = {unspecified}, number = {93.03}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {June} } @INPROCEEDINGS{VG:Bos1991, author = {Jean-Marc Bost}, title = {Discriminating agents for visual indexing}, booktitle = {Proceedings 3rd SGAICO Meeting (Swiss Group for Artificial Intelligence and Cognitive Science), Biel-Bienne, Switzerland}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, pages = {19--35}, month = {October}, note = {(published as: University of Bern, Institute for Comp. Science and Mathematics, Technical Report IAM-91--004, H. Kaiser, R. Bach and H. Bunke, Eds., March 1992)} } @INPROCEEDINGS{VG:Bos1990, author = {Jean-Marc Bost}, title = {Parallel access to high-level knowledge in a computer vision system}, booktitle = {SGAICO'90, Swiss Group for Artificial Intelligence and Cognitive Science, Geneva, Switzerland}, year = {1990}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October} } @ARTICLE{VG:BBM1991, author = {J.-M. Bost and P.-Y. Burgi and R. Milanese}, title = {{SGAICO} 91, Report on the conference}, journal = {SI-Information, Bulletin of the Swiss Association for Computer Science}, year = {1991}, volume = {Proceedings of SGAICO}, vgclass = {otherjournals}, vgproject = {unspecified} } @INPROCEEDINGS{VG:BMP1993, author = {Jean-Marc Bost and Ruggero Milanese and Thierry Pun}, title = {Temporal precedence in asynchronous visual indexing}, booktitle = {Proceedings of the 5th International Conference on Computer Analysis of Images and Patterns (CAIP'93), Budapest, Hungary}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, editor = {D. Chetverikov and W. G. Kropatsch}, number = {719}, series = {Lecture Notes in Computer Science}, pages = {468--475}, month = {September}, publisher = {Springer-Verlag} } @INPROCEEDINGS{VG:BMP1993a, author = {Jean-Marc Bost and Ruggero Milanese and Thierry Pun}, title = {Transforming an image into a data-flow for visual indexing}, booktitle = {Proceedings of the 7th International Conference on Image Analysis and Processing, Capitolo, Monopoli, Italy}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, editor = {S. Impedovo}, pages = {298--301}, month = {September}, publisher = {World Scientific} } @INPROCEEDINGS{VG:BSP1993, author = {Jean-Marc Bost and Serguei Startchik and Thierry Pun}, title = {Delaying as a key feature for visual indexing}, booktitle = {Swiss Vision'93 (5th SGAICO Symposium + 2nd Swiss IAPR Symposium), Z\"urich, Switzerland}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, pages = {27--36}, month = {September} } @TECHREPORT{VG:Mar0303, author = {Tayeb Bouzerda and St{\'e}phane Marchand-Maillet}, title = {A flexible framework for the development of XML protocols: Applications to MRML}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {viper}, number = {03.03}, address = {rue General Dufour, 24, CH-1211, Geneva, Switzerland}, month = {June} } @MISC{VG:Bri1991, vgclass = {licence}, vgproject = {unspecified}, author = {Claude Briffod}, title = {Vision \`a la {G}rossberg ({S}imulation du mod\`ele monoculaire pr\'eattentif}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {February}, year = {1991} } @TECHREPORT{VG:BrB1991, author = {C. Briffod and Pierre-Yves Burgi}, title = {Vision \`a la {G}rossberg: simulation du mod\`ele monoculaire pr\'eattentif}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1991}, vgclass = {report}, vgproject = {unspecified}, number = {91.05}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April} } @MISC{VG:Bru1987, vgclass = {licence}, vgproject = {unspecified}, author = {Denis Brunet}, title = {Conception et r\'ealisation d'un logiciel pour mod\'eliser et visualiser des objets en trois dimensions par la m\'ethode du tra\c cage de rayons}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {October}, year = {1987} } @INPROCEEDINGS{VG:BrP1993, author = {Denis Brunet and Thierry Pun}, title = {A modular architecture for asynchronous visual processing}, booktitle = {Swiss Vision'93 (5th SGAICO Symposium + 2nd Swiss IAPR Symposium), Z\"urich, Switzerland}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, pages = {37--44}, month = {September} } @INPROCEEDINGS{VG:BrP1991, author = {Denis Brunet and Thierry Pun}, title = {Multisource and color lighting for detection of small protuberances}, booktitle = {Optics, Illumination and Image Sensing for Machine Vision VI}, year = {1991}, vgclass = {refpap}, vgproject = {unspecified}, volume = {1614}, series = {SPIE Proceedings}, pages = {23--34}, address = {Boston, USA}, month = {November}, note = {(SPIE Conference on Advances in Intelligent Robotic Systems)} } @TECHREPORT{VG:BrP1991a, author = {Denis Brunet and Thierry Pun}, title = {The {P}otato {O}peration: germs detection by shadows analysis and controlled lighting}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1991}, vgclass = {report}, vgproject = {unspecified}, number = {91.03}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {May} } @INPROCEEDINGS{Bruno2007, author = {Eric Bruno and Jana Kludas and St\'ephane Marchand-Maillet}, title = {Combining Multimodal Preferences for Multimedia Information Retrieval}, booktitle = {Proc. of International Workshop on Multimedia Information Retrieval}, year = {2007}, address = {Augsburg, Germany}, month = {September}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://vision.unige.ch/publications/postscript/2007/mir2007-bruno.pdf}, vgclass = {refpap}, vgproject = {viper} } @INPROCEEDINGS{VG:BRUNO:CBMI03, author = {Eric Bruno and Stephane Marchand Maillet}, title = {Nonlinear Temporal Modeling for Motion-based Video Overviewing}, booktitle = {Proceedings of the 3rd International Workshop on Content-Based Multimedia Indexing, CBMI'03}, year = {2003}, address = {Rennes, France}, month = {September}, url = {http://vision.unige.ch/publications/postscript/2003/bruno_cbmi03.pdf}, vgclass = {refpap}, vgproject = {viper} } @INPROCEEDINGS{VG:BRUNO:GRETSI03, author = {Eric Bruno and Stephane Marchand Maillet}, title = {Pr{\'e}diction Temporelle de Descripteurs Visuels pour la Mesure de Similarit{\'e} entre Vid{\'e}os}, booktitle = {Proceedings of the GRETSI'03}, year = {2003}, address = {Paris, France}, month = {September}, url = {http://vision.unige.ch/publications/postscript/2003/bruno_gretsi03.pdf}, vgclass = {refpap}, vgproject = {viper} } @INPROCEEDINGS{bruno_amr05, author = {Eric Bruno and Nicolas Moenne-Loccoz and St{\'e}phane Marchand Maillet}, title = {Learning User Queries in Multimodal Dissimilarity Spaces}, booktitle = {Proceedings of the 3rd International Workshop on Adaptive Multimedia Retrieval, AMR'05 }, year = {2005}, address = {Glasgow, UK}, month = {July}, url = {http://vision.unige.ch/publications/postscript/2005/BrunoDissiSpaces.AMR05.pdf}, vgclass = {refpap}, vgproject = {viper} } @INPROCEEDINGS{bruno_mlmm05, author = {Eric Bruno and Nicolas Moenne-Loccoz and St{\'e}phane Marchand Maillet}, title = {Interactive Video Retrieval based on Multimodal Dissimilarity Representation}, booktitle = {Proceedings of the Machine Learning Techniques for Processing Multimedia Content- ICML workshop, MLMM'05}, year = {2005}, vgclass = {refpap}, vgproject = {viper}, address = {Bonn, Germany}, month = {August}, url = {http://vision.unige.ch/publications/postscript/2005/bruno_MLMM05.pdf}, vgclass = {refpap}, vgproject = {viper} } @ARTICLE{Bruno, author = {Eric Bruno and Nicolas Moenne-Loccoz and St\'ephane Marchand-Maillet}, title = {Design of multimodal dissimilarity spaces for retrieval of multimedia documents}, journal = {To appear in IEEE Transaction on Pattern Analysis and Machine Intelligence}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://vision.unige.ch/publications/postscript/2007/EricBrunoPAMI.2007.08.pdf}, year = {2008}, vgclass = {refpap}, vgproject = {viper} } @INPROCEEDINGS{Bruno2006, author = {Eric Bruno and Nicolas Moenne-Loccoz and St\'ephane Marchand-Maillet}, title = {Asymmetric Learning and Dissimilarity Spaces for Content-based Retrieval}, booktitle = {Proc. of International Conference on Image and Video Retrieval (CIVR)}, year = {2006}, pages = {330-339}, address = {Tempe, AZ}, month = {July}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://vision.unige.ch/publications/postscript/2006/bruno_civr06.pdf}, vgclass = {refpap}, vgproject = {viper} } @ARTICLE{BrunoPAA05, author = {Eric Bruno and Nicolas Moenne-Loccoz and Stephane Marchand-Maillet}, title = {Unsupervised Event Discrimination Based on Nonlinear Temporal Modelling of Activity}, journal = {Pattern Analysis and Application, special issue on Video Event Mining}, year = {2005}, note = {DOI: 10.1007/s10044-005-0242-9}, url = {http://vision.unige.ch/publications/postscript/2005/BrunoEventDiscrimination.PAA.pdf}, url1 = {http://www.springerlink.com/app/home/contribution.asp?wasp=b1cbf65840c14b68b90b05e5fe44bbdc\&referrer=parent\&backto=issue,2,11;journal,1,23;linkingpublicationresults,1:103609,1}, vgclass = {refpap}, vgproject = {viper} } @ARTICLE{Bruno2004, author = {Eric Bruno and Nicolas Moenne-Loccoz and St\'ephane Marchand-Maillet}, title = {Unsupervised Event Discrimination Based on Nonlinear Temporal Modelling of Activity}, journal = {Pattern Analysis and Application}, year = {2004}, volume = {7}, pages = {402-410}, number = {4}, month = {December}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://vision.unige.ch/publications/postscript/2005/BrunoEventDiscrimination.PAA.pdf}, url1 = {http://www.springerlink.com/app/home/contribution.asp?wasp=b1cbf65840c14b68b90b05e5fe44bbdc\&referrer=parent\&backto=issue,2,11;journal,1,23;linkingpublicationresults,1:103609,1}, vgclass = {refpap}, vgproject = {viper} } @CONFERENCE{Bruno2002, author = {E. Bruno and D. Pellerin}, title = {Video structuring, indexing and retrieval based on global motion wavelet coefficients }, booktitle = {Proceedings of International Conference of Pattern Recognition (ICPR)}, year = {2002}, address = {Quebec City, Canada}, month = {August}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://vision.unige.ch/publications/postscript/2002/bruno_icpr.pdf}, vgclass = {refpap}, vgproject = {viper} } @CONFERENCE{Bruno2002a, author = {E. Bruno and D. Pellerin}, title = {Video shot detection based on temporal linear prediction of motion}, booktitle = {Proceedings of the IEEE International Conference on Multimedia and Exposition (ICME)}, year = {2002}, address = {Lausanne, Switzerland}, month = {August}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://vision.unige.ch/publications/postscript/2002/bruno_icme.pdf}, vgclass = {refpap}, vgproject = {viper} } @INPROCEEDINGS{VG:PAAVBED01, author = {{\'E}ric Bruno and Nicolas Mo{\"e}nne-Loccoz and St{\'e}phane Marchand-Maillet}, title = {Unsupervised Event Discrimination Based on Nonlinear Temporal Modelling of Activity}, booktitle = {Pattern Analysis and Application {(PAA)}, special issue on Video Based Event Detection, to appear}, year = {2001}, vgclass = {refpap}, vgproject = {viper} } @MISC{VG:Buc1987, vgclass = {diploma}, vgproject = {unspecified}, author = {Markus Buchi}, title = {Labo {I}mage: conception et r\'ealisation d'un logiciel de morphologie math\'ematique binaire}, howpublished = {Diploma thesis, University of Geneva}, month = {December}, year = {1987} } @TECHREPORT{VG:Bui1997, author = {J.-F. Buisson}, title = {Environnement s\'ecuris\'e pour les watermarks}, institution = {Computer Vision Group, Computing Centre, University of Geneva and r3 Security Engineering}, year = {1997}, vgclass = {report}, vgproject = {watermarking}, number = {97.08}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {September} } @INPROCEEDINGS{VG:Bur1991, author = {Pierre-Yves Burgi}, title = {Figure-ground separation: evidence for asynchronous processing in visual perception?}, booktitle = {Proceedings 3rd SGAICO Meeting (Swiss Group for Artificial Intelligence and Cognitive Science), Biel-Bienne, Switzerland}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, pages = {36--48}, month = {October}, note = {(published as: University of Bern, Institute for Comp. Science and Mathematics, Technical Report IAM-91--004, H. Kaiser, R. Bach and H. Bunke, Eds., March 1992)} } @INPROCEEDINGS{VG:Bur1992, author = {Pierre-Yves Burgi}, title = {Active segmentation: a consequence of asynchrony in visual analysis}, booktitle = {1st Swiss Symposium on Pattern Recognition and Computer Vision, Lausanne, Switzerland}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, pages = {75--83}, month = {January} } @ARTICLE{VG:Bur1992a, author = {Pierre-Yves Burgi}, title = {Analysis and understanding of neuronal structures}, journal = {Neurocomputing}, year = {1992}, volume = {4}, pages = {137--166}, vgclass = {refpap}, vgproject = {unspecified} } @PHDTHESIS{VG:Bur1992b, author = {Pierre-Yves Burgi}, title = {Understanding the early human visual system through modeling and temporal analysis of neuronal structures}, school = {University of Geneva}, year = {1992}, type = {{P}h.{D}. {D}issertation {N}o. 2536}, address = {Switzerland}, note = {Thesis Jury: Prof.~Murat Kunt (EPF-Lausanne, CH), Dr.\ Simon Thorpe (Neurosciences, Paris, FR), Prof.~Christian Pellegrini (Geneva, CH), Prof.~Thierry Pun (director, Geneva, CH)}, vgclass = {thesis}, vgproject = {unspecified} } @INCOLLECTION{VG:BuP1991, author = {Pierre-Yves Burgi and Thierry Pun}, title = {Temporal analysis of contrast and geometric selectivity in early human visual system}, booktitle = {Channels in the Visual Nervous System: Neurophysiology, Psychophysics, Models}, publisher = {Freund}, year = {1991}, editor = {B. Blum}, vgclass = {refpap}, vgproject = {unspecified} } @ARTICLE{VG:BuP1994, author = {Pierre-Yves Burgi and Thierry Pun}, title = {Asynchronous image analysis: using the relationship luminance-to-latency to improve segmentation}, journal = {Journal of the Optical Society of America (A)}, year = {1994}, volume = {11}, pages = {1720--1726}, vgclass = {refpap}, vgproject = {unspecified}, number = {6}, month = {June} } @TECHREPORT{VG:BuP1993, author = {Pierre-Yves Burgi and Thierry Pun}, title = {Asynchrony in image analysis: using the relationship luminance-to-response-latency to improve segmentation}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1993}, vgclass = {report}, vgproject = {unspecified}, number = {93.04}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {June} } @INPROCEEDINGS{VG:BuP1991a, author = {Pierre-Yves Burgi and Thierry Pun}, title = {Figure-ground separation: evidences for asynchronous processing in visual perception?}, booktitle = {Neural Networks for Vision and Image Processing, Boston, USA}, year = {1991}, vgclass = {fullconf}, vgproject = {unspecified}, month = {May} } @INPROCEEDINGS{VG:BuP1991b, author = {Pierre-Yves Burgi and Thierry Pun}, title = {Figure-ground separation: evidences for asynchronous processing in visual perception?}, booktitle = {13th European Conference on Visual Perception, Vilnius, Lithuania}, year = {1991}, vgclass = {fullconf}, vgproject = {unspecified}, month = {August} } @INPROCEEDINGS{VG:BuP1990, author = {Pierre-Yves Burgi and Thierry Pun}, title = {Temporal analysis and modeling of the visual circuitry}, booktitle = {SGAICO'90, Swiss Group for Artificial Intelligence and Cognitive Science, Geneva, Switzerland}, year = {1990}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October} } @INPROCEEDINGS{VG:BPP1989, author = {Pierre-Yves Burgi and Thierry Pun and Christian Pellegrini}, title = {Temporal analysis and modeling of the visual circuitry}, booktitle = {12th European Conference on Visual Perception, Jerusalem-Haifa, Israel}, year = {1989}, vgclass = {fullconf}, vgproject = {unspecified}, month = {September}, note = {Also appears in: \emph{Perception}, 4(18)} } @ARTICLE{VG:BPP1989a, author = {Pierre-Yves Burgi and Thierry Pun and Christian Pellegrini}, title = {Temporal analysis and modeling of the visual circuitry}, journal = {Perception}, year = {1989}, volume = {4}, vgclass = {fullconf}, vgproject = {unspecified}, number = {18} } @MISC{VG:Cha2001, vgclass = {licence}, vgproject = {viper}, author = {Nicolas Chabloz}, title = {Cr\'eation D'un Client Pour Le Syst\`eme de Recherche D'images {\it Viper}}, howpublished = {Licence thesis (BSc), University of Geneva}, month = {October}, year = {2001}, url = {http://viper.unige.ch/demo.php} } @INPROCEEDINGS{VG:Cha1992, author = {Lawrence Chachere}, title = {A Knowledge-based approach for acquiring visual features}, booktitle = {10th Nat. Conference on AI (AAAI-92), Workshop on constrained Learning with Prior Knowledge, San-Jose, CA, USA}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, month = {July}, note = {(research summary)} } @INPROCEEDINGS{VG:Cha1992a, author = {Lawrence Chachere}, title = {A knowledge-based learning approach for acquiring characteristic visual features}, booktitle = {Proceedings SGAICO'92, Neuch\^atel, Switzerland}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, month = {September} } @INPROCEEDINGS{VG:CGP1993, author = {Lawrence Chachere and Catherine De Garrini and Thierry Pun}, title = {Extracting symbolic features defined by natural language for construction of a visual object recognition knowledge base}, booktitle = {Swiss Vision'93 (5th SGAICO Symposium + 2nd Swiss IAPR Symposium), Z\"urich, Switzerland}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, pages = {131--136}, month = {September}, note = {(Talk prepared and presented by Thierry Pun)} } @INPROCEEDINGS{VG:ChP1993, author = {Lawrence Chachere and Thierry Pun}, title = {Extracting a domain theory from natural language to construct a knowledge base for visual recognition}, booktitle = {AAAI Fall Symposium Series: Machine Learning in Computer Vision: What, Why and How?, Raleigh, NC, USA}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, pages = {85--89}, address = {Menlo-Park, CA}, month = {October}, publisher = {AAAI Press}, note = {(TR FS-93--04)} } @INPROCEEDINGS{Chanel:2007:SMC, author = {Guillaume Chanel and Karim Ansari-Asl and Thierry Pun}, title = {Valence-arousal evaluation using physiological signals in an emotion recall paradigm}, booktitle = {Proceedings of the IEEE SMC and International Conference on Systems, Man and Cybernetics, Smart cooperative systems and cybernetics: advancing knowledge and security for humanity}, year = {2007}, vgclass = {refpap}, vgproject = {bmi}, address = {Montreal, Canada}, month = {October 7--10}, owner = {beekhof}, timestamp = {2007.08.29} } @MISC{Chanel:HUMABIO:TEAPR, vgclass = {fullconf}, vgproject = {bmi}, author = {Guillaume Chanel and Karim Ansari-Asl and Thierry Pun}, title = {From thoughts to emotions: emotional state assessment using physiological recordings}, howpublished = {HUMABIO EU Project Workshop,``Securing infrastructures and enhancing safety in critical operations, Humabio physiological and behavioural biometrics for unobtrusive authentication and monitoring''}, month = {Feb 2}, year = {2007}, address = {Basel, Switzerland} } @MISC{Chanel:HUMAINE:PRPCS, vgclass = {fullconf}, vgproject = {bmi}, author = {Guillaume Chanel and Julien Kronegg and Didier Grandjean and Teodor Iulian Alecu and Thierry Pun}, title = {Pattern recognition in peripheral and central signaling}, howpublished = {Workshop on Multimodal synchronization in affective expressions, Humaine European NOE 3rd Summer School and Affective Sciences NCCR}, month = {Sept 22--24}, year = {2006}, note = {Genova, Italy (Invited long presentation)}, address = {Genova, Italy} } @INPROCEEDINGS{Chanel:MRCS:EAAEEGPERI, author = {Guillaume Chanel and Julien Kronegg and Didier Grandjean and Thierry Pun}, title = {Emotion assessment: Arousal evaluation using EEG's and peripheral physiological signals}, booktitle = {Proc. Int. Workshop Multimedia Content Representation, Classification and Security (MRCS), Special Session: Multimodal Signal Processing}, year = {2006}, vgclass = {refpap}, vgproject = {bmi}, address = {Istanbul, Turkey}, month = {Sept 11--13} } @MISC{Chanel:SIMILAR:EAPS, vgclass = {fullconf}, vgproject = {bmi}, author = {Guillaume Chanel and Julien Kronegg and Didier Grandjean and Thierry Pun}, title = {Emotion assessment using physiological signals}, howpublished = {Similar NOE Workshop}, month = {June 8--9}, year = {2006}, note = {Heraklion, Greece}, address = {Heraklion, Greece} } @TECHREPORT{CHANEL.05.02, author = {Guillaume Chanel and Julien Kronegg and Didier Grandjean and Thierry Pun}, title = {Emotion Assessment: Arousal Evaluation Using EEG's and Peripheral Physiological Signals}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2005}, vgclass = {report}, vgproject = {bmi}, month = {December 15}, abstract = {The arousal dimension of human emotions is assessed from two different physiological sources: peripheral signals and electroencephalographic (EEG) signals from the brain. A complete acquisition protocol is presented to build a physiological emotional database for real participants. Arousal assessment is then formulated as a classification problem, with classes corresponding to 2 or 3 degrees of arousal. The performance of 2 classifiers has been evaluated, on peripheral signals, on EEG's, and on both. Results confirm the possibility of using EEG's to assess the arousal component of emotion, and the interest of multimodal fusion between EEG's and peripheral physiological signals.}, url = {http://vision.unige.ch/publications/postscript/2005/RAPPORT_TECH_05.02.pdf} } @MISC{Chanel:SIMILAR:EAPS2, vgclass = {fullconf}, vgproject = {bmi}, author = {Guillaume Chanel and Julien Kronegg and Thierry Pun}, title = {Emotion assessment using physiological signals}, howpublished = {Similar NOE Workshop}, month = {November 9--10}, year = {2005}, note = {Barcelona, Spain}, address = {Barcelona, Spain} } @TECHREPORT{VG:Che1997, author = {Michel Cherbuliez}, title = {Wavelet-Based Image Querying}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1997}, vgclass = {report}, vgproject = {dvp,cbir}, number = {97.02}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {February} } @MISC{VG:Che1997a, vgclass = {diploma}, vgproject = {dvp,cbir}, author = {Michel Cherbuliez}, title = {Content-based image querying}, howpublished = {Diploma thesis, University of Geneva}, month = {October}, year = {1997}, abstract = {In this document, we investigate the problem of performing content-based image retrieval on a database containing several hundreds of images. The goal is to facilitate the task of television broadcasters, and specifically archivists, while looking for a piece of news or a documentary. Currently, they perform a text-based query in a database, and then visualize numerous video tapes to find the specific clip they were looking for. Content-based search opens new horizons for performing this task because it is faster and more user-friendly. We describe two methods for content-based image retrieval. The first one is based on the Haar wavelet decompositions of images, which has already been used for image retrieval. We propose enhancements and optimizations to get more accurate results. The second method is a novel one, and exploits invariant properties of the Fourier-Mellin transform in order to overcome some limitations of the wavelet-based method. We finally compare both methods and discuss about the results we obtained. We show that the results given by the Fourier-Mellin based method are better suited for content-based image retrieval.}, keywords = {Content based, image retrieval, data-mining, wavelet transforms, Fourier transform, logarithmic polar transform} } @MISC{VG:Cro2001, vgclass = {licence}, vgproject = {viper}, author = {Rita Crotta}, title = {Le D\'eveloppement D'outils de Recherche Dans Une Base de Donn\'ees Multim\'edia}, howpublished = {Licence thesis, CESID, University of Geneva}, month = {October}, year = {2001} } @INPROCEEDINGS{VG:CD1999, author = {Gabriella Csurka and Fr{\'e}d{\'e}ric Deguillaume and Joseph J. K. {{\'O}~Ruanaidh} and Thierry Pun}, title = {A {B}ayesian approach to affine transformation resistant image and video watermarking}, booktitle = {International Workshop on Information Hiding}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, volume = {LNCS 1768}, series = {Lecture Notes in Computer Science}, pages = {270--285}, address = {Dresden, Germany}, month = {29~September~--1~October}, publisher = {Springer Verlag}, abstract = {This paper proposes a new approach for assessing the presence of a digital watermark in images and videos. This approach relies on a Bayesian formulation that allows to compute the probability that a watermark was generated using a given key. The watermarking itself relies on the discrete Fourier transform (DFT) of the image, of video frames or of three dimensional chunks of video scene. Two kinds of information are hidden in the digital data: a watermark and a template. Both are encoded using an owner key to ensure the system security and are embedded in the 2D or 3D DFT magnitude of the image or video. The watermark is encoded in the form of a spread spectrum signal. The template is a key based grid and is used to detect and invert the effect of an affine geometric transformation (rotations, scaling and/or aspect ratio change) or in the case of the video frame-rate changes, aspect-ratio modification and rescaling of frames. It is shown that, for the spread spectrum signal described in the paper, it is possible to positively detect the presence of a watermark without necessarily decoding it, given only the key used to generate it. To do that, the Bayesian approach allows the deduction of the relative log-probability of the presence of a watermark in an image given only the key. All that is required for positive watermark verification is the key. This approach also allows to infer the number of bits contained in the watermark. The performance of the presented techniques and the usefulness of the relative log-probability are shown through various applications and experimental results.}, url = { http://vision.unige.ch/publications/postscript/99/CsurkaDeguillaumeORuanaidhPun_wih99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/CsurkaDeguillaumeORuanaidhPun_wih99.pdf} } @INPROCEEDINGS{VG:CDO1999, author = {Gabriella Csurka and Fr{\'e}d{\'e}ric Deguillaume and Joseph J. K. {{\'O}~Ruanaidh} and Thierry Pun}, title = {Tatouage d'images bas\'e sur la transform\'ee de Fourier discr\`ete}, booktitle = {5\`emes Journ\'ees d'\'etudes et d'\'echanges ``Compression et Repr\'esentation des Signaux Audiovisuels'' (CORESA 99)}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, address = {Sophia-Antipolis, Alpes-Maritimes, France}, month = {14--15 juin}, abstract = {Le tatouage d'images est un champ de recherche r\'ecent et tr\`es prometteur, ayant pour but de d\'ecourager la copie et la distribution illicite de mat\'eriel prot\'eg\'e, ainsi que la protection de la propri\'et\'e intellectuelle des donn\'ees digitales. L'id\'ee de base est d'ins\'erer une information sous la forme d'un filigrane digital concernant le propri\'etaire de l'image, de m\^eme que des instructions concernant son copyright. Il est important que d'un c\^ot\'e l'extraction ou la suppression de cette information de l'image soit difficile voire impossible, et d'un autre c\^ot\'e que la distorsion introduite dans l'image par le filigrane soit minimale et invisible \ldots}, url = { http://vision.unige.ch/publications/postscript/99/CsurkaDeguillaumeORuanaidhPun_coresa99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/CsurkaDeguillaumeORuanaidhPun_coresa99.pdf} } @PHDTHESIS{VG:Deg2002, author = {Fr{\'e}d{\'e}ric Deguillaume}, title = {Hybrid robust watermarking and tamperproofing of visual media}, school = {Computer Vision and Multimedia Laboratory, University of Geneva}, year = {2002}, address = {Geneva, Switzerland}, month = {October}, vgproject = {watermarking} } @TECHREPORT{VG:Deg1997, author = {Fr{\'e}d{\'e}ric Deguillaume}, title = {Segementation de films vid\'eos, et caract\'erisation des mouvements de cam\'era}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1997}, vgclass = {report}, vgproject = {dvp,cbir}, number = {97.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {February} } @MISC{VG:Deg1997a, vgclass = {diploma}, vgproject = {dvp,cbir}, author = {Fr{\'e}d{\'e}ric Deguillaume}, title = {Segmentation de Clips Vid\'eo et Caract\'erisation des Mouvements de la Cam\'era}, howpublished = {Diploma thesis, University of Geneva}, month = {December}, year = {1997} } @INPROCEEDINGS{VG:DCO1999, author = {Fr{\'e}d{\'e}ric Deguillaume and Gabriella Csurka and Joe J. K. {{\'O}~Ruanaidh} and Thierry Pun}, title = {Robust {3D} {DFT} Video Watermarking}, booktitle = {IS\&T/SPIE's 11th Annual Symposium, Electronic Imaging '99: Security and Watermarking of Multimedia Contents}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, editor = {Wah Wong, Ping and Edward J. Delp}, volume = {3657}, series = {SPIE Proceedings}, pages = {113--124}, address = {San Jose, California USA}, month = {23--29~January}, note = {Paper EI 3657-13 (Program on Multimedia Processing and Applications)}, abstract = {This paper proposes a new approach for digital watermarking and secure copyright protection of videos, the principal aim being to discourage illicit copying and distribution of copyrighted material. The method presented here is based on the discrete Fourier transform (DFT) of three dimensional chunks of video scene, in contrast with previous works on video watermarking where each video frame was marked separately, or where only intra-frame or motion compensation parameters were marked in MPEG compressed videos. Two kinds of information are hidden in the video: a watermark and a template. Both are encoded using an owner key to ensure the system security and are embedded in the 3D DFT magnitude of video chunks. The watermark is a copyright information encoded in the form of a spread spectrum signal. The template is a key based grid and is used to detect and invert the effect of frame-rate changes, aspect-ratio modification and rescaling of frames. The template search and matching is performed in the log-log-log map of the 3D DFT magnitude. The performance of the presented technique is evaluated experimentally and compared with a frame-by-frame 2D DFT watermarking approach.}, keywords = {video watermarking, MPEG, 3D discrete Fourier transform, log-polar-log and log-log-log mapping, spread spectrum}, url = { http://vision.unige.ch/publications/postscript/99/DeguillaumeCsurkaORuanaidhPun_eiswmc99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/DeguillaumeCsurkaORuanaidhPun_eiswmc99.pdf} } @INPROCEEDINGS{VG:DCP2000, author = {Fr{\'e}d{\'e}ric Deguillaume and Gabriella Csurka and Thierry Pun}, title = {Countermeasures for unintentional and intentional video watermarking attacks}, booktitle = {IS\&T/SPIE's 12th Annual Symposium, Electronic Imaging 2000: Security and Watermarking of Multimedia Content II}, year = {2000}, vgclass = {refpap}, vgproject = {watermarking}, editor = {Wah Wong, Ping and Edward J. Delp}, volume = {3971}, series = {SPIE Proceedings}, address = {San Jose, California USA}, month = {23--28~January}, note = {(Paper EI 3971-33)}, abstract = {The rapidly growing digital multimedia market has revealed an urgent need for effective copyright protection mechanisms. Therefore, digital audio, image and video watermarking has recently become a very active area of research. Many important issues have been pointed out, one of them being the robustness to non-intentional and intentional attacks. This paper studies some attacks and proposes countermeasures applied to videos. General attacks are lossy copying/transcoding (such as MPEG compression and digital/analogic conversion), changes of frame-rate, changes of display format, and geometrical distortions. More specific attacks are sequence edition, and statistical attacks such as averaging or collusion. Averaging attack consists of the local averaging of consecutive frames in order to cancel the watermark. This attack works well for schemes which embed random independent marks into frames. In collusion attacks the watermark is first estimated by averaging frames from different scenes, and is then substracted from each frame. Collusion works well when the same mark was embedded in all frames. The proposed countermeasure first ensures robustness to general attacks by Spread Spectrum encoding of the watermark in the frequency domain and by the use of an additional synchronization template. Secondly, a Bayesian criterion which evaluates the probability of a correctly decoded watermark, is used for the rejection the of outliers, that is of incorrect watermarks. This Bayesian approach also allows to resit to statistical attacks. The idea is to embed randomly chosen marks among a finite set of marks, into subsequences of videos which are long enough to resist averaging attacks, but short enough to avoid collusion attacks. The Bayesian criterion is needed to select the correct mark at the decoding step. Finally, the paper presents experimental results showing the robustness of the proposed method.}, url = { http://vision.unige.ch/publications/postscript/2000/DeguillaumeCsurkaPun_spie2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/DeguillaumeCsurkaPun_spie2000.pdf} } @INPROCEEDINGS{Deguillaume:2005:ICME05, author = {Fr\'{e}d\'{e}ric Deguillaume and Y. Rytsar and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Data-hiding based text document security and automatic processing}, booktitle = {IEEE International Conference on Multimedia \& Expo (ICME) 2005}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Amsterdam, The Netherlands}, month = {July 6-8}, note = {submitted} } @MISC{VG:DVPMP2001, vgclass = {otherjournals}, vgproject = {watermarking}, author = {Fr{\'e}d{\'e}ric Deguillaume and Sviatoslav Voloshynovskiy and Shelby Pereira and Maribel Madue{\~n}o and Thierry Pun}, title = {Filigranage D'images Digitales}, howpublished = {Bull. ASE/SEV}, month = {April}, year = {2001}, pages = {19-27}, volume = {9} } @MISC{Deguillaume:2004:CVG, vgclass = {patent}, vgproject = {watermarking}, author = {Fr{\'e}d{\'e}ric Deguillaume and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Character and vector graphics watermark for structured electronic documents security}, howpublished = {US Patent Application 10/949,318}, month = {September 27}, year = {2004}, note = {(pending)} } @ARTICLE{Deguillaume:2003:SHR, author = {Fr{\'e}d{\'e}ric Deguillaume and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Secure hybrid robust watermarking resistant against tampering and copy-attack}, journal = {Signal Processing}, year = {2003}, volume = {83}, pages = {2133--2170}, vgclass = {refpap}, vgproject = {watermarking}, number = {10}, month = {October}, url = {http://vision.unige.ch/publications/postscript/2003/SP-SpecialSection2003_SecureHybridRobustWatermarking.pdf} } @INPROCEEDINGS{VG:DVP2002b, author = {Fr{\'e}d{\'e}ric Deguillaume and Sviatoslav Voloshynovskiy and Thierry Pun}, title = { Method for the Estimation and Recovering from General Affine Transforms in Digital Watermarking Applications}, booktitle = {SPIE Photonics West, Electronic Imaging 2002, Security and Watermarking of Multimedia Contents IV}, year = {2002}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, CA, USA}, month = {January 20-24}, url = {http://vision.unige.ch/publications/postscript/2002/DeguillaumeVoloshynovskiyPun_SPIE2002.ps.gz}, url1 = {http://vision.unige.ch/publications/postscript/2002/DeguillaumeVoloshynovskiyPun_SPIE2002.pdf} } @MISC{VG:DVP2002c, vgclass = {patent}, vgproject = {watermarking}, author = { Fr{\'e}d{\'e}ric Deguillaume and Sviatoslav Voloshynovskiy and Thierry Pun}, title = { A method for hybrid robust watermarking and tamper proofing}, howpublished = {US Patent Application}, month = {filed June 2, 2002}, year = {2002} } @MISC{VG:DVP2002d, vgclass = {patent}, vgproject = {watermarking}, author = { Fr{\'e}d{\'e}ric Deguillaume and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {A method for the estimation and recovering of general affine transform}, howpublished = {US Patent Application}, month = {filed January 19, 2002}, year = {2002} } @INPROCEEDINGS{VG:DVP2002f, author = {Fr{\'e}d{\'e}ric Deguillaume and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Hybrid robust watermarking resistant against copy attack}, booktitle = {Proceedings of the European Signal Processing Conference {(EUSIPCO2002)}}, year = {2002}, vgclass = {refpap}, vgproject = {watermarking}, address = {Toulouse, France}, month = {September}, url = {http://vision.unige.ch/publications/postscript/2002/DeguillaumeVoloshynovskiyPun_EUSIPCO2002.pdf} } @INPROCEEDINGS{VG:DSM1992, author = {J.-D. Dessimoz and P.-A. Sch{\"u}pbach and A. Mercier and Thierry Pun}, title = {Do {I} need a robot or a non-robot automated system?}, booktitle = {Proceedings 1992 IEEE/RSJ Conference on Intelligent Robots and Systems, Raleigh, North Carolina, USA}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, pages = {1161--1168}, month = {July} } @INPROCEEDINGS{VG:DSM1992a, author = {J.-D. Dessimoz and P.-A. Sch{\"u}pbach and A. Mercier and Thierry Pun}, title = {Choosing a robot versus another automated system}, booktitle = {Proceedings 23rd International Symposium on Industrial Robots, Barcelona, Spain}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, pages = {661--666}, month = {October} } @MISC{Deville:2007:NOE, vgclass = {fullconf}, vgproject = {bmi}, author = {Beno\^{i}t Deville and Guido Bologna and Michel Vinckenbosch and Thierry Pun}, title = {Guiding the focus of attention of blind people using saliency}, howpublished = {Similar NOE Workshop}, month = {June 4--5}, year = {2007}, note = {University of Magdeburg, Germany}, address = {University of Magdeburg, Germany}, booktitle = {Similar NOE Workshop}, owner = {beekhof}, timestamp = {2007.08.29} } @MISC{VG:Dou1999, vgclass = {licence}, vgproject = {unspecified}, author = {Daniel Doubrovkine}, title = {Rx cervicales, {S}yst\`eme d'analyse pour la radiologie cervicale fonctionelle}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {March}, year = {1999}, note = {(En collaboration avec le Dr. Paul Cohen, chef de clinique adjoint de la clinique de r\'e\'education de l'H\^opital Cantonal de Gen\`eve.)}, abstract = {Dans leur travail quotidien avec des patients, des chirurgien et des neurologues tr\`es sp\'ecialis\'es sont amen\'es \`a examiner des centaines d'images radiographi\'ees et \`a d\'etecter des dizaines d'anomalies telles que des d\'eplacements vert\'ebraux. Ce travail minutieux n\'ecessite un professionnalisme sans \'egal et une concentration extr\^eme. Les cas \'etudi\'es ne pr\'esentent que tr\`es rarement des probl\`emes visibles \`a l'\oeil nu et des mesures particuli\`erement pr\'ecises d\'ecident toujours d'un besoin d'intervention du m\'edecin. Ainsi, les h\^opitaux utilisent des techniques d'avant-garde en mati\`ere d'informatique et ont pouss\'e le d\'eveloppement de logiciels aidant le m\'edecin dans son travail avec les patients. D\'esormais, le domaine de l'imagerie m\'edicale et plus particuli\`erement celui du traitement d'images radiographi\'ees propose un vaste champ d'application pour des travaux de recherche. Dans le pr\'esent document nous nous int\'eressons aux radiographies de patients en traitement \`a l'H\^opital Cantonal Universitaire de Gen\`eve et plus particuli\`erement de la Clinique de R\'e\'education. Nous pr\'esentons tout d'abord une base logicielle pour des applications dans le domaine d'imagerie m\'edicale suivie d'une automatisation de mesures sur les angles intervert\'ebraux. De nombreux groupes de recherche se sont int\'eress\'es aux coupes effectu\'ees par des scanners IRM et ont produit des logiciels d'analyse pouss\'es. Les aspects comme la simulation en trois dimensions et la m\'edecine \`a distance sont largement explor\'es. En revanche, nous offrons une approche plus ax\'ee sur les mesures de distances et d'angles. Ainsi, Rx-Cervicales, le logiciel d\'evelopp\'e dans le cadre de ce travail offre principalement une base vectorielle mais n'omet toutefois point l'aspect traitement d'images gr\^ace \`a de nombreux filtres. Rx-Cervicales permet \'egalement de superposer des images, d'en modifier la taille et d'effectuer des d\'eplacements et des rotations libres. Par la suite, nous \'etudions ici la reconnaissance de contours sur des calques de radiographies et permettons au m\'edecin de mesurer des angles entre deux clich\'es de flexion et d'extension de la colonne cervicale ou lombaire du m\^eme patient puis de comparer ces r\'esultats avec des valeurs d'individus sains. Ainsi, des anomalies peuvent \^etre d\'etect\'ees par l'ordinateur en quelques secondes. Notons que notre produit est directement utilis\'e par la Clinique de R\'e\'education de l'HCUG. En conclusion, soulignons que malgr\'e le nombre important de groupes de recherche et d'institutions travaillant dans ce domaine, il n'existe pas \`a notre connaissance, de logiciels semblables \`a celui propos\'e dans le pr\'esent travail de recherche. Donc, nous fournissons un outil, muni d'une premi\`ere application, qui montre l'efficacit\'e de l'approche utilis\'ee et laisse entrevoir de larges perspectives d'avenir.}, url = {http://cui.unige.ch/~doubrov5/uni/license/}, url1 = { http://vision.unige.ch/publications/postscript/99/Doubrovkine_licence99.ps.gz}, url2 = { http://vision.unige.ch/publications/postscript/99/Doubrovkine_licence99.pdf} } @ARTICLE{VG:DDP1992, author = {B. Dubrez and Alain Jacot-Descombes and Thierry Pun and G. Cimasoni}, title = {Comparison of photodensitometric with high-resolution digital analysis of bone density from serial dental radiographs}, journal = {Journal of Dentomaxilofacial Radiology}, year = {1992}, volume = {21}, pages = {40--44}, vgclass = {refpap}, vgproject = {unspecified}, month = {February} } @ARTICLE{VG:DJC1995, author = {B. Dubrez and S. Jacot-Descombes and G. Cimasoni}, title = {Reliability of a paralleling instrument for dental radiographs}, journal = {Journal of Oral Surgery, Oral Medicine, Oral Pathology}, year = {1995}, volume = {80}, pages = {358--364}, vgclass = {refpap}, vgproject = {unspecified}, number = {3}, month = {September} } @TECHREPORT{VG:Dur1992, author = {E. Durante}, title = {La dynamique des r\'eseaux de neurones}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1992}, vgclass = {report}, vgproject = {unspecified}, number = {93.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {September}, note = {(Diploma work, performed under the supervision of Pierre-Yves Burgi)} } @MISC{VG:Dur1992a, vgclass = {diploma}, vgproject = {unspecified}, author = {Ernesto Durante}, title = {La dynamique des r\'eseaux de neurones}, howpublished = {Diploma thesis, University of Geneva}, month = {September}, year = {1992} } @TECHREPORT{VG:Gar1995, author = {Catherine De Garrini}, title = {Exploratory statistics for automated structuration of large image databases}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1995}, vgclass = {report}, vgproject = {cbir}, number = {95.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {September} } @TECHREPORT{VG:Gar1994, author = {Catherine De Garrini}, title = {D\'etermination de la translation, de la rotation et du facteur d'echelle d'un objet dans differents contextes}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {94.08}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {October}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/degarrin/94.10.report.ps.Z} } @MISC{VG:Gar1993, vgclass = {diploma}, vgproject = {unspecified}, author = {Catherine De Garrini}, title = {Qualification et reconstruction de formes g\'eom\'etriques simples}, howpublished = {Diploma thesis, University of Geneva}, month = {December}, year = {1993} } @MISC{VG:DeG1998, vgclass = {diploma}, vgproject = {cbir}, author = {Andr{\'e} De~Giacomi}, title = {Structures d'indexation efficaces pour archivage / recherche dans des bases de donn\'ees multim\'edia}, howpublished = {Diploma thesis, University of Geneva}, month = {April}, year = {1998}, note = {(Travail r\'ealis\'e au sein du groupe de Vision par ordinateur, dans le cadre d'un dipl\^ome du CNAM, Conservatoire National des Arts et M\'etiers, France)} } @PHDTHESIS{VG:Gil1997, author = {Sylvia Gil}, title = {Robust object tracking in video sequences by integration of multiple visual features}, school = {University of Geneva}, year = {1997}, type = {{P}h.{D}. {D}issertation {N}o. 2929}, address = {Switzerland}, month = {July}, note = {Thesis Jury: Prof.~Murat Kunt (EPF-Lausanne, CH), Dr.\ Dieter Koller (Caltech and Autodesk, USA), Prof.~Christian Pellegrini (Geneva, CH), Prof.~Thierry Pun (director, Geneva, CH)}, vgclass = {thesis}, vgproject = {unspecified} } @TECHREPORT{VG:Gil1994, author = {Sylvia Gil}, title = {D\'etection de mouvement dans une sc\`ene de trafic interurbain: analyse des r\'esultats}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {94.02}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {January} } @TECHREPORT{VG:Gil1994a, author = {Sylvia Gil}, title = {Comptage de v\'ehicules pour trafic interurbain: une \'etude pr\'eliminaire}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {94.04}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April} } @INPROCEEDINGS{VG:GLG1992a, author = {Sylvia Gil and Marc Lefebvre and M.-A. Glassey and C. Baur and C. W. Burckhardt and R. Clavel and Thierry Pun}, title = {{O}p\'eration {P}atate: {V}ision par ordinateur en robotique agricole}, booktitle = {Actes 14\`emes Journ\'ees Francophones sur l'Informatique: Imagerie Num\'erique, M\'ethodes et Applications, Gen\`eve, Switzerland}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, pages = {1--5}, month = {April}, url = {ftp://ftp@cui.unige.ch/PUBLIC/vision/papers/gil/jf.ps.Z} } @INPROCEEDINGS{VG:GLG1992, author = {Sylvia Gil and Marc Lefebvre and M.-A. Glassey and C. Baur and Thierry Pun}, title = {3{D} Image analysis for agricultural robotics: the {P}otato {O}peration}, booktitle = {Eusipco 92, 6th European Signal Processing Conference, Brussels, Belgium}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, pages = {1781--1784}, month = {August}, keywords = {VG:GLG1992key}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/gil/eusipco.ps.Z} } @ARTICLE{VG:GiM1993, author = {Sylvia Gil and Ruggero Milanese}, title = {Scientific training in the {USA}}, journal = {SI-Information, Bulletin of the Swiss Association for Computer Science}, year = {1993}, volume = {38}, vgclass = {otherjournals}, vgproject = {unspecified}, month = {March} } @INPROCEEDINGS{VG:GMP1994, author = {Sylvia Gil and Ruggero Milanese and Thierry Pun}, title = {Feature selection for object tracking in traffic scenes}, booktitle = {Intelligent Vehicle Highway Systems}, year = {1994}, vgclass = {refpap}, vgproject = {unspecified}, editor = {Richard J. Becherer}, volume = {2344}, series = {SPIE Proceedings}, pages = {253--266}, address = {Boston, USA}, month = {November}, abstract = {This paper describes a motion-analysis system, applied to the problem of vehicle tracking in real-world highway scenes. The system is structured in two stages. In the first one, a motion-detection algorithm performs a figure/ground segmentation, providing binary masks of the moving objects. In the second stage, vehicles are tracked for the rest of the sequence, by using Kalman filters on two state vectors, which represent each target's position and velocity. A vehicle's motion is represented by an affine model, taking into account translations and scale changes. Three types of features have been used for the vehicle's description state vectors. Two of them are contour-based: the bounding box and the centroid of the convex polygon approximating the vehicles contour. The third one is region-based and consists of the 2-D pattern of the vehicle in the image. For each of these features, the performance of the tracking algorithm has been tested, in terms of the position error, stability of the estimated motion parameters, trace of the motion model's covariance matrix, as well as computing time. A comparison of these results appears in favor of the use of the bounding box features.}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/gil/spie94.ps.Z} } @INPROCEEDINGS{VG:GMP1996a, author = {Sylvia Gil and Ruggero Milanese and Thierry Pun}, title = {Combining multiple motion estimates for vehicle tracking}, booktitle = {Computer Vision - ECCV 96, Cambridge, UK}, year = {1996}, vgclass = {refpap}, vgproject = {unspecified}, editor = {B. Buxton and R. Cipolla}, number = {1064}, series = {Lecture Notes in Computer Science}, pages = {307--320}, month = {April}, publisher = {Springer-Verlag}, note = {(Proceedings of the 4th European Conference Computer Vision, Volume II)} } @INPROCEEDINGS{VG:GMP1997, author = {Sylvia Gil and Ruggero Milanese and Thierry Pun}, title = {Motion estimates combination for object tracking}, booktitle = {Proceedings of the 30th ISATA, Symposium on Automotive Technology and Automation}, year = {1997}, vgclass = {refpap}, vgproject = {unspecified}, pages = {109--117}, address = {Florence, Italy}, month = {June}, note = {Topical Track on Robotics, Motion and Machine Vision in the Automotive Industry} } @ARTICLE{VG:GMP1996, author = {Sylvia Gil and Ruggero Milanese and Thierry Pun}, title = {Comparing features for target tracking in traffic scenes}, journal = {Pattern Recognition}, year = {1996}, volume = {29}, pages = {1285--1296}, vgclass = {refpap}, vgproject = {unspecified}, number = {8}, month = {August} } @INPROCEEDINGS{VG:GiP1993, author = {Sylvia Gil and Thierry Pun}, title = {Non-linear multiresolution relaxation for alerting}, booktitle = {Proceedings of the 11th European Conference on Circuit Theory and Design, Davos, Switzerland}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, editor = {H. Dedieu}, pages = {1639--1644}, month = {August}, publisher = {Elsevier Science Publishers}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/gil/ecctd.ps.Z} } @INPROCEEDINGS{VG:GiP1993a, author = {Sylvia Gil and Thierry Pun}, title = {Multiresolution alerting for motion detection}, booktitle = {Proceedings of the 14th GRETSI Symposium on Signal and Image Processing, Juan-les-Pins}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, pages = {903--906}, month = {September}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/gil/gretsi.ps.Z} } @MISC{VG:Ger1989, vgclass = {diploma}, vgproject = {unspecified}, author = {Christian Girard}, title = {Conception et r\'ealisation d'un logiciel modulaire et portable de segmentation d'images \`a niveaux de gris}, howpublished = {Diploma thesis, University of Geneva}, month = {December}, year = {1989} } @MISC{VG:Ham1993, vgclass = {diploma}, vgproject = {unspecified}, author = {Sarah Hamdan}, title = {Analyse et extraction d'attributs d'images de texture}, howpublished = {Diploma thesis, University of Geneva}, month = {February}, year = {1993} } @MISC{VG:Ham1999, vgclass = {diploma}, vgproject = {unspecified}, author = {R{\'e}mi Hammerli}, title = {Logiciel de contr\^ole d'une orth\`ese pour myopathes}, howpublished = {Diploma thesis, University of Geneva}, month = {October}, year = {1999}, note = {(Travail r\'ealis\'e \`a l'Ecole d'Ing\'enieurs de Gen\`eve, prof. Ren\'e Beuchat)} } @INCOLLECTION{VG:HBA1990, author = {R. Haralick and H. Bunke and K. Ammon and N. Bartneck and F. Casacuberta and D. Hita and O. V. Larsen and A. Leduc and Thierry Pun and L. Quan and A. Sanfeliu and B. Wrobel}, title = {Hybrid methods, Report of the Working Group}, booktitle = {Structural Pattern Analysis}, publisher = {World Scientific}, year = {1990}, editor = {R. Mohr and T. Pavlidis and A. Sanfeliu}, pages = {245--247}, vgclass = {otherjournals}, vgproject = {unspecified} } @MISC{VG:Har1999, vgclass = {diploma}, vgproject = {abweb}, author = {Eric Harth}, title = {Plate-forme de Sonification Dynamique de Pages Web Pour Aveugles et Malvoyants}, howpublished = {Diploma thesis, University of Geneva}, month = {September}, year = {1999} } @ARTICLE{VG:Her1999, author = {Alexander Herrigel}, title = {Eigentum sch\"utzen mit Wasserzeichen}, journal = {Computerworld}, year = {1999}, pages = {A14--A16}, vgclass = {otherjournals}, vgproject = {watermarking}, number = {6}, month = {8~February}, note = {(special issue: Internet)} } @INPROCEEDINGS{VG:Her1998, author = {Alexander Herrigel}, title = {Copyright protection for multimedia data based on asymmetric cryptographic techniques}, booktitle = {Electronic Imaging: Processing, Printing and Publishing in Colour}, year = {1998}, vgclass = {refpap}, vgproject = {watermarking}, series = {SPIE Proceedings}, address = {Z\"urich, Switzerland}, month = {May}, note = {({SPIE}/{IST}/{E}uropto Symposium on Advanced Imaging and Network Technologies)}, abstract = {This paper presents a new approach for the copyright protection of digital multimedia data. The system applies cryptographic protocols and a public key technique for different purposes, namely encoding/decoding a digital watermark generated by any spread spectrum technique and the secure transfer of watermarked data from the sender to the receiver in a commercial business process. The public key technique is applied for the construction of a one-way watermark embedding and verification function to identify and prove the uniqueness of the watermark. In addition, our approach provides secure owner authentication data who has initiated the watermark process for a specific data set. Legal dispute resolution is supported for multiple watermarking of digital data without revealing the confidential keying information.} } @INPROCEEDINGS{VG:HOP1998, author = {Alexander Herrigel and Joe J. K. {{\'O}~Ruanaidh} and Holger Petersen and Shelby Pereira and Thierry Pun}, title = {Secure copyright protection techniques for digital images}, booktitle = {Information Hiding}, year = {1998}, vgclass = {refpap}, vgproject = {watermarking}, editor = {David Aucsmith}, volume = {1525}, series = {Lecture Notes in Computer Science}, pages = {169--190}, address = {Berlin}, publisher = {Springer}, note = {(Second International Workshop IH'98, Portland, OR, USA, April~15--17, 1998)}, abstract = {This paper presents a new approach for the secure and robust copyright protection of digital images. A system for generating digital watermarks and for trading watermarked images is described. The system is based on a new watermarking technique, which is robust against image transformation techniques such as compression, rotation, translation, scaling and cropping. It uses modulation of the magnitude components in Fourier space to embed a watermark and an accompanying template. During the watermark extraction,the template is read in the log polar transform of the frequency domain. The template is used for analyzing scaling and rotation suffered by the watermarked stego-image. The detection of the watermarks is also possible without any need for the original cover-image. In addition, the system applies asymmetric cryptographic protocols for different purposes, namely embedding/detecting the watermark and transferring watermarked data. The public key technique is applied for the construction of a one-way watermark embedding and the verification function to identify and prove the uniqueness of the watermark. Legal dispute resolution is supported for the multiple watermarking of a digital image without revealing the confidential keying information.}, isbn = {3-540-65386-4}, url = { http://vision.unige.ch/publications/postscript/98/HerrigelORuanaidhPetersenPereiraPun_ih98.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/HerrigelORuanaidhPetersenPereiraPun_ih98.pdf}, url2 = {http://link.springer.de/link/service/series/0558/tocs/t1525.htm} } @MISC{VG:HOP1997, vgclass = {patent}, vgproject = {watermarking}, author = {Alexander Herrigel and Joe J. K. {{\'O}~Ruanaidh} and Thierry Pun}, title = {Method for generating digital watermarks and for exchanging data containing digital watermarks}, howpublished = {International Patent Application, September 1997, Sept. 1998, March 2000}, year = {1997} } @INPROCEEDINGS{VG:HPO1997, author = {Alexander Herrigel and Adrian Perrig and Joe J. K. {{\'O}~Ruanaidh}}, title = {A copyright protection environment for digital images}, booktitle = {VIS 97, Verlassliche Informationssysteme, Gesellschaft fuer Informatik}, year = {1997}, vgclass = {refpap}, vgproject = {watermarking}, address = {Freiburg, Germany}, month = {September} } @INPROCEEDINGS{VG:HeP1999, author = {Alexander Herrigel and Thierry Pun}, title = {Digital Copyright Protection for Multimedia Documents}, booktitle = {Telecom 99}, year = {1999}, vgclass = {otherjournals}, vgproject = {watermarking}, address = {Geneva, Switzerland}, month = {10--17~October}, url = { http://vision.unige.ch/publications/postscript/99/HerrigelPun_telecom99.pdf} } @INPROCEEDINGS{VG:HV2001, author = {Alexander Herrigel and Sviatoslav Voloshynovskiy}, title = {Counterfeit Attacks against a new Currency Protection Scheme}, booktitle = { Int. Conf. on Communications and Multimedia Security CMS2001}, year = {2001}, vgclass = {refpap}, vgproject = {watermarking}, editor = { }, address = { Darmstadt, Germany}, month = {May 21-22} } @INPROCEEDINGS{VG:HeV1998, author = {Alexander Herrigel and Sviatoslav Voloshynovskiy}, title = {Copyright and content protection for digital images based on asymmetric cryptographic techniques}, booktitle = {Multimedia and Security Workshop, Sixth ACM International Multimedia Conference}, year = {1998}, vgclass = {refpap}, vgproject = {watermarking}, editor = {J. Dittman and P. Horster and P. Wohlmacher}, pages = {99--112}, address = {Bristol, U.K.}, month = {September}, abstract = {This paper presents a new approach for the copyright protection of digital multimedia data. The system applies cryptographic protocols and a public key technique for different purposes, namely encoding/decoding a digital watermark generated by any spread spectrum technique and the secure transfer of watermarked data from the sender to the receiver in a commercial business process. The public key technique is applied for the construction of a one-way watermark embedding and verification function to identify and prove the uniqueness of the watermark. Our approach provides secure owner authentication data who has initiated the watermark process for a specific data set. Legal dispute resolution is supported for multiple watermarking of digital data without revealing the confidential keying information. Content protection for images is provided by ciphering/deciphering the data in the transform domain.} } @INPROCEEDINGS{VG:HVH1999, author = {Alexander Herrigel and Sviatoslav Voloshynovskiy and Z. Hrytskiv}, title = {Optical/digital identification/verification system based on digital watermarking technology}, booktitle = {SPIE International Workshop on Optoelectronic and Hybrid Optical/Digital Systems for Image/Signal Processing ODS'99}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, series = {SPIE Proceedings}, address = {Lviv, Ukraine}, month = {20--24~sep}, abstract = {This paper presents a new approach for the secure integrity verification of driver licenses, passports or other analogue identification documents. The system embeds (detects) the reference number of the identification document with the DCT watermark technology in (from) the owner photo of the identification document holder. Since the watermark technology is resistant against many image distortions such as affine transformations, lossy compression, quantization, dithering and other common image processing operations, the owner photo my even be damaged without any performance decrease in the detection process. During verification the reference number is extracted and compared with the reference number printed in the in the identification document. The approach combines optical and digital image processing techniques. The detection system must be able to scan an analogue driver license or passport, convert the image of this document into a digital representation and then apply the watermark verification algorithm to check the payload of the embedded watermark. If the payload of the watermark is identical with the printed visual reference number of the issuer, the verification was successful and the passport or driver license has not been modified. This approach constitutes a new class of application for the watermark technology, which was originally targeted for the copyright protection of digital multimedia data. The presented approach substantially increases the security of the analogue identification documents applied in many European countries.}, url = { http://vision.unige.ch/publications/postscript/99/HerrigelVoloshynovskiyHrytskiv_spie99.pdf} } @INPROCEEDINGS{VG:HVR2001, author = {Alexander Herrigel and Sviatoslav Voloshynovskiy and Yuriy Rytsar}, title = {The Watermark Template Attack}, booktitle = {SPIE Photonics West, Electronic Imaging 2001, Security and Watermarking of Multimedia Contents III}, year = {2001}, vgclass = {refpap}, vgproject = {watermarking}, editor = {W. Wong and E. J. Delp}, number = {paper 4314-46}, address = {San Jose, CA, USA}, month = {jan}, url = { http://vision.unige.ch/publications/postscript/2001/HerrigelVoloshynovskiyRytsar_spie2001.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2001/HerrigelVoloshynovskiyRytsar_spie2001.pdf} } @ARTICLE{VG:HAP1988, author = {D. Hochstrasser and V. Augsburger and Thierry Pun and D. Weber and Christian Pellegrini and A. M{\"u}ller}, title = {High resolution mini-two-dimensional gel electrophoresis automatically run and stained in less than six hours with small, ready to use slab gels}, journal = {Clinical Chemistry}, year = {1988}, volume = {34}, pages = {166--170}, vgclass = {refpap}, vgproject = {unspecified}, number = {1}, month = {January} } @INPROCEEDINGS{VG:HFA1990, author = {D. F. Hochstrasser and M. Funk and R. D. Appel and Thierry Pun and R. W. James and A.-C. Hochstrasser and J.-R. Scherrer and Christian Pellegrini and A. F. Muller}, title = {From a biopsy to automatic diagnosis}, booktitle = {Schweizerischen Medizinischen Wochenschrift}, year = {1990}, vgclass = {refpap}, vgproject = {unspecified}, series = {120}, pages = {1862--1866} } @INPROCEEDINGS{Holotyak:CMS2005:BSS, author = {Taras Holotyak and Jessica Fridrich and Sviatoslav Voloshynovskiy}, title = {Blind Statistical Steganalysis of Additive Steganography Using Wavelet Higher Order Statistics}, booktitle = { 9th IFIP TC-6 TC-11 Conference on Communications and Multimedia Security (CMS 2005)}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Salzburg, Austria}, month = {September 19-21} } @MISC{VG:Hon1999, vgclass = {licence}, vgproject = {abweb}, author = {Lin Hong}, title = {Recherche de cha\^{i}nes de caract\`eres dans une image bitmap}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {March}, year = {1999}, abstract = {La d\'etection automatique et la reconnaissance de cha\^{i}nes de caract\`eres contenues dans des images bitmap est tr\`es utile pour les syst\`emes multim\'edias, les librairies digitales et les syst\`emes d'informations g\'eographiques. Cependant, les syst\`emes commerciaux actuels qui utilisent des OCR (Optical Character Recognition) sont limit\'es au traitement de cha\^{i}nes de caract\`eres imprim\'ees sur des fonds uniformes (p.ex. caract\`eres noirs sur fond blanc). N\'eanmoins, une nouvelle approche a \'et\'e propos\'ee. Trois phases distinctes sont n\'ecessaires pour extraire le texte contenu dans une image: la d\'etection des r\'egions contenant du texte, l'extraction du texte (suppression du fond) et l'affinement du r\'esultat obtenu. Intrigu\'ee par l'efficacit\'e de cette nouvelle approche, je l'ai implant\'ee en Java en obtenant des r\'esultats tr\`es satisfaisants. Dans ce m\'emoire, les d\'etails d'implantation sont pr\'esent\'es et les r\'esultats obtenus sont analys\'es.} } @MISC{VG:Hu1993, vgclass = {diploma}, vgproject = {unspecified}, author = {Ziping Hu}, title = {Speedup of algorithms by using a {C}onnection {M}achine through a network: application to image processing}, howpublished = {Diploma thesis, University of Geneva}, month = {June}, year = {1993} } @MISC{VG:Hu1991, vgclass = {licence}, vgproject = {unspecified}, author = {Ziping Hu}, title = {Spine planimetry: a clinical image analysis tool}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {December}, year = {1991} } @INPROCEEDINGS{VG:HPP1988, author = {Z. Hu and Thierry Pun and Christian Pellegrini}, title = {Expert system for image segmentation}, booktitle = {{SGAICO} - Swiss Group of {AI} and Cognitive Sciences Annual Conference on Artificial Intelligence in Manufacturing, Assembly, and Robotics, Bern}, year = {1988}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October} } @ARTICLE{VG:HPP1990, author = {Z. P. Hu and Thierry Pun and Christian Pellegrini}, title = {An expert system for guiding image segmentation}, journal = {Computerized Medical Imaging and Graphics}, year = {1990}, volume = {14}, pages = {13--24}, vgclass = {refpap}, vgproject = {unspecified}, number = {1} } @MISC{VG:Iqu2000, vgclass = {diploma}, vgproject = {watermarking}, author = {Victor Iquise}, title = {Attaques Contre Le Filigranage Digital D'images et de Vid\'eos, Bas\'ees sur Le Concept de Suppression Du Bruit}, howpublished = {Diploma thesis (MSc), University of Geneva}, month = {November}, year = {2000} } @TECHREPORT{VG:Ite1990, author = {Robert Iten}, title = {{SN}1: {C}oncept acquisition combining symbolic and numerical information}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1990}, vgclass = {report}, vgproject = {unspecified}, number = {90.08}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {December} } @PHDTHESIS{VG:Jac1993, author = {Alain Jacot-Descombes}, title = {Groupage perceptuel asynchrone pour la compr\'ehension qualitative d'images: des contours aux primitives g\'en\'eriques}, school = {Universit\'e de Gen\`eve}, year = {1993}, type = {{P}h.{D}. {D}issertation {N}o. 2642}, address = {Switzerland}, month = {November}, note = {Thesis Jury: Dr.~Radu Horaud (LIFIA, Grenoble, FR), Prof.~Bernard Levrat (Geneva, CH), Prof.~Thierry Pun (director, Geneva, CH)}, vgclass = {thesis}, vgproject = {unspecified} } @MISC{VG:Jac1988, vgclass = {diploma}, vgproject = {unspecified}, author = {Alain Jacot-Descombes}, title = {Laboratoire {I}mage: d\'eveloppement d'un environnement convivial pour le traitement interactif et automatique d'images}, howpublished = {Diploma thesis, University of Geneva}, month = {December}, year = {1988} } @MISC{VG:Jac1987, vgclass = {licence}, vgproject = {unspecified}, author = {Alain Jacot-Descombes}, title = {Labo {I}mage: d\'eveloppement d'un environnement convivial pour le traitement interactif d'images}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {December}, year = {1987} } @INPROCEEDINGS{VG:JDP1992, author = {Alain Jacot-Descombes and Thierry Pun}, title = {A probabilistic approach to 3-{D} inference of geons from a 2-{D} view}, booktitle = {Applications of Artificial Intelligence X: Machine Vision and Robotics}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, editor = {Kevin W. Bowyer}, volume = {1708}, series = {SPIE Proceedings}, pages = {579--588}, address = {Orlando, FLA, USA}, month = {April}, note = {(Special Session on: Recognition by Components or Geon-Based Systems)}, abstract = {A new, probabilistic approach for inferring 3-D volumetric primitives from a single 2-D view is presented. This recognition relies on the assumption that every object can be decomposed into component parts that belong to a finite set or alphabet of volumetric primitives (geons). For each possible primitive from the permissible set, a conditional probability function is computed. This law specifies the probability of obtaining the primitive given an observable 2- D measure or feature. The distribution functions are determined by simulation, on the basis of a representative number of random projections of the primitives. The measures themselves are chosen in such a way that they can easily be extracted from real images and their discriminative power for the volumetric primitive inference is high. Examples illustrate the proposed approach.} } @INCOLLECTION{VG:JDP1994, author = {Alain Jacot-Descombes and Thierry Pun}, title = {Labo{I}mage: an experimental window-based environment for teaching and research in image analysis}, booktitle = {Experimental Environments for Computer Vision and Image Processing}, publisher = {World Scientific}, year = {1994}, editor = {H. I. Christensen and J. L. Crowley}, pages = {89--108}, vgclass = {refpap}, vgproject = {unspecified} } @INCOLLECTION{VG:JDP1993, author = {Alain Jacot-Descombes and Thierry Pun}, title = {Labo{I}mage}, booktitle = {Prime Time Freeware for Unix}, publisher = {software}, year = {1993}, editor = {R. Morin}, volume = {2}, edition = {2}, vgclass = {refpap}, vgproject = {unspecified} } @ARTICLE{VG:JDP19, author = {Alain Jacot-Descombes and Thierry Pun}, title = {Asynchronous perceptual grouping: from contours to relevant 2{D} structures}, journal = {Computer Vision and Image Understanding}, year = {1997}, volume = {66}, pages = {1--24}, vgclass = {refpap}, vgproject = {unspecified}, number = {1}, month = {April} } @TECHREPORT{VG:JaP1994, author = {Alain Jacot-Descombes and Thierry Pun}, title = {Asynchronous perceptual grouping: from contours to generic primitives}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {94.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {January} } @ARTICLE{VG:JaP1990, author = {A. Jacot-Descombes and Thierry Pun}, title = {Labo{I}mage 3.0}, journal = {Computerized Medical Imaging and Graphics}, year = {1990}, volume = {14}, pages = {III}, vgclass = {otherjournals}, vgproject = {unspecified}, number = {4}, note = {(Software Survey Section)} } @INPROCEEDINGS{VG:JRP1992, author = {Alain Jacot-Descombes and Marianne Rupp and Thierry Pun}, title = {Labo{I}mage: {A} portable window based environment for research in image processing and analysis}, booktitle = {Image Processing and Interchange: Implementation and Systems}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, editor = {Ronald B. Arps and William K. Pratt}, volume = {1659}, series = {SPIE Proceedings}, pages = {331--340}, address = {San Jose, California, USA}, month = {February}, abstract = {LaboImage provides scientists with general purpose as well as specific processing families and tools in a highly interactive environment. The current software results from an evolution reflecting several years of development and experiences. This paper first presents the new X Window / OSF Motif version of LaboImage, as it is seen by the user. It also describes how an image is manipulated in the system, how processing methods are applied and results are visualized. Multiple types of interaction between the user and the system are addressed. The implementation aspects are then detailed. They concern data structures as well as algorithms and interfaces. The data file and descriptor file formate used for strong images is described. The organization in memory of multiple data such as images, vectors, and macros is presented. The source code organization is also discussed. A clear separation between algorithmic and interface parts in the code appears to be very important, in order to allow easy further developments of the system.} } @INPROCEEDINGS{VG:JRP1992a, author = {Alain Jacot-Descombes and M. Rupp and Thierry Pun}, title = {Labo{I}mage 4.0: {P}ortable window based environment for research in image processing and analysis}, booktitle = {Medinfo 92, 7th World Congress on Medical Informatics, Geneva, Switzerland}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, month = {September} } @ARTICLE{VG:JTP1991, author = {Alain Jacot-Descombes and K. Todorov and Christian Pellegrini and D. F. Hochstrasser and Thierry Pun}, title = {Labo{I}mage: a workstation environment for research in image processing and analysis}, journal = {Computer Applications in the Biosciences}, year = {1991}, volume = {7}, pages = {225--232}, vgclass = {refpap}, vgproject = {unspecified}, number = {2}, month = {April} } @MISC{VG:Jac1992, vgclass = {licence}, vgproject = {unspecified}, author = {Sabrina Jacot-Descombes}, title = {Approches pour \'evaluation de la sym\'etrie d'objets}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {May}, year = {1992} } @ARTICLE{Janvier2006a, author = {Bruno Janvier and \'Eric Bruno and St\'ephane Marchand-Maillet and Thierry Pun}, title = {Information-theoretic temporal segmentation of videos and applications: multiscale keyframe selection and transition detection}, journal = {Multimedia Tools and Applications}, year = {2006}, volume = {30}, pages = {273-288}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://www.springerlink.com/content/q650q0936j5710k7} } @INPROCEEDINGS{Janvier:EUSIPCO2005:CMSVT, author = {Bruno Janvier and \'Eric Bruno and St\'ephane Marchand-Maillet and Thierry Pun}, title = {A contextual model for semantic video structuring}, booktitle = {Proceedings of the 13th European Signal Processing Conference (Eusipco 2005)}, year = {2005}, vgclass = {refpap}, vgproject = {viper}, address = {Antalya, Turkey}, month = {September 4-8}, url = {http://vision.unige.ch/publications/postscript/2005/janvier_cmsvt.pdf} } @ARTICLE{Janvier:MTAP2005:ITTS, author = {Bruno Janvier and \'Eric Bruno and St\'ephane Marchand-Maillet and Thierry Pun}, title = {Information-theoretic temporal segmentation of videos and applications: multiscale keyframe selection and transition detection}, journal = {Multimedia Tools and Applications}, year = {2005}, vgclass = {refpap}, vgproject = {viper}, note = {(to appear)}, url = {http://vision.unige.ch/publications/postscript/2005/janvier_itts.pdf} } @INPROCEEDINGS{Janvier2006, author = {Bruno Janvier and Eric Bruno and St{\'e}phane Marchand Maillet and Thierry Pun}, title = {Performance evaluation of a contextual news story segmentation algorithm}, booktitle = {Proc. SPIE Vol. 6073, 60730X, Multimedia Content Analysis, Management, and Retrieval}, year = {2006}, volume = {6073}, address = {San Jose, CA}, month = {January}, editors = {Edward Y. Chang, Alan Hanjalic, Nicu Sebe}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://bookstore.spie.org/index.cfm?fuseaction=DetailPaper\&ProductId=642754\&coden=} vgclass = {refpap}, vgproject = {viper}, } @INPROCEEDINGS{VG:JANVIER:CBMI03, author = {Bruno Janvier and Eric Bruno and St{\'e}phane Marchand Maillet and Thierry Pun}, title = {Information-Theoretic Framework for The Joint Temporal Partionning and Representation of Video Data}, booktitle = {Proceedings of the 3rd International Workshop on Content-Based Multimedia Indexing, CBMI'03}, year = {2003}, address = {Rennes, France}, month = {September}, url = {http://vision.unige.ch/publications/postscript/2003/VideoTemporalSegmentation.cbmi.pdf} vgclass = {refpap}, vgproject = {viper}, } @INPROCEEDINGS{VG:JMM2003, author = {Carlo Jelmini and St{\'e}phane Marchand-Maillet}, title = {{DEVA}: an extensible ontology-based annotation model for visual document collections }, booktitle = {Proceedings of {SPIE} Photonics West, Electronic Imaging 2002, Internet Imaging {IV}}, year = {2003}, vgclass = {refpap}, vgproject = {viper}, editor = {R. Schettini and S. Santini Eds}, address = {Santa Clara, CA, USA} } @INPROCEEDINGS{VG:jelmini2004, author = {Carlo Jelmini and St{\'e}phane Marchand-Maillet}, title = {OWL-based reasoning with retractable inference}, booktitle = {Proceedings of {RIAO} 2004, Conference on coupling approaches, coupling media and coupling languages for information retrieval}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {Avignon, France} } @TECHREPORT{VG:Oct0305, author = {C. Jelmini and S. Marchand-Maillet}, title = {The Semantic Web Knowledge Base ({SWKB}), an {OWL} reasoning tool with retractable inference}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {viper}, number = {03.05}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland} } @MISC{VG:Kab1999, vgclass = {diploma}, vgproject = {unspecified}, author = {Oussama Chaban Kabakibo}, title = {M\'ecanismes de paiement \'electronique pour les flux de donn\'ees audio et vid\'eo}, howpublished = {Diploma thesis, University of Geneva}, month = {February}, year = {1999}, note = {(Travail r\'ealis\'e au sein du groupe de Syst\`emes bas\'es objets (Dr. D. Konstantas))} } @INPROCEEDINGS{VG:KaR2001, author = {Hesham Kamel and Patrick Roth}, title = {{G}raphics and {U}sers {E}xploration via {S}imple {S}onics ({GUESS}): Providing Interrelation Representation of Objects in a Non-visual Environment}, booktitle = {ICAD 2001, In International Conference on Auditory Display}, year = {2001}, vgclass = {refpap}, vgproject = {abweb}, address = {Espoo , Finland}, month = {July 29-August 1} } @INPROCEEDINGS{VG:KKC1998, author = {Jean Khedari and Joseph Khedari and Gabriela Csurka and Jongjit Hirunlabh}, title = {General analytical modelling of heat transfer in isotropic solid materials under periodic steady regime}, booktitle = {Int. Conf. on Contribution of Cognition to Modelling (CCM 98)}, year = {1998}, vgclass = {refpap}, vgproject = {watermarking}, address = {Lyon, France}, month = {jul 6--8} } @INPROCEEDINGS{Kludas:FDIA07:MRCWC, author = {Jana Kludas}, title = {Multimedia Retrieval and Classification for Web Content}, booktitle = {Proceedings of BCS IRSG Symposium: Future Directions in Information Access (FDIA)}, year = {2007}, vgclass = {refpap}, vgproject = {viper}, address = {Glasgow, Scotland}, month = {August 28-29}, abstract = { *The population of the World Wide Web with media of all types such as texts, images, videos and audio files in recent years raised the attractiveness of multimedia retrieval. With our work on the influence of dependencies between modalities and features we investigate why these approaches still do not perform convincingly better than plain text search approaches when applied to large, noisy collections like web content, even though these approaches have more information at their hands. This article suggests that, due to the size and noise, the modality’s dependencies necessary for efficient information fusion becomes small and hard to exploit. Preliminary experiments with two multi modal collections underpin this statement.* }, url = {http://vision.unige.ch/publications/postscript/2007/kludas.fdia07.pdf} } @INPROCEEDINGS{Kludas:AMR07:IFMIR, author = {Jana Kludas and Eric Bruno and Stephane Marchand-Maillet}, title = {Information Fusion in Multimedia Information Retrieval}, booktitle = {Proceedings of 5th international Workshop on Adaptive Multimedia Retrieval (AMR)}, year = {2007}, vgclass = {refpap}, vgproject = {viper}, address = {Paris, France}, month = {July 5-6}, abstract = {In retrieval, indexing and classification of multimedia data an efficient information fusion of the different modalities is essential for the system's overall performance. Since information fusion, its influence factors and performance improvement boundaries have been lively dis- cussed in the last years in different research communities, we will review their latest findings. They most importantly point out that exploiting the feature's and modality's dependencies will yield to maximal performance. In data analysis and fusion tests with annotated image collections this is undermined.}, url = {http://vision.unige.ch/publications/postscript/2007/Kludas.amr07.pdf} } @inproceedings{morrison07-automatic, Author = {Morrison, Donn and Marchand-Maillet, St\'ephane and Bruno, Eric}, Title = {Automatic image annotation with relevance feedback and latent semantic analysis}, BookTitle = {Proceedings 5th International Workshop on Adaptive Multimedia Retrieval}, address = {Paris, France}, month = {July 5-6}, Year = {2007} } @inproceedings{morrison07-hierarchical, Author = {Morrison, Donn and Marchand-Maillet, St\'ephane and Bruno, Eric}, Title = {Hierarchical long-term learning for automatic image annotation}, BookTitle = {Proceedings 2nd International Conference on Semantic and Digital Media Technologies}, address = {Genova, Italy}, month = {December 5-7}, Year = {2007} } @ARTICLE{VG:KMJ2000, author = {Dimitri Konstantas and Ruggiero Milanese and Alain Jacot-Descombes and Thierry Pun}, title = {Distributed video production, distributed musical rehearsal and distributed video editing and retrieval}, journal = {Comtec}, year = {2000}, volume = {2}, pages = {30-37}, vgclass = {otherjournals}, vgproject = {dvp} } @INBOOK{VG:KTM2000, pages = {47--56}, title = {Towards the Digitalization of the Braille and Audio-Book Library of the A.B.A.}, publisher = {University of Geneva}, year = {2000}, editor = {D. Tsichritzis}, author = {Dimitri Konstantas and Karim Taha and Jean-Henry Morin and Lori Petrucci}, booktitle = {Internet Objects}, vgclass = {refpap}, vgproject = {abweb} } @TECHREPORT{VG:Kosinov0601, author = {Serhiy Kosinov}, title = {Dual diffusion model of spreading activation for content-based image retrieval}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2006}, vgclass = {report}, vgproject = {viper}, number = {06.01}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland} } @TECHREPORT{VG:Dec0307, author = {Serhiy Kosinov}, title = {Visual object recognition using distance-based discriminant analysis}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {viper}, number = {03.07}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland} } @INPROCEEDINGS{VG:Kosinov06visual, author = {Serhiy Kosinov and St\'ephane Marchand-Maillet}, title = {Visual object categorization with indefinite kernels in discriminant analysis framework}, booktitle = {Proceedings of SPIE Photonics West, Electronic Imaging 2006, Multimedia Content Analysis, Management, and Retrieval 2006 (EI122)}, year = {2006}, vgclass = {refpap}, vgproject = {viper}, address = {San Jose, USA}, month = {January, 15-19} } @INPROCEEDINGS{VG:Kosinov04evaluation, author = {Serhiy Kosinov and St{\'e}phane Marchand-Maillet}, title = {Evaluation of distance-based discriminant analysis and its kernelized extension in visual object recognition}, booktitle = {Proceedings of the 7th International on signal/image processing and pattern recognition ({UkrObraz} 2004)}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {Kijiv, Ukraine} } @INPROCEEDINGS{VG:Kosinov04hierarchical, author = {Serhiy Kosinov and St{\'e}phane Marchand-Maillet}, title = {Hierarchical Ensemble Learning For Multimedia Categorization And Autoannotation}, booktitle = {Proceedings of the 2004 {IEEE} Signal Processing Society Workshop ({MLSP} 2004)}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, pages = {645--654}, address = {S\~{a}o Lu{\'i}s, Brazil}, url = {http://vision.unige.ch/publications/postscript/2004/MLSP2004-KosinovMarchandMaillet.pdf} } @INPROCEEDINGS{VG:Kosinov04multimedia, author = {Serhiy Kosinov and St{\'e}phane Marchand-Maillet}, title = {Multimedia autoannotation via hierarchical semantic ensembles}, booktitle = {Proceedings of the Int. Workshop on Learning for Adaptable Visual Systems ({LAVS} 2004)}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {Cambridge, UK} } @INPROCEEDINGS{Kosinov03overview, author = {Serhiy Kosinov and St{\'e}phane Marchand-Maillet}, title = {Overview of approaches to semantic augmentation of multimedia databases for efficient access and content retrieval}, booktitle = {Proceedings of the 1st International Workshop on Adaptive Multimedia Retrieval (AMR 2003)}, year = {2003}, vgclass = {refpap}, vgproject = {viper}, address = {Hamburg}, url = {http://www.springerlink.com/link.asp?id=uln4brc7t0xjejj2} } @INPROCEEDINGS{VG:Kosinov06dual, author = {Serhiy Kosinov and St{\'e}phane Marchand-Maillet and Igor Kozintsev and Carole Dulong and Thierry Pun}, title = {Dual diffusion model of spreading activation for content-based image retrieval}, booktitle = {8th ACM SIGMM International Workshop on Multimedia Information Retrieval}, year = {2006}, vgclass = {refpap}, vgproject = {viper}, address = {Santa Barbara, CA, USA}, month = {October}, url = {http://portal.acm.org/ft_gateway.cfm?id=1178686\&type=pdf\&coll=\&dl=ACM\&CFID=15151515\&CFTOKEN=6184618} } @INPROCEEDINGS{VG:Kosinov05countering, author = {Serhiy Kosinov and St\'ephane Marchand-Maillet and Thierry Pun}, title = {Countering the false positive projection effect in nonlinear asymmetric classification}, booktitle = {The IEEE Symposium on Signal Processing and Information Technology (ISSPIT'05)}, year = {2005}, vgclass = {refpap}, vgproject = {viper}, address = {Athens, Greece}, month = {December, 18-21} } @INPROCEEDINGS{Kosinov04iterative, author = {Serhiy Kosinov and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Iterative majorization approach to the distance-based discriminant analysis}, booktitle = {Proceedings of the 28th Annual Conference of the {GfKl} 2004}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {Dortmund, Germany}, month = {March 9--11}, url = {http://vision.unige.ch/publications/postscript/2004/KosinovMarchandMailletPunGFKL2004.ps.gz} } @INPROCEEDINGS{Kosinov04visual, author = {Serhiy Kosinov and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Visual object categorization using distance-based discriminant analysis}, booktitle = {Proceedings of the 4th International Workshop on Multimedia Data and Document Engineering}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {Washington, DC}, month = {July}, url = {http://vision.unige.ch/publications/postscript/2004/KosinovMarchandMailletPunMDDE2004.pdf} } @INPROCEEDINGS{VG:Kosinov05large, author = {Serhiy Kosinov and Ivan Titov and St{\'e}phane Marchand Maillet}, title = {Large Margin Multiple Hyperplane Classification for Content-based Multimedia Retrieval}, booktitle = {Proceedings of the 1st Workshop on Machine Learning Techniques for Processing Multimedia Content, {MLMM'05}}, year = {2005}, vgclass = {refpap}, vgproject = {viper}, address = {Bonn, Germany}, month = {August} } @TECHREPORT{Koval:TR2006, author = {Oleksiy Koval and Sviatoslav Voloshinovskiy and Thierry Pun}, title = {Analysis of modality dependence/independence impact on the performance of multimodal fusion systems: Summary of main results}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2006}, vgclass = {report}, vgproject = {watermarking}, number = {06.12}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland}, url = {http://vision.unige.ch/publications/postscript/2006/KVP_Multimodal_Fusion_Systems_Summary-2006.pdf} } @INPROCEEDINGS{Koval:2007:RPH-Security, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and Fokko Beekhof and Thierry Pun}, title = {Security Analysis of Robust Perceptual Hashing}, year = {2008}, note = {(submitted)}, owner = {beekhof}, timestamp = {2007.08.16} } @INPROCEEDINGS{Koval:2007:Sphere-Decoding, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and Fokko Beekhof and Thierry Pun}, title = {Analysis of physical unclonable identification based on reference list decoding}, year = {2008}, note = {(submitted)}, owner = {beekhof}, timestamp = {2007.08.16} } @INPROCEEDINGS{Koval:WaCha:2007, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and Fokko Beekhof and Thierry Pun}, title = {Decision-theoretic consideration of robust perceptual hashing: link to practical algorithms}, booktitle = {WaCha2007, /Third WAVILA Challenge/}, year = {2007}, vgclass = {refpap}, vgproject = {watermarking}, address = {Saint Malo, France}, month = {June 15th} } @INPROCEEDINGS{Koval:SPIE2005, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and Fr\'{e}d\'{e}ric Deguillaume and F. Perez-Gonzalez and Thierry Pun}, title = {Robustness improvement of known-host-state watermarking using host statistics}, booktitle = {Proceedings of SPIE Photonics West, Electronic Imaging 2005, Security, Steganography, and Watermarking of Multimedia Contents VII (EI120)}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 16-20}, url = {http://vision.unige.ch/publications/postscript/2005/KovalVoloshynovskiyDeguillaumePerezGonzalezPun_SPIE2005.pdf} } @INPROCEEDINGS{VG:EUSIPCO2004a, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and Fr\'{e}d\'{e}ric Deguillaume and F. Perez-gonzalez and Thierry Pun}, title = {Spread spectrum watermarking for real images: is everything so hopeless?}, booktitle = {Proceedings of 12th European Signal Processing Conference, EUSIPCO 2004}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, address = {Vienna, Austria}, month = {September 6-10}, url = {http://vision.unige.ch/publications/postscript/2004/KovalVoloshynovskiyDeguillaumePerezGonzalezPun_EUSIPCO2004.pdf} } @INPROCEEDINGS{Koval:ACM2006, author = {Oleksiy Koval and S. Voloshynovskiy and Taras Holotyak and Thierry Pun}, title = {Information-theoretic analysis of steganalysis in real images}, booktitle = {ACM Multimedia and Security Workshop 2006}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {Geneva, Switzerland}, month = {September 26-27}, url = {http://vision.unige.ch/publications/postscript/2006/mmsec169-koval.ps} } @INPROCEEDINGS{VG:ACM2004, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and F. Perez-Gonzalez and F. Deguillame and Thierry Pun}, title = {Quantization-based watermarking performance improvement using host statistics: AWGN attack case}, booktitle = {ACM Multimedia and Security Workshop 2004}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, address = {Magdeburg, Germany}, month = {September 20-21}, url = {http://vision.unige.ch/publications/postscript/2004/2004.ACM.Non_uniform_quantizer.pdf} } @INPROCEEDINGS{Koval:IWMSP:2007a, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Analysis of multimodal binary detection systems based on dependent/independent modalities}, booktitle = {Proceedings of the IEEE 2007 International Workshop on Multimedia Signal Processing}, year = {2007}, vgclass = {refpap}, vgproject = {watermarking}, address = {Chania, Crete, Greece}, month = {October 1--3} } @INPROCEEDINGS{Koval:SPIE2007:EEA, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Error exponent analysis of person identification based on fusion of dependent/independent modalities}, booktitle = {Proceedings of {SPIE-IS{\&}T} Electronic Imaging 2007, Security, Steganography, and Watermarking of Multimedia Contents IX}, year = {2007}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {28 Jan. -- 1 Feb.}, abstract = {Abstract--Performance limits of multimodal detection systems are analyzed in this paper. Two main setups are analyzed, i.e., based on fusion of dependent and independent modalities, respectively. The analysis is performed in terms of attainable probability of detection errors characterized by the corresponding error exponents. It is demonstrated that an expected performance gain from fusion of dependent modalities is superior than in the case when one fuses independent signals. In order to quantify the efficiency of dependent modality fusion versus the independent case, the problem analysis is performed in the Gaussian formulation.}, url = {http://vision.unige.ch/publications/postscript/2007/SPIE-EI-2007-Error-Exponent-paper.pdf} } @INPROCEEDINGS{Koval:WIC2006:Koval_wic2006, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Laplacian channel state estimation for state dependent channels}, booktitle = {Proceedings of 27-th Symposium on information theory in the Benelux}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {Noordwijk, The Netherlands}, month = {June 8-9, 2006,}, url = {http://vision.unige.ch/publications/postscript/2006/Koval_wic2006.pdf} } @ARTICLE{Koval:SP2005:RIKHSW, author = {Oleksiy Koval and Sviatoslav Voloshynovskiy and J.E. Vila-Forc{\'e}n and F. P{\'e}rez-Gonz{\'a}lez and Fr\'{e}d\'{e}ric Deguillaume and Thierry Pun}, title = {Robustness Improvement of Known-Host-State Watermarking Using Host Statistics}, journal = {Elsevier Science, Signal Processing}, year = {2006}, volume = {86}, pages = {1076--1088}, vgclass = {refpap}, vgproject = {watermarking}, number = {5}, month = {May}, url = {http://vision.unige.ch/publications/postscript/2006/robustnees-improvement.pdf} } @TECHREPORT{BMI:Dec0309, author = {Jullien Kronegg}, title = {Capacity study of the memoryless channel with additive independent Gaussian noise and its application to brain-computer interfaces}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {bmi}, number = {03.09}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland}, url = {http://vision.unige.ch/publications/postscript/2003/Kronegg2003__Capacity_Study_of_AWGN_channel_(TR0309).pdf} } @MISC{VG:Kro2001, vgclass = {diploma}, vgproject = {external}, author = {Julien Kronegg}, title = {Dispositif de Capture Des Mouvements Oculaires Pour un Simulateur de Vision}, howpublished = {Diploma thesis (MSc), University of Geneva}, month = {June}, year = {2001}, url = { http://vision.unige.ch/publications/postscript/2001/kronegg_diploma.pdf} } @INPROCEEDINGS{Kronegg:TAIMA:AMDICO, author = {Julien Kronegg and Teodor Alecu and Guillaume Chanel and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Analyse des mesures de d{\'e}bit pour interfaces cerveau-ordinateur}, booktitle = {TAIMA'2005, Traitement et Analyse de l'Information : M{\'e}thodes et Applications}, year = {2005}, vgclass = {refpap}, vgproject = {bmi}, address = {Hammamet, Tunisia}, month = {26 Sep -- 1Oct} } @MISC{Kronegg:SIMILAR:TUFBCI, vgclass = {fullconf}, vgproject = {bmi}, author = {Julien Kronegg and Teodor Alecu and Thierry Pun}, title = {Towards user friendly BCIs}, howpublished = {EU NOE Similar Workshop}, month = {Nov. 8--9}, year = {2004}, note = {Sophia-Antipolis, France}, address = {Sophia-Antipolis, France,} } @INPROCEEDINGS{BMI:HCII2003, author = {Julien Kronegg and Teodor Alecu and Thierry Pun}, title = {Information theoretic bit-rate optimization for average trial protocol Brain-Computer Interfaces}, booktitle = {HCI International 2003, 10th International Conference on Human-Computer Interaction}, year = {2003}, vgclass = {refpap}, vgproject = {bmi}, address = {Crete, Greece}, month = {June 22-27}, url = {http://vision.unige.ch/publications/postscript/2003/Kronegg2003-HCII2003-fullpaper.ps.gz}, url1 = {http://vision.unige.ch/publications/postscript/2003/Kronegg2003-HCII2003-fullpaper.pdf} } @ARTICLE{Kronegg:NSRE:EEG-BCI, author = {Julien Kronegg and Guillaume Chanel and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {EEG-based synchronized brain-computer interfaces: a model for optimizing the number of mental tasks}, journal = {IEEE transactions on neural systems and rehabilitation engineering}, year = {2007}, volume = {15}, vgclass = {refpap}, vgproject = {bmi}, number = {1}, month = {March} } @MISC{Kronegg:SIMILAR:ITRBPO, vgclass = {fullconf}, vgproject = {bmi}, author = {Julien Kronegg and Guillaume Chanel and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Information-transfer rate based performance optimization for brain-computer interfaces}, howpublished = {Similar NOE Workshop}, month = {June 8--9}, year = {2006}, note = {Heraklion, Greece}, address = {Heraklion, Greece} } @INPROCEEDINGS{Kronegg:BCI:MPBCIITR, author = {Julien Kronegg and Thierry Pun}, title = {Measuring the performance of brain-computer interfaces using the information transfer rate}, booktitle = {BCI 2005, Brain-Computer Interface Technology: Third International Meeting}, year = {2005}, vgclass = {refpap}, vgproject = {bmi}, address = {Rensselaerville, NY, USA}, month = {June 14--19} } @INPROCEEDINGS{BMI:Kronegg05, author = {Julien Kronegg and Svyatoslav Voloshynovskiy and Thierry Pun}, title = {Analysis of bit-rate definitions for Brain-Computer Interfaces}, booktitle = {Proceedings of the 2005 Int. Conf. on Human-computer Interaction {(HCI'05)}}, year = {2005}, vgclass = {refpap}, vgproject = {bmi}, address = {Las Vegas, Nevada, USA}, month = {June}, url = {http://vision.unige.ch/publications/postscript/2005/Kronegg2005__Analysis_of_bit_rate_definitions_for_BCIs.pdf} } @TECHREPORT{Kronegg:TR:TR0503, author = {Julien Kronegg and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Information-transfer rate modeling of EEG-based synchronized brain-computer interfaces}, institution = {University of Geneva, Computer Vision and Multimedia Laboratory, Computing Centre}, year = {2005}, vgclass = {techreport}, vgproject = {abweb}, number = {05.03}, address = {Rue G{\'e}n{\'e}ral Dufour, 24, CH-1211, Geneva, Switzerland}, month = {December 20}, abstract = {The information-transfer rate (ITR) is commonly used to assess the performance of brain-computer interfaces (BCI). Various studies have shown that the optimal number of mental tasks to be used is fairly low, around 3 or 4. We propose a formal approach and an experimental validation to demonstrate and confirm that this optimum is user and BCI design dependent. Even if increasing the number of mental tasks to the optimum indeed leads to an increase of the ITR, the gain remains small. This might not justify the added complexity in terms of protocol design.}, url = {http://vision.unige.ch/publications/postscript/2005/Kronegg2005__TechReport0503.pdf} } @TECHREPORT{BMI:Jun0403, author = {Jullien Kronegg and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Brain-computer interface model: Upper-capacity bound, signal-to-noise ratio estimation, and optimal number of symbols}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2004}, vgclass = {report}, vgproject = {bmi}, number = {04.03}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland}, url = {http://vision.unige.ch/publications/postscript/2004/Kronegg2004__BCI_Model_upper_capacity_bound_(TR0403).pdf} } @MISC{VG:Kru1996, vgclass = {diploma}, vgproject = {unspecified}, author = {Attila Kruszely}, title = {Suivi d'objet bas\'e sur la couleur dans une s\'equence d'images}, howpublished = {Diploma thesis, University of Geneva}, month = {June}, year = {1996} } @INPROCEEDINGS{VG:KVH2000, author = {Martin Kutter and Sviatoslav Voloshynovskiy and Alexander Herrigel}, title = {Watermark copy attack}, booktitle = {IS\&T/SPIE's 12th Annual Symposium, Electronic Imaging 2000: Security and Watermarking of Multimedia Content II}, year = {2000}, vgclass = {refpap}, vgproject = {watermarking}, editor = {Wah Wong, Ping and Edward J. Delp}, volume = {3971}, series = {SPIE Proceedings}, address = {San Jose, California USA}, month = {23--28~jan}, note = {(Paper EI 3971-35)}, abstract = {Research in digital watermarking has progressed along two paths. While new watermarking technologies are being developed, some researchers are also investigating di erent ways of attacking digital watermarks. Common attacks to watermarks usually aim to destroy theembedded watermark or to impair its detection. In this paper we propose a conceptually new attack for digitally watermarked images. The proposed attack doesnot destroy anembedded watermark, but copies it from one image to a di erent image. Although this new attack does not destroy awatermark or impair its detection, it creates new challenges, especially when watermarks are used for copyright protection and identi cation. The process of copying the watermark requires neither algorithmic knowledge of the watermarking technology nor the watermarking key. The attack is based on an estimation of the embedded watermark in the spatial domain through a ltering process. The estimate of the watermark is then adapted and inserted into the target image. To illustrate the performance of the proposed attack we applied it to commercial and non-commercial watermarking schemes. The experiments showed that the attack is very e ective in copying a watermark from one image to a di erent image. In addition, we have a closer look at application dependent implications of this new attack.}, url = { http://vision.unige.ch/publications/postscript/2000/KutterVoloshynovskiyHerrigel_spie2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/KutterVoloshynovskiyHerrigel_spie2000.pdf} } @INPROCEEDINGS{VG:LMB1997, author = {Abderrahim Labbi and Ruggero Milanese and Holger Bosch}, title = {Gray-level object segmentation with a network of {F}itz{H}ugh-{N}agumo oscillators}, booktitle = {Proceedings of the International Workshop on Artificial and Natural Neural Networks (IWANN'97), Lanzarote, Canary Islands}, year = {1997}, vgclass = {refpap}, vgproject = {unspecified}, series = {Lecture Notes in Computer Science}, publisher = {Springer-Verlag}, abstract = {In this paper we adopt a temporal coding approach to neuronal modeling of the visual cortex, using oscillations. We propose a hierarchy of three processing modules corresponding to different levels of representation. The first layer encodes the input image (stimulus) into an array of units, while the second layer consists of a network of FitzHugh-Nagumo oscillators. The dynamical behaviour of the coupled oscillators is rigorously investigated and a stimulus-driven synchronization theorem is derived. However, this module reveals itself insufficient to correctly encode and segregate different objects when they have similar gray-levels in the input image. Therefore, a third layer connected in a feedback loop with the oscillators is added. This ensures synchronization (resp. desynchronization) of neuron ensembles representing the same (resp. a different) object. Simulation results are presented using synthetic as well as real and noisy gray-level images.}, url = { http://vision.unige.ch/publications/postscript/97/LabbiMilaneseBosch_iwann97.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/LabbiMilaneseBosch_iwann97.pdf} } @TECHREPORT{VG:LMB1997a, author = {Abderrahim Labbi and Ruggero Milanese and Holger Bosch}, title = {Global synchronization and selective desynchronization of {F}itz{H}ugh-{N}agumo oscillators}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1997}, vgclass = {report}, vgproject = {unspecified}, number = {97.05}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {July}, url = { http://vision.unige.ch/publications/postscript/97/VGTR97.05_LabbiMilaneseBosch.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/VGTR97.05_LabbiMilaneseBosch.pdf} } @INPROCEEDINGS{VG:LMB1997b, author = {Abderrahim Labbi and Ruggero Milanese and Holger Bosch}, title = {A Network of {F}itz{H}ugh-{N}agumo Oscillators for Object Segmentation}, booktitle = {Proceedings of the International Symposium on Nonlinear Theory and its Applications (NOLTA'97)}, year = {1997}, vgclass = {refpap}, vgproject = {unspecified}, address = {Honolulu, Hawaii, USA}, month = {November}, abstract = {This paper adresses the problem of modeling object segmentation in the visual cortex using oscillations. The proposed architecture is based on a network of locally connected FitzHugh-Nagumo oscillators which receive graded external input. We show the suitability of such a network to encode the stimulus since the amplitude of oscillations increases monotonically as a function of the input in the neighborhood of a bifurcation, while the frequency remains nearly constant. However, due to the diffusive effects of the Laplacian connectivity, the oscillators tend to be in phase even when they represent different objects. Therefore a desynchronization mechanism, which represents spatial information about the objects, is added. The overall dynamics are described and simulation results on real images are shown.}, url = { http://vision.unige.ch/publications/postscript/97/LabbiMilaneseBosch_nolta97.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/LabbiMilaneseBosch_nolta97.pdf} } @TECHREPORT{VG:Lef1992, author = {Marc Lefebvre}, title = {Vision pour la robotique agricole}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1992}, vgclass = {report}, vgproject = {unspecified}, number = {92.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {July} } @TECHREPORT{VG:LBD1991, author = {Marc Lefebvre and Denis Brunet and J.-D. Dessimoz and P. Gugerli and R. Strasser and Thierry Pun}, title = {The {P}otato {O}peration: general overview}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1991}, vgclass = {report}, vgproject = {unspecified}, number = {91.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {January} } @TECHREPORT{VG:LBP1991, author = {Marc Lefebvre and Denis Brunet and Thierry Pun}, title = {The {P}otato {O}peration: germs detection using contour based measures}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1991}, vgclass = {report}, vgproject = {unspecified}, number = {91.02}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {January} } @INPROCEEDINGS{VG:LDG1990, author = {Marc Lefebvre and J.-D. Dessimoz and P. Gugerli and Thierry Pun}, title = {Potato {O}peration}, booktitle = {Computer Vision Workshop, SGAICO'90, Swiss Group for Artificial Intelligence and Cognitive Science, Geneva, Switzerland}, year = {1990}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October} } @INPROCEEDINGS{VG:LGB1993, author = {Marc Lefebvre and Sylvia Gil and C. Baur and J.-D. Dessimoz and Thierry Pun}, title = {The {P}otato {O}peration: computer vision for agricultural robotics and quality control}, booktitle = {Proceedings of the 4th International Symposium on Fruit, Nut and Vegetable Production Engineering, Valencia, Spain}, year = {1993}, vgclass = {refpap}, vgproject = {unspecified}, pages = {1--8}, month = {March} } @ARTICLE{VG:LGB1993a, author = {Marc Lefebvre and Sylvia Gil and Denis Brunet and E. Natonek and C. Baur and P. Gugerli and Thierry Pun}, title = {Computer vision and agricultural robotics for disease control: the {P}otato {O}peration}, journal = {Computers and Electronics in Agriculture}, year = {1993}, volume = {9}, pages = {85--102}, vgclass = {refpap}, vgproject = {unspecified}, note = {(Special Edition on Computer Vision)}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/lefebvre/93.2.SFNVPE.ps.Z} } @INPROCEEDINGS{VG:LGG1992, author = {Marc Lefebvre and Sylvia Gil and M.-A. Glassey and C. Baur and Thierry Pun}, title = {3{D} computer vision for agrotics: the {P}otato {O}peration, an overview}, booktitle = {11th IAPR - Computer Vision and Applications, The Hague, The Netherlands}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, pages = {207--210}, month = {August}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/lefebvre/92.IAPR.ps.Z} } @INPROCEEDINGS{VG:LZB1994a, author = {Marc Lefebvre and T. Zimmerman and C. Baur and P. Gugerli and Thierry Pun}, title = {Potato {O}peration: status report}, booktitle = {Proceedings 2nd Symposium on Artificial Intelligence and Robotics, Lausanne, Switzerland}, year = {1994}, vgclass = {fullconf}, vgproject = {unspecified}, editor = {R. Bless}, pages = {91--96}, month = {September}, organization = {National Research Program NFP/PNR 23} } @INPROCEEDINGS{VG:LZB1994, author = {Marc Lefebvre and Thierry Zimmerman and Charles Baur and Paul Gugerli and Thierry Pun}, title = {Potato operation: automatic detection of potato diseases}, booktitle = {Optics in Agriculture, Forestry and Biological Processing}, year = {1994}, vgclass = {refpap}, vgproject = {unspecified}, editor = {George E. Meyer and James A. DeShazer}, volume = {2345}, series = {SPIE Proceedings}, pages = {2--9}, address = {Boston, USA}, month = {October}, abstract = {The Potato Operation is a collaborative, multidisciplinary project in the domain of destructive testing of agricultural products. It aims at automatizing pulp sampling of potatoes in order to detect possible viral diseases. Such viruses can decrease fields productivity by a factor of up to ten. A machine, composed of three conveyor belts, a vision system, a robotic arm and controlled by a PC has been built. Potatoes are brought one by one from a bulk to the vision system, where they are seized by a rotating holding device. The sprouts, where the viral activity is maximum, are then detected by an active vision process operating on multiple views. The 3D coordinates of the sampling point are communicated to the robot arm holding a drill. Some flesh is then sampled by the drill, then deposited into an Elisa plate. After sampling, the robot arm washes the drill in order to prevent any contamination. The PC computer simultaneously controls these processes, the conveying of the potatoes, the vision algorithms and the sampling procedure. The master process, that is the vision procedure, makes use of three methods to achieve the sprouts detection. A profile analysis first locates the sprouts as protuberances. Two frontal analyses, respectively based on fluorescence and local variance, confirm the previous detection and provide the 3D coordinate of the sampling zone. The other two processes work by interruption of the master process.}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/lefebvre/94.SPIE.ps.Z} } @MISC{VG:Lou2001, vgclass = {diploma}, vgproject = {viper}, author = {Tatiana Louchnikova}, title = {Segmentation {d'Images} Interactive}, year = {2001}, note = {In French}, url = {http://viper.unige.ch/segmentation/} } @INPROCEEDINGS{VG:LMM2002, author = {Tatiana Louchnikova and St{\'e}phane Marchand-Maillet}, title = {Flexible Image Decomposition for Multimedia Indexing and Retrieval}, booktitle = {Proceedings of {SPIE} Photonics West, Electronic Imaging 2002, Internet Imaging {III}}, year = {2002}, vgclass = {refpap}, vgproject = {viper}, editor = {G. Beretta and R. Schettini Eds}, address = {San Jose, USA} } @MISC{VG:Luo2000, vgclass = {licence}, vgproject = {viper}, author = {Cornelia Luoni}, title = {Development of an Interface to a Database Storing the Features of a Multimedia Retrieval System}, howpublished = {Licence thesis (BSc), University of Geneva}, month = {December}, year = {2000} } @TECHREPORT{VG:Lut1990, author = {Ren{\'e} Lutz}, title = {Segmentation de r\'egions par une m\'ethode r\'ecursive}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1990}, vgclass = {report}, vgproject = {unspecified}, number = {90.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {May} } @MISC{VG:Lut1988, vgclass = {diploma}, vgproject = {unspecified}, author = {Ren{\'e} Lutz}, title = {Conception et r\'ealisation d'outils interactifs pour l'enseignement du graphisme et du traitement d'images}, howpublished = {Diploma thesis, University of Geneva}, month = {December}, year = {1988} } @ARTICLE{VG:LPP1991, author = {Ren{\'e} Lutz and Thierry Pun and Christian Pellegrini}, title = {Colour displays and lookup tables: real time modifications of digital images}, journal = {Computerized Medical Imaging and Graphics}, year = {1991}, volume = {15}, pages = {73--84}, vgclass = {refpap}, vgproject = {unspecified}, number = {2} } @MISC{VG:Lut1987, vgclass = {licence}, vgproject = {unspecified}, author = {Ren{\'e} W. Lutz}, title = {Conception et r\'ealisation d'un environnement convivial pour l'enseignement pratique du graphisme et la programmation de syst\`emes graphiques simples}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {December}, year = {1987} } @TECHREPORT{VG:Dec0308, author = {S. Marchand-Maillet}, title = {Collection guiding}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {viper}, number = {03.08}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland} } @TECHREPORT{VG:Mar0301, author = {St{\'e}phane Marchand-Maillet}, title = {Meeting Record Modelling for Enhanced Browsing}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {viper}, number = {03.01}, address = {rue General Dufour, 24, CH-1211, Geneva, Switzerland}, month = {March} } @TECHREPORT{VG:Mar0302, author = {St{\'e}phane Marchand-Maillet}, title = {MRML: Steps towards version 2}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {viper}, number = {03.02}, address = {rue General Dufour, 24, CH-1211, Geneva, Switzerland}, month = {March} } @INPROCEEDINGS{VG:Mar2002, author = {St{\'e}phane Marchand-Maillet}, title = {Construction of a Formal Multimedia Benchmark}, booktitle = {Proceedings of the European Signal Processing Conference {(EUSIPCO2002)}}, year = {2002}, vgclass = {refpap}, vgproject = {viper}, address = {Toulouse, France}, month = {September}, note = {(Invited paper)}, abstract = {The global acceptance of the digital medium to carry information (in particular over the WWW) makes common the use and development of multimedia information processing systems. This class of systems is very wide and numerous instances are presented in the relevant literature. A common scheme for such presentation mostly follows the classical scheme of specification, development and test. However, in most cases, the evaluation of these systems is related to each particular system. Our aim here is to abstract the class of multimedia systems in order to present a base framework via which systems could be formally compared. This paper analyzes the construction of such a multimedia benchmark by looking at the system from different angles and inheriting from techniques in related fields. Examples of known multimedia system benchmarks are discussed.} } @MISC{VG:Mar2002a, vgclass = {fullconf}, vgproject = {viper}, author = {St{\'e}phane Marchand-Maillet}, title = {{CBIR} in Geneva: Past, Present and Future}, howpublished = {Meeting Content-Based Image and Video Retrieval (Dagstuhl seminar) - (Invited)}, month = {Januray}, year = {2002}, note = {J. Malik (UC Berkeley, USA), H.-P. Kriegel (LMU M\"unchen, Germany), L. Shapiro (Univ. of Washington, USA), R. Veltkamp (Utrecht Univ., The Netherlands) eds.} } @INPROCEEDINGS{VG:Mar2001, author = {St{\'e}phane Marchand-Maillet}, title = {Performance Evaluation in Content-Based Image Retrieval}, booktitle = {Multimedia Content-Based Indexing and Retrieval {(MMCBIR} 2001)}, year = {2001}, vgclass = {refpap}, vgproject = {viper}, address = {INRIA Rocquencourt, Paris, France}, month = {September}, note = {Invited contribution}, abstract = {Content-based image retrieval (CBIR) has now reached a mature stage. Search techniques are well-categorized and several research prototypes or commercial products are available. However, CBIR true performance is still difficult to quantify. Setting up a CBIR benchmark is a heavy task and can only be done via the collaboration of all parties involved in the research and development of CBIR prototypes and related commercial products. The Benchathlon effort proposes to create such a context in which CBIR will be evaluated thoroughly and objectively. In this paper, we present the Benchathlon and its objectives in more details. The goal of CBIR benchmarking has been divided into various parallel and inter-related sub-tasks. One essential such task is the definition of ground truth data. Since no such data exists, the image collection is to be constructed from scratch. Copyright issues should be resolved so as to be able to freely distribute, extend and modify this collection. Further, different sub-collections should be available for different specialized applications. It is also acknowledged here that no unique ground truth exists. Techniques to account for user subjectivity should therefore be developed. Considering the effort involved, tools for easing the task of data annotation need also to be designed. Related to this is the definition of objective quantitative performance measures. These measures should be both thorough and orthogonal. In other words, they should allow for a complete evaluation and highlight weaknesses and strengths of the CBIR system under evaluation. The goal being both to compare systems and to help system developers to profile their techniques. To use this data in practical evaluation, there is also the need for defining standard test queries and result sets. Domain-specific constraints will strongly influence the design of such test cases. Another aspect is the feasibility of CBIR benchmarking. This imposes the definition of a flexible software architecture enabling automated benchmarking while leading to little (optimally no) programming overhead. Again, legal issues about the openness of the systems under evaluation should be accounted for. In our paper, we also shortly present the solutions proposed by the Viper team at University of Geneva. These realizations are gathered under the umbrella of our GIFT project where the central feature is the Multimedia Retrieval Markup Language (MRML), an XML-based communication protocol that we think is a necessary tool for enabling CBIR benchmarking. We describe the architecture of our MRML-based benchmark and sketch results for the Viper search engine.} } @TECHREPORT{VG:Mar2000, author = {St{\'e}phane Marchand-Maillet}, title = {Content-Based Video Retrieval: An Overview}, institution = {CUI - University of Geneva}, year = {2000}, vgclass = {report}, vgproject = {viper}, number = {00.06}, address = {Geneva, Switzerland}, abstract = {Content-based Image Retrieval systems (CBIRS) start flourishing on the Web. Their performances are continuously improving and their base principles span a wide range of diversity. Content-based Video Retrieval systems (CBVRS) are less common and seem at a first glance to be a natural extension of CBIRS. In this document, we summarise advances made in the development of CBVRS and analyse their relationship to CBIRS. While doing so, we show that CBVRS are actually not so obvious extensions of CBIRS. (40 References)}, url = { http://vision.unige.ch/publications/postscript/2000/VGTR00.06_Marchand.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2000/VGTR00.06_Marchand.pdf}, url2 = {http://viper.unige.ch/~marchand/CBVR/} } @BOOK{Marchand-Maillet2007, title = {Adaptive Multmedia Retrieval: User, Context and Feedback}, publisher = {Springer-Verlag}, year = {2007}, author = {St\'ephane Marchand-Maillet and Eric Bruno and Andreas Nurnberger and Marcin Detyniecki}, series = {Lecture Notes on Computer Science}, owner = {beekhof}, timestamp = {2007.10.09} } @INPROCEEDINGS{VG:SMM04collection, author = {St{\'e}phane Marchand-Maillet and {\'E}ric Bruno}, title = {Collection Guiding: A new framework for handling large multimedia collections}, booktitle = {Proceedings of the First Workshop on Audio-visual Content And Information Visualization In Digital Librairies, {AVIVDiLib05}}, year = {2005}, vgclass = {refpap}, vgproject = {viper}, address = {Cortona, Italy} } @INPROCEEDINGS{VG:MLM2001, author = {St{\'e}phane Marchand-Maillet and Nadia Lasri and Henning M{\"u}ller and Wolfgang M{\"u}ller and Thierry Pun}, title = {The Reality of Content-based Image Retrieval}, booktitle = {Proceeding of the meeting Suchbilder}, year = {2001}, vgclass = {fullconf}, vgproject = {viper}, address = {Berlin, Germany}, month = {February}, note = {(to appear)}, url = {http://www.suchbilder.de/} } @MISC{VG:Mar1995, vgclass = {diploma}, vgproject = {viper}, author = {Marc Martin}, title = {Recherche d'images par leur contenu ({SPIP}: {S}earch pictures in pictures)}, howpublished = {Diploma thesis, University of Geneva}, month = {June}, year = {1995}, abstract = {Avec l'apparition sur le march\'e de machines chaque jour de plus en plus puissantes, les ordinateurs deviennent capables de traiter des informations de plus en plus volumineuses comme les sons ou encore les images num\'eris\'es. Ce sont ces derni\`eres, qui nous int\'eressent plus particuli\`erement, les machines de type ``ordinateur personnel'' sont d\'esormais capables de g\'erer des images de plusieurs millions de pixels avec un nombre de couleurs si \'elev\'e qu'il d\'epasse la capacit\'e de discernement de l'oeil humain. Ainsi, avec les possibilit\'es de traitement qu'autorise la num\'erisation, les images informatiques ne pouvaient que se multiplier. Il est aujourd'hui possible de trouver des images sur n'importe quel sujet, et c'est ici qu'un probl\`eme se pose. Pour des raisons qui lui sont propres, un utilisateur quelconque peut avoir un besoin urgent d'une image qui comporte une voiture rouge gar\'ee sur de l'herbe verte. Il se rappellera peut-\^etre avoir d\'ej\`a vu une image de ce genre quelque part, mais aura certainement beaucoup de mal \`a la retrouver sans outils sp\'ecifiques Or, il se trouve que de tels outils sont encore introuvables sur le march\'e. C'est apr\`es avoir constat\'e ce manque que certains laboratoires de recherche se sont attel\'es \`a produire un logiciel qui soit capable de retrouver, si possible, une image en fonction de son contenu. Et parmi les produits qui sont apparus, on pourra citer le syst\`eme QBIC (Querying By Image Content [4]) produit par les laboratoires de recherche d'IBM au cours de l'ann\'ee 1993.}, url = { http://vision.unige.ch/publications/postscript/95/MarcMartin_diploma.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/95/MarcMartin_diploma.pdf} } @MISC{VG:McI1990, vgclass = {licence}, vgproject = {unspecified}, author = {Fiona McIntosh}, title = {Evaluation of new image segmentation techniques for {PET-SHOP} ({E}valuation de nouvelles techniques de segmentation d'images pour {PET-SHOP})}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {January}, year = {1990} } @INPROCEEDINGS{VG:Mil1993, author = {Ruggero Milanese}, title = {Selection of visual information with a bottom-up attention system}, booktitle = {{NATO} Advanced Studies Institute on Statistics and Neural Networks, Les Arcs, France}, year = {1993}, vgclass = {fullconf}, vgproject = {unspecified}, month = {June}, note = {(Research Summary for Poster Presentation)} } @PHDTHESIS{VG:Mil1993a, author = {Ruggero Milanese}, title = {Detecting salient regions in an image: from biological evidence to computer implementation (``D\'etection des r\'egions saillantes d'une image: de l'\'evidence biologique \`a l'impl\'ementation'')}, school = {University of Geneva}, year = {1993}, type = {{P}h.{D}. {D}issertation {N}o. 2647}, address = {Switzerland}, month = {December}, note = {Thesis Jury: Prof.~Harry Wechsler (Geaorge Mason Univ., USA), Dr.~Yves Burnod (Neurosciences, Paris, FR), Prof.~Christian Pellegrini (Geneva, CH), Prof.~Thierry Pun (director, Geneva, CH)}, url = {http://cui.unige.ch/~milanese/pub/thesis.html}, vgclass = {thesis}, vgproject = {unspecified} } @TECHREPORT{VG:Mil1993b, author = {Ruggero Milanese}, title = {Mathematical derivation of energy functions for the integration of conspicuity maps}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1993}, vgclass = {report}, vgproject = {unspecified}, number = {93.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {January} } @INPROCEEDINGS{VG:Mil1991, author = {Ruggero Milanese}, title = {Detection of salient features for focus of attention}, booktitle = {Proceedings 3rd SGAICO Meeting (Swiss Group for Artificial Intelligence and Cognitive Science), Biel-Bienne, Switzerland}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, pages = {87--101}, month = {October}, note = {(published as: University of Bern, Institute for Comp. Science and Mathematics, Technical Report IAM-91--004, H. Kaiser, R. Bach and H. Bunke, Eds., March 1992)} } @TECHREPORT{VG:Mil1990, author = {Ruggero Milanese}, title = {Focus of attention in human vision: a survey}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1990}, vgclass = {report}, vgproject = {unspecified}, number = {90.07}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {August} } @TECHREPORT{VG:Mil1990a, author = {Ruggero Milanese}, title = {Applying focus of attention to a computer vision system}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1990}, vgclass = {report}, vgproject = {unspecified}, number = {90.07}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {December} } @INPROCEEDINGS{VG:MBP1991, author = {Ruggero Milanese and Jean-Marc Bost and Thierry Pun}, title = {Visual indexing with an attentive system}, booktitle = {Proceedings Second AI*IA Scientific Congress (Associazione Italiana per l'Intelligenza Artificiale), Palermo, Italy}, year = {1991}, vgclass = {refpap}, vgproject = {unspecified}, editor = {E. Ardizzone and S. Gaglio and F. Sorbello}, number = {549}, series = {Lecture Notes in Artificial Intelligence}, pages = {415--419}, month = {October}, publisher = {Springer-Verlag}, note = {Published in: Trends in Artificial Intelligence} } @INPROCEEDINGS{VG:MBP1992a, author = {Ruggero Milanese and Jean-Marc Bost and Thierry Pun}, title = {A relaxation network for a feature-driven visual attention system}, booktitle = {Neural and Stochastic Methods in Image and Signal Processing}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, editor = {Su-Shing Chen}, volume = {1766}, series = {SPIE Proceedings}, pages = {542--552}, address = {San Diego, CA, USA}, month = {July}, note = {(Conference on Application of Digital Image Processing XV)}, abstract = {In this paper an attention module is described, which can be used by an active vision system to generate gaze changes. This module is based on a bottom-up, feature-driven analysis of the image. The results are regions of the input image which contain strange features, i.e., locations of the most `interesting' and `important' information. The method proposed for detecting such regions is based on the decomposition of the input image into a set of independent retinotopic feature maps. Each map represents the value of a certain attribute computed on a set of low-level primitives such as contours and regions. Relevant objects can be detected if the corresponding primitives have a feature value strongly different from the neighboring ones. Local comparisons of feature values are used to compute such measures of `difference' for each feature map and give rise to a corresponding set of conspicuity maps. In order to obtain a single measure of interest for each location and to make the process robust to noise, a relaxation algorithm is run on the set of conspicuity maps. A dozen iterations are sufficient to detect a binary mask identifying the attention regions. Results on real scenes are presented.}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/milanese/92.07.spie92.ps.Z} } @INPROCEEDINGS{VG:MBP1992b, author = {Ruggero Milanese and Jean-Marc Bost and Thierry Pun}, title = {A bottom-up attention system for active vision}, booktitle = {Proceedings ECAI 92, 10th. European Conference on Artificial Intelligence, Vienna}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, editor = {B. Neumann}, pages = {808--810}, month = {August}, publisher = {John Wiley and Sons}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/milanese/92.08.ecai92.ps.Z} } @INPROCEEDINGS{VG:MBP1992, author = {Ruggero Milanese and Jean-Marc Bost and Thierry Pun}, title = {Extraction of interesting regions with bottom-up visual attention}, booktitle = {1st Swiss Symposium on Pattern Recognition and Computer Vision, Lausanne, Switzerland}, year = {1992}, vgclass = {refpap}, vgproject = {unspecified}, pages = {85--96}, month = {January} } @INPROCEEDINGS{VG:MBP1991a, author = {Ruggero Milanese and Jean-Marc Bost and Thierry Pun}, title = {Visione attentiva}, booktitle = {First Workshop on Perception, AI*IA (Associazione Italiana per l'Intelligenza Artificiale), Parma, Italy}, year = {1991}, vgclass = {fullconf}, vgproject = {unspecified}, month = {April} } @ARTICLE{VG:MiC1999, author = {Ruggero Milanese and Michel Cherbuliez}, title = {A Rotation, Translation, and Scale-Invariant Approach to Content-Based Image Retrieval}, journal = {Visual Communication and Image Representation}, year = {1999}, volume = {10}, pages = {186--196}, vgclass = {refpap}, vgproject = {cbir}, number = {2}, month = {June}, abstract = {We describe a method for computing an image signature, suitable for content-based retrieval from image databases. The signature is extracted from the Fourier power spectrum by performing a mapping from cartesian to logarithmic-polar coordinates, projecting this mapping onto two 1D signature vectors, and computing their power spectra coefficients. Similar to wavelet-based approaches, this representation is \emph{holistic} and, thus, provides a compact description of all image aspects, including shape, texture, and color. Furthermore, it has the advantage of being invariant to 2D rigid transformations, such as any combination of rotation, scaling, and translation. Experiments have been conducted on a database of 2082 images extracted from various news video clips. Results confirm invariance to 2D rigid transformations, as well as high resilience to more general affine and projective transformations. Moreover, the signature appears to capture perceptually relevant image features, in that it allows successful database querying using example images which have been subject to arbitrary camera and subject motion.} } @INPROCEEDINGS{VG:MCP1999, author = {Ruggero Milanese and Michel Cherbuliez and Thierry Pun}, title = {Invariant content-based image retrieval using the {F}ourier-{M}ellin transform}, booktitle = {International Conference on Advances in Pattern Recognition (ICAPR'98)}, year = {1999}, vgclass = {refpap}, vgproject = {viper}, editor = {S. Singh}, pages = {73--82}, publisher = {Springer}, note = {(Plymouth, UK, 23--25 November 1998)}, abstract = {Recent advances in storage, computing and communication technology have created the need for efficient, user-friendly access methods to multimedia archives. In this paper we address the problem of automatically extracting visual descriptions suitable for indexing images and videos in a database. A new method is proposed, and its applicability is shown using a collection of still images extracted from a video archive. Contrarily to classical approaches, which describe different image aspects (e.g. color, shape, texture) separately, we take on a holistic approach, through the use of integral transforms. In this way, a unique multidimensional descriptor is available to represent all image aspects, and the user is not required to combine multiple independent rankings. With respect to other holistic approaches, such as those based on the wavelet transform, we seek a superior robustness to image transformations such as translation, rotation, and scaling. [insert abstract2] Invariance to rotation, translation and scaling has been verified for the ideal case of rigid 2D image transformations, as well as using images that have been transformed through camera motion (pan/tilt/rotation) and zooming effects. An experimental database has been created using various TV news clips. Shots presenting considerable camera motion, zooming, as well as unrestricted subject motion have been detected, and a number of still images have been extracted from each of them, for a total of 2'082 images. This shot-based clustering naturally provides a ground truth for the desired similarity rankings. Experimental results yield on average 67\% recall for the 12 top-ranked hits, and 54\% precision at 100\% recall. This shows that, although the signature is only meant to conceal rigid 2D euclidean transformations, it is highly resilient to much more complex transformations (projection, arbitrary subject motion, subject appearance/disappearance), and seemingly captures perceptually relevant image features.}, abstract2 = {The proposed image signature is obtained through the following steps. First, translation invariance is obtained by computing the Fourier power spectrum. A coordinate change from cartesian to logarithmic-polar maps rotation and scaling transformations into shifts in the transformed space. These quasi-invariant properties are preserved under projection of this 2D representation onto two 1D normalized orthogonal subspaces. The latter describe, respectively, the probability density of the image's spectrum coefficients with respect to the orientation and scale. Finally, complete invariance to rotation and scaling is again achieved by computing the Fourier power spectrum of these vectors, and by suppressing their even-symmetry components. In practice, this image representation by two 2D signature vectors proves to be very compact (64 coefficients for each color plane of 256x256 images) and prone to efficient implementations, both for signature extraction and for indexing (matching with other images of a database). Moreover tools can easily be devised in order to identify the most relevant aspects of a query image (e.g. its dominant frequency range, the relevance of chromatic information, etc.). User-entered relevance weights can indeed be employed to modulate the distance function in the R64 space.}, url = { http://vision.unige.ch/publications/postscript/98/MilaneseCherbuliezPun_icapr98.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/MilaneseCherbuliezPun_icapr98.pdf} } @INPROCEEDINGS{VG:MDJ1997, author = {Ruggero Milanese and Fr{\'e}d{\'e}ric Deguillaume and Alain Jacot-Descombes}, title = {Video segmentation and camera motion characterization using compressed data}, booktitle = {Multimedia Storage and Archiving Systems II}, year = {1997}, vgclass = {refpap}, vgproject = {dvp,cbir}, editor = {C.-C. J. Kuo and Shih Fu Chang and Venkat N. Gudivada}, volume = {3229}, series = {SPIE Proceedings}, address = {Dallas TX}, month = {November}, abstract = {We address the problem of automatically extracting visual indexes from videos, in order to provide sophisticated access methods to the contents of a video server. We focus on two tasks, namely the decomposition of a video clip into uniform segments (shots) and the characterization of each shot by camera motion parameters. For the first task we use a Bayesian classification approach to detecting scene cuts by analyzing motion vectors. For the second task a least-squares fitting procedure determines the pan/tilt/zoom camera parameters. In order to guarantee the highest processing speed, all techniques process and analyze directly MPEG-1 motion vectors, without need for video decompression. Experimental results are reported for a database of news video clips.}, keywords = {Shot detection, Camera motion, Video archival, Content-based retrievnal, Bayesian classification, MPEG}, url = { http://vision.unige.ch/publications/postscript/97/MilaneseDeguillaumeJacot-Descombes_msasII.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/MilaneseDeguillaumeJacot-Descombes_msasII.pdf} } @ARTICLE{VG:MDJ1998, author = {Ruggero Milanese and Fr{\'e}d{\'e}ric Deguillaume and Alain Jacot-Descombes}, title = {Efficient Segmentation and Camera Motion Indexing of Compressed Video}, journal = {Journal of Real-Time Imaging}, year = {1998}, vgclass = {refpap}, vgproject = {dvp,cbir}, note = {(accepted for publication)}, abstract = {In order to provide sophisticated access methods to the contents of video servers, it is necessary to automatically process and represent each video through a number of visual indexes. We focus on two tasks, namely the hierarchical representation of a video as a sequence of uniform segments (shots), and the characterization of each shot by a vector describing the camera motion parameters. For the first task we use a Bayesian classification approach to detecting scene cuts by analyzing motion vectors. Adaptability to different compression qualities is achieved by learning different classification masks. For the second task, the optical flow is processed in order to distinguish between stationary and moving shots. A least-squares fitting procedure determines the pan/tilt/zoom camera parameters within shots that present regular motion. Each shot is then indexed by a vector representing the dominant motion components and the type of motion. In order to minimize processing speed, all techniques process and analyze directly MPEG-1 motion vectors, without need for video decompression. An overall processing rate of 59 frames/s is achieved on software. The successful classification performance, evaluated on various news video clips for a total of 61,023 frames, attains 97.7\% for the shot segmentation, 88.4\% for the stationary vs. moving shot classification, and 94.7\% for the detailed camera motion characterization.} } @ARTICLE{VG:MGP1995, author = {Ruggero Milanese and Sylvia Gil and Thierry Pun}, title = {Attentive mechanisms for dynamic and static scene analysis}, journal = {Optical Engineering}, year = {1995}, volume = {34}, pages = {2428--2434}, vgclass = {refpap}, vgproject = {unspecified}, number = {8}, month = {August} } @TECHREPORT{VG:MJP1998, author = {Ruggero Milanese and Alain Jacot-Descombes and Thierry Pun and Fr{\'e}d{\'e}ric Deguillaume and Lori Petrucci and Michel Cherbuliez and Andr{\'e} De Giacomi}, title = {Distributed Video Editing, Archival and Retrieval}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1998}, vgclass = {report}, vgproject = {dvp,cbir}, number = {98.02}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {February}, note = {(Final Report, ACTS Project DVP, Distributed Video Production)}, abstract = {Within the Distributed Video Production project (European Union ACTS A089), the goal of the Distributed Video Editing, Archival and Retrieval (DVER) application is to provide broadcasters with a complete solution for distributed video post-production. This system should combine together archival, retrieval, and editing functionalities in order to increase the accessibility and reuse of archive material. Moreover, the system should be geographically distributed, guarantee a high degree of portability to different platforms, and employ digital video using standard compression formats. All these objectives have been achieved, and a complete prototype has been integrated and put in operation by our end user (MegaChannel TV) for news post-production.}, url = { http://vision.unige.ch/publications/postscript/98/VGTR98.02_MilaneseJacot-DescombesPun_et_al.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/VGTR98.02_MilaneseJacot-DescombesPun_et_al.pdf} } @INPROCEEDINGS{VG:MiP1994, author = {Ruggero Milanese and Thierry Pun}, title = {Un mod\`ele computationnel de l'attention visuelle}, booktitle = {NSI 94, 7\`emes Journ\'ees Neurosciences et Sciences de l'Ing\'enieur}, year = {1994}, vgclass = {refpap}, vgproject = {unspecified}, pages = {19--22}, address = {Chamonix, France}, month = {May}, note = {(extended abstract)} } @INPROCEEDINGS{VG:MPG1994, author = {Ruggero Milanese and Thierry Pun and Sylvia Gil and Jean-Marc Bost}, title = {Exploiting dynamic aspects of visual perception for objects recognition}, booktitle = {PerAc 94, From Perception to Action, Lausanne, Switzerland}, year = {1994}, vgclass = {refpap}, vgproject = {unspecified}, editor = {P. Gaussier and J.-D. Nicoud}, pages = {193--205}, month = {September}, publisher = {IEEE Computer Society Press} } @INCOLLECTION{VG:MPW1993, author = {Ruggero Milanese and Thierry Pun and Harry Wechsler}, title = {A non-linear integration process for the selection of visual information}, booktitle = {Intelligent Perceptual Systems: New Directions in Computational Perception}, publisher = {Springer-Verlag}, year = {1993}, editor = {V. Roberto}, volume = {745}, series = {Lecture Notes in Artificial Intelligence}, pages = {322--336}, url = { ftp://cui.unige.ch/PUBLIC/vision/papers/milanese/93.lnai.springer-verlag.ps.Z}, vgclass = {refpap}, vgproject = {unspecified} } @INPROCEEDINGS{VG:MPW1994, author = {Ruggero Milanese and Thierry Pun and Harry Wechsler}, title = {Integration of bottom-up and top-down information for visual attention}, booktitle = {4th AI*IA Congress, Workshop on Perception and Robotics, Parma, Italy}, year = {1994}, vgclass = {refpap}, vgproject = {unspecified}, month = {September} } @INPROCEEDINGS{VG:MPW1992, author = {Ruggero Milanese and Thierry Pun and Harry Wechsler}, title = {A bottom-up attention system for active vision}, booktitle = {Second Workshop on Perception, AI*IA (Associazione Italiana per l'Intelligenza Artificiale), Trieste}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October} } @INPROCEEDINGS{VG:MSP1996, author = {Ruggero Milanese and David McG. Squire and Thierry Pun}, title = {Correspondence Analysis and Hierarchical Indexing For Content-Based Image Retrieval}, booktitle = {IEEE International Conference on Image Processing}, year = {1996}, vgclass = {refpap}, vgproject = {viper}, editor = {P. Delogne}, volume = {3}, pages = {859--862}, address = {Lausanne, Switzerland}, month = {September}, abstract = {This paper describes a two-stage statistical approach supporting content-based search in image databases. The first stage performs correspondence analysis, a factor analysis method transforming image attributes into a reduced-size, uncorrelated factor space. The second stage performs ascendant heirarchical classification, an iterative clustering method which constructs a heirarchical index structure for the images of the database. Experimental results supporting the applicability of both techniques to data sets of heterogeneous images are reported.}, url = { http://vision.unige.ch/publications/postscript/96/MSP96_icip_paper.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/96/MSP96_icip_paper.pdf} } @INPROCEEDINGS{VG:MWG1994, author = {Ruggero Milanese and Harry Wechsler and Sylvia Gil and Jean-Marc Bost and Thierry Pun}, title = {Integration of bottom-up and top-down cues for visual attention using non-linear relaxation}, booktitle = {IEEE - CVPR 94 (Computer Vision and Pattern Recognition), Seattle, Washington}, year = {1994}, vgclass = {refpap}, vgproject = {unspecified}, pages = {781--785}, month = {June}, publisher = {IEEE Computer Society Press}, url = { ftp://cui.unige.ch/PUBLIC/vision/papers/milanese/94.06.cvpr94.300dpi.ps.Z} } @TECHREPORT{VG:MWG1994a, author = {Ruggero Milanese and Harry Wechsler and Sylvia Gil and Jean-Marc Bost and Thierry Pun}, title = {Integration of bottom-up and top-down cues for visual attention using non-linear relaxation}, institution = {International Computer Science Institute}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {TR-94-014}, address = {Berkeley, CA}, month = {March}, url = {http://vision.unige.ch/publications/postscript/94/tr-94-014.ps.gz} } @ARTICLE{Moenne-Loccoz2006, author = {Nicolas Mo\"enne-Loccoz and Bruno Janvier and St\'ephane Marchand-Maillet and Eric Bruno}, title = {Handling Temporal Heterogeneous Data for Content-Based Management of Large Video Collections}, journal = {Multimedia Tools and Applications}, year = {2006}, volume = {31}, pages = {309-325}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://www.springerlink.com/content/b323103150v76742/} } @ARTICLE{moenne2005b, author = {Nicolas Mo\"enne-Loccoz and Bruno Janvier and St\'ephane Marchand-Maillet and Eric Bruno}, title = {Handling Temporal Heterogeneous Data for Content-Based Management of Large Video Collections}, journal = {Multimedia Tools and Applications}, year = {2005}, note = {(to appear)}, url = {http://viper.unige.ch/lib/data/paperNotOnline.pdf} } @INPROCEEDINGS{nml_amr05, author = {Nicolas Moenne-Loccoz and Eric Bruno and St{\'e}phane Marchand Maillet}, title = {Interactive Retrieval of Video Sequences from Local Feature Dynamics}, booktitle = {Proceedings of the 3rd International Workshop on Adaptive Multimedia Retrieval, AMR'05}, year = {2005}, address = {Glasgow, UK}, month = {July} } @INPROCEEDINGS{nml_icip05, author = {Nicolas Moenne-Loccoz and Eric Bruno and St{\'e}phane Marchand-Maillet}, title = {Interactive Partial Matching of Video Sequences in Large Collections}, booktitle = {IEEE International Conference on Image Processing (ICIP'05)}, year = {2005}, address = {Genova, Italy} } @ARTICLE{moennePAA2005, author = {Nicolas Moenne-Loccoz and {\'E}ric Bruno and St{\'e}phane Marchand-Maillet}, title = {Knowledge-based Detection of Events in Video Streams from Salient Regions of Activities}, journal = {Pattern Analysis and Applications (PAA), special issue Video Event Mining}, year = {2005}, note = {DOI: 10.1007/s10044-004-0235-0}, url = {http://www.springerlink.com/app/home/contribution.asp?wasp=ca2c7ba28940434893bb7ff52333bc1f\&referrer=parent\&backto=issue,1,9;journal,1,23;linkingpublicationresults,1:103609,1} } @MISC{VG:Mon1993, vgclass = {diploma}, vgproject = {unspecified}, author = {Daniel Monteiro}, title = {Etude, sp\'ecification et implantation sur machine r\'epartie d'un syst\`eme modulaire de vision}, howpublished = {Diploma thesis, University of Geneva}, month = {November}, year = {1993}, note = {(travail r\'ealis\'e avec le groupe Parall\'elisme)} } @INPROCEEDINGS{Moustakas:SIMILAR2006:MTIIVIDMP, author = {Konstantinos Moustakas and Georgios Nikolakis and Dimitrios Tzovaras and Beno\^{i}t Deville and Guido Bologna and Ioannis Marras and Jakov Pavlek}, title = {Multimodal tools and interfaces for the intercommunication between visually impaired and "deaf and mute" people}, booktitle = {Proceedings of the eNTERFACE 2006 Workshop}, year = {2006}, vgclass = {refpap}, vgproject = {seecolor}, address = {Dubrovnik, Croatia}, month = {july--August} } @TECHREPORT{VG:Oct0304, author = {Nicolas Mo{\"e}nne-Loccoz}, title = {Characterizing activity in video shots based on salient points}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2003}, vgclass = {report}, vgproject = {viper}, number = {03.04}, address = {rue General Dufour, 24, CH-1211, Geneva, Switzerland}, month = {October} } @INPROCEEDINGS{moennen:2005:ICIP, author = {Nicolas Mo{\"e}nne-Loccoz and Eric Bruno and St{\'e}phane Marchand-Maillet}, title = {Interactive Partial Matching of Video Sequences in Large Collections}, booktitle = {{IEEE} International Conference on Image Processing}, year = {2005}, vgclass = {refpap}, vgproject = {viper}, address = {Genova, Italy}, month = {11-14 September}, note = {accepted} } @INPROCEEDINGS{VG:MoenneLoccoz04video, author = {Nicolas Mo{\"e}nne-Loccoz and {\'E}ric Bruno and St{\'e}phane Marchand-Maillet}, title = {Video Content Representation as Salient Regions of Activity}, booktitle = {Proceedings of the International Conference on Image and Video Retrieval}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {Dublin, Ireland} } @INPROCEEDINGS{VG:MoenneLoccoz04managing, author = {Nicolas Mo{\"e}nne-Loccoz and Bruno Janvier and {\'E}ric Bruno and St{\'e}phane Marchand-Maillet}, title = {Managing Video at Large}, booktitle = {Proceedings of the ACM SIGMOD Workshop on Computer Vision meets Databases}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {Paris, France} } @INPROCEEDINGS{VG:MoenneLoccoz04integrating, author = {Nicolas Mo{\"e}nne-Loccoz and Bruno Janvier and St{\'e}phane Marchand-Maillet and {\'E}ric Bruno}, title = {An Integrating Framework for the Management of Video Collections}, booktitle = {Proceedings of the 2004 First Workshop on Machine Learning and Multimodal Interaction, {MLMI'04}}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, series = {Lecture Notes in Computer Science 3361}, address = {Martigny, Switzerland}, month = {June}, url = {http://vision.unige.ch/publications/postscript/2004/moennen.mlmi04.pdf} } @INPROCEEDINGS{VG:Muller04benchmarking, author = {Henning Muller and Antoine Geissbuhler and St{\'e}phane Marchand-Maillet and Paul Clough}, title = {Benchmarking Image Retrieval Applications}, booktitle = {Proceedings of the 7th Internatinoal Conference on VISual Information Systems {(VIS'2004)}}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {San Francisco, USA} } @MISC{VG:Mue2002, vgclass = {otherjournals}, vgproject = {viper}, author = {Henning M{\"u}ller}, title = {{J}\"ager des verlorenen {F}otos - {D}as {GNU} {I}mage {F}inding {T}ool in der {P}raxis}, howpublished = {ct Magazin {f\"ur} Computertechnik, Volume 6, pp. 252--257}, year = {2002}, pages = {252--257} } @PHDTHESIS{VG:MulH2002, author = {Henning M{\"u}ller}, title = {User interaction and evaluation in content-based visual information retrieval}, school = {Computer Vision and Multimedia Laboratory, University of Geneva}, year = {2002}, address = {Geneva, Switzerland}, month = {June}, vgproject = {viper} } @MISC{VG:Mue2001, vgclass = {otherjournals}, vgproject = {viper}, author = {Henning M{\"u}ller}, title = {{S}uchen ohne {W}orte -- wie inhaltsbasierte {S}uche funktioniert}, howpublished = {ct Magazin {f\"ur} Computertechnik, Volume 15, pp.162--172}, year = {2001}, pages = {162--172} } @INPROCEEDINGS{VG:MMP2002, author = {Henning M{\"u}ller and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {The Truth About {C}orel -- Evaluation in Image Retrieval}, booktitle = {Proceedings of The Challenge of Image and Video Retrieval {(CIVR2002)}}, year = {2002}, vgclass = {refpap}, vgproject = {viper}, address = {London, UK}, month = {July}, note = {(to appear)} } @INPROCEEDINGS{VG:MMM2000b, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and St{\'e}phane Marchand-Maillet and David McG. Squire}, title = {Strategies for positive and negative relevance feedback in image retrieval}, booktitle = {Proceedings of the International Conference on Pattern Recognition (ICPR'2000)}, year = {2000}, vgclass = {refpap}, vgproject = {viper}, editor = {A. Sanfeliu and J.J. Villanueva and M. Vanrell and R. Alquezar and J.-O. Eklundh and Y. Aloimonos}, volume = {1}, series = {Computer Vision and Image Analysis}, pages = {1043-1046}, address = {Barcelona, Spain}, month = {sep 3--8}, abstract = {Relevance feedback has been shown to be a very effective tool for enhancing retrieval results in text retrieval. In content-based image retrieval it is more and more frequently used and very good results have been obtained. However, too much negative feedback may destroy a query as good features get negative weightings. This paper compares a variety of strategies for positive and negative feedback. The performance evaluation of feedback algorithms is a hard problem. To solve this, we obtain judgments from several users and employ an automated feedback scheme. We can then evaluate different techniques using the same judgments. Using automated feedback, the ability of a system to adapt to the user s needs can be measured very effectively. Our study highlights the utility of negative feedback, especially over several feedback steps.}, url = { http://vision.unige.ch/publications/postscript/2000/MullerHMuellerWMarchandPunSquire_icpr2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/MullerHMuellerWMarchandPunSquire_icpr2000.pdf} } @INPROCEEDINGS{VG:IJMTA03, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and St{\'e}phane Marchand-Maillet and David McG. Squire and Thierry Pun}, title = {A framework for benchmarking in visual information retrieval}, booktitle = {Int. Journal on Multimedia Tools and Applications (Kluwer), Special Issue on Multimedia Information Retrieval}, year = {2003}, vgclass = {refpap}, vgproject = {viper}, volume = {21}, number = {2}, pages = {55-73}, url = {http://vision.unige.ch/publications/postscript/2003/}, url1 = {http://vision.unige.ch/publications/postscript/2003/} } @ARTICLE{VG:MMM2002, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and St{\'e}phane Marchand-Maillet and David McG. Squire and Thierry Pun}, title = {A Framework for Benchmarking in Visual Information Retrieval}, journal = {International Journal on Multimedia Tools and Applications}, year = {2002}, vgclass = {refpap}, vgproject = {viper}, note = {(Special Issue on Multimedia Information Retrieval) - to appear} } @TECHREPORT{VG:MMM2001, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and St{\'e}phane Marchand-Maillet and David McG. Squire and Thierry Pun}, title = {Automated benchmarking in content-based image retrieval}, institution = {University of Geneva}, year = {2001}, vgclass = {report}, vgproject = {viper}, number = {01.01}, month = {May}, abstract = {Benchmarking has always been a crucial problem in content-based image retrieval (CBIR). A key issue is the lack of a common access method to retrieval systems, such as SQL for relational databases. The Multimedia Retrieval Mark-up Language (MRML) solves this problem by standardizing access to CBIR systems (CBIRSs). Other difficult problems are also shortly addressed, such as obtaining relevance judgments and choosing a database for performance comparison. In this article we present a fully automated benchmark for CBIRSs based on MRML, which can be adapted to any image database and almost any kind of relevance judgment. The test evaluates the performance of positive and negative relevance feedback, which can be generated automatically from the relevance judgments. To illustrate our purpose, a freely available, non-copyright image collection is used to evaluate our CBIRS, \emph{Viper}. All scripts described here are also freely available for download.}, url = { http://vision.unige.ch/publications/postscript/2001/MuellerHMuellerWMarchandSquirePun_tr01.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2001/MuellerHMuellerWMarchandSquirePun_tr01.ps.gz} } @INPROCEEDINGS{VG:MMMSP2001, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and St{\'e}phane Marchand-Maillet and David McG. Squire and Thierry Pun}, title = {A Web-Based Evaluation System for Content-Based Image Retrieval}, booktitle = {Proceedings of the {ACM} Multimedia Workshop on Multimedia Information Retrieval {(ACM} {MIR} 2001)}, year = {2001}, vgclass = {refpap}, vgproject = {viper}, pages = {50--54}, address = {Ottawa, Canada} } @INPROCEEDINGS{VG:MMS2000e, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Learning features weights from user behavior in Content-Based Image Retrieval}, booktitle = {ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Workshop on Multimedia Data Mining MDM/KDD2000)}, year = {2000}, vgclass = {refpap}, vgproject = {viper}, editor = {S.J. Simoff and O.R. Zaiane}, address = {Boston, MA, USA}, month = {aug 20-23}, abstract = {This article describes an algorithm for obtaining knowledge about the importance of features from analyzing user log files of a content-based image retrieval system (CBIRS). The user log files from the usage of the \emph{Viper} web demonstration system a re analyzed over a period of four months. Within this period about 3500 accesses to the system were made w ith almost 800 multiple image queries. All the actions of the users were logged in a file. The analysis only includes multiple image queries of the system with positive and/or negative input images, because only multiple image q ueries contain enough information for the method described. Features frequently present in images marked together positively in the same que ry step get a higher weighting, whereas features present in one image marked positively and an other image marked negatively in the same step get a lower weighting. The \emph{Viper} system offers a very large number of simple features. This allows the creation of flexible feature weightings with high values for importan t and low values for less important features. These weightings for features can of course differ between collections and as well between users. The results are evaluated with an experiment using the relevance judgments of re al users on a database containing 2500 images. The results of the system with learned weights are compared to the system withou t the learned feature weights.}, url = { http://vision.unige.ch/publications/postscript/2000/MuellerHMuellerWSquireMarchandPun_mdmkdd2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/MuellerHMuellerWSquireMarchandPun_mdmkdd2000.pdf} } @ARTICLE{VG:MMS2001, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Performance Evaluation in Content-Based Image Retrieval: Overview and Proposals}, journal = {Pattern Recognition Letters (Special Issue on Image and Video Indexing)}, year = {2001}, volume = {22}, pages = {593--601}, vgclass = {refpap}, vgproject = {viper}, number = {5}, note = {H. Bunke and X. Jiang Eds.}, abstract = {Evaluation of retrieval performance is a crucial problem in content-based image retrieval (CBIR). Many different methods for measuring the performance of a system have been created and used by researchers. This article discusses the advantages and shortcomings of the performance measures currently used. Problems such as defining a common image database for performance comparisons and a means of getting relevance judgments (or ground truth) for queries are explained. The relationship between CBIR and information retrieval (IR) is made clear, since IR researchers have decades of experience with the evaluation problem. Many of their solutions can be used for CBIR, despite the differences between the fields. Several methods used in text retrieval are explained. Proposals for performance measures and means of developing a standard test suite for CBIR, similar to that used in IR at the annual Text REtrieval Conference (TREC), are presented. (c) Copyright 2001, Elsevier Science, All rights reserved.}, url = {http://www.elsevier.nl/gej-ng/10/35/61/49/29/36/abstract.html} } @INPROCEEDINGS{VG:MMS2001a, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Automated Benchmarking in Content-based Image Retrieval}, booktitle = {Proceedings of the 2001 IEEE International Conference on Multimedia and Expo (ICME2001)}, year = {2001}, vgclass = {refpap}, vgproject = {viper}, address = {Tokyo, Japan}, month = {August}, abstract = {Benchmarking has always been a crucial problem in content-based image retrieval (CBIR). A key issue is the lack of a common access method to retrieval systems, such as SQL for relational databases. The Multimedia Retrieval Mark-up Language (MRML) solves this problem by standardizing access to CBIR systems (CBIRSs). Other difficult problems are also shortly addressed, such as obtaining relevance judgments and choosing a database for performance comparison. In this article we present a fully automated benchmark for CBIRSs based on MRML, which can be adapted to any image database and almost any kind of relevance judgment. The test evaluates theperformance of positive and negative relevance feedback, which can be generated automatically from the relevance judgments. To illustrate our purpose, a freely available, non-copyright image collection is used to evaluate our CBIRS, Viper. All scripts described here are also freely available for download.}, url = {http://www.giti.waseda.ac.jp/ICME2001/} } @TECHREPORT{VG:MMS2000, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Strategies for positive and negative relevance feedback in image retrieval}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {2000}, vgclass = {report}, vgproject = {viper}, number = {00.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {jan}, abstract = {Relevance feedback has been shown to be a very effective tool for enhancing retrieval results in text retrieval. In content-based image retrieval it is more and more frequently used and very good results have been obtained. However, too much negative feedback may destroy a query as good features get negative weightings. This paper compares a variety of strategies for positive and negative feedback. The performance evaluation of feedback algorithms is a hard problem. To solve this, we obtain judgments from several users and employ an automated feedback scheme. We can then evaluate different techniques using the same judgments. Using automated feedback, the ability of a system to adapt to the user's needs can be measured very effectively. Our study highlights the utility of negative feedback, especially over several feedback steps.}, url = { http://vision.unige.ch/publications/postscript/2000/VGTR00.01_HMuellerWMuellerSquireMarchandPun.ps}, url1 = { http://vision.unige.ch/publications/postscript/2000/VGTR00.01_HMuellerWMuellerSquireMarchandPun.pdf} } @TECHREPORT{VG:MMS2000b, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Long-Term Learning from User Behavior in Content-Based Image Retrieval}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {2000}, vgclass = {report}, vgproject = {viper}, number = {00.04}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {mar}, abstract = {This article describes a simple algorithm for obtaining knowledge about the importance of features from analyzing user log files of a content-based image retrieval system (CBIRS). The user log files of the usage of the Viper web demonstration system are analyzed over a period of four months. In this time about 3500 accesses to the system were made with 800 multiple image queries. The analysis only takes into account multiple image queries of the system with positive or negative input images, because only these queries contain enough information for the method described in the paper. Features frequently present in images marked together positively in the same query step get a higher weighting whereas features present in an image marked positively and another image marked negatively in the same step get a lower weighting. The Viper system offers a very large number of simple features which allows the creation of feature weightings with high values for important and low values for less important features. These weightings for features can of course differ for several collections and as well for several users. The results are evaluated using the relevance judgments of real users and compared to the system without the long-term learning.}, url = { http://vision.unige.ch/publications/postscript/2000/VGTR00.04_MuellerHMuellerWSquireMarchandPun.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/VGTR00.04_MuellerHMuellerWSquireMarchandPun.pdf} } @INPROCEEDINGS{VG:MMS2000f, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Lernen von Merkmalsgewichtungen beim inhaltsbasierten Suchen in grossen Bilddatenbanken (Content-based image retrieval)}, booktitle = {Proceedings of the Fachwissenschaftlicher Informatik-Kongress}, year = {2000}, vgclass = {fullconf}, vgproject = {viper}, pages = {304--307}, address = {Bad Schussenried, Germany}, month = {oct}, url = { http://vision.unige.ch/publications/postscript/2000/MuellerHMuellerWSquireMarchandPun_fik2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/MuellerHMuellerWSquireMarchandPun_fik2000.pdf} } @TECHREPORT{VG:MMS2000a, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and Zoran Pe\u{c}enovi\'{c} and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {An Open Framework for Distributed Multimedia Retrieval}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {2000}, vgclass = {report}, vgproject = {viper}, number = {00.03}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {mar}, abstract = {This article describes a framework for distributed multimedia retrieval which permits the connection of compliant user interfaces with a variety of multimedia retrieval engines via an open communication protocol, MRML (Multi Media Retrieval Markup Language). It allows the choice of image collection, feature set and query algorithm during run--time, permitting multiple users to query a system adapted to their needs, using the query paradigm adapted to their problem such as query by example (QBE), browsing queries, or query by annotation. User interaction is implemented over several levels and in diverse ways. Relevance feedback is implemented using positive and negative example images that can be used for a best--match QBE query. In contrast, browsing methods try to ap proach the searched image by giving overviews of the entire collection and by successive refinements. In addition to these query methods, Long term off line learning is implemented. It allows feature preferences per user, user domain or over all users to be learned automatically. We present the Viper multimedia retrieval system as the core of the framework and an example of an MRML-compliant search engine. Viper uses techniques adapted from traditional information retrieval (IR) to retrieve multimedia documents, thus benefiting from the many years of IR research. As a result, textual and visual features are treated in the same way, facilitating true multimedia retrieval. The MRML protocol also allows other applications to make use of the search engi nes. This can for example be used for the design of a benchmark test suite, querying several search engines in the same way and comparing the results. This is motivated by the fact that the content--based image retrieval community really lacks such a benchmark as it already exists in text retrieval.}, url = { http://vision.unige.ch/publications/postscript/2000/VGTR00.03_MuellerHMuellerWSquirePecenovicMarchandPun.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/VGTR00.03_MuellerHMuellerWSquirePecenovicMarchandPun.pdf} } @INPROCEEDINGS{VG:MMS2000c, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and Zoran Pe\u{c}enovi\'{c} and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {An Open Framework for Distributed Multimedia Retrieval}, booktitle = {Recherche d'Informations Assist\'ee par Ordinateur (RIAO'2000) Computer-Assisted Information Retrieval}, year = {2000}, vgclass = {refpap}, vgproject = {viper}, volume = {1}, pages = {701--712.}, address = {Paris, France}, month = {apr 12-14}, abstract = {This article describes a framework for distributed multimedia retrieval which permits the connection of compliant user interfaces with a variety of multimedia retrieval engines via an open communication protocol, MRML (Multi Media Retrieval Markup Language). It allows the choice of image collection, feature set and query algorithm during run--time, permitting multiple users to query a system adapted to their needs, using the query paradigm adapted to their problem such as query by example (QBE), browsing queries, or query by annotation. User interaction is implemented over several levels and in diverse ways. Relevance feedback is implemented using positive and negative example images that can be used for a best--match QBE query. In contrast, browsing methods try to approach the searched image by giving overviews of the entire collection and by successive refinement. In addition to these query methods, Long term off line learning is implemented. It allows feature preferences per user, user domain or over all users to be learned automatically. We present the Viper multimedia retrieval system as the core of the framework and an example of an MRML-compliant search engine. Viper uses techniques adapted from traditional information retrieval (IR) to retrieve multimedia documents, thus benefiting from the many years of IR research. As a result, textual and visual features are treated in the same way, facilitating true multimedia retrieval. The MRML protocol also allows other applications to make use of the search engnes. This can for example be used for the design of a benchmark test suite, querying several search engines in the same way and comparing the results. This is motivated by the fact that the content--based image retrieval community really lacks such a benchmark as it already exists in text retrieval.}, url = { http://vision.unige.ch/publications/postscript/2000/MullerHMullerWSquirePecenovicMarchandPun_riao.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/MullerHMullerWSquirePecenovicMarchandPun_riao.pdf} } @TECHREPORT{VG:MMS1999, author = {Henning M{\"u}ller and Wolfgang M{\"u}ller and David McG. Squire and Thierry Pun}, title = {Performance Evaluation in Content-Based Image Retrieval: Overview and Proposals}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1999}, vgclass = {report}, vgproject = {viper}, number = {99.05}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {dec}, abstract = {Evaluation of retrieval performance is a crucial problem in content-based image retrieval (CBIR). Many different methods for measuring the performance of a system have been created and used by researchers. This article discusses the advantages and shortcomings of the performance measures currently used. Problems such as a common image database for performance comparisons and a means of getting relevance judgments (or ground truth) for queries are explained. The relationship between CBIR and information retrieval (IR) is made clear, since IR researchers have decades of experience with the evaluation problem. Many of their solutions can be used for CBIR, despite the differences between the fields. Several methods used in text retrieval are explained. Proposals for performance measures and means of developing a standard test suite for CBIR, similar to that used in IR at the annual Text REtrieval Conference (TREC), are presented.}, url = { http://vision.unige.ch/publications/postscript/99/VGTR99.05_HMuellerWMuellerSquirePun.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/VGTR99.05_HMuellerWMuellerSquirePun.pdf} } @TECHREPORT{VG:MSM1999, author = {Henning M{\"u}ller and David McG. Squire and Wolfgang M{\"u}ller and Thierry Pun}, title = {Efficient access methods for content-based image retrieval with inverted files}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1999}, vgclass = {report}, vgproject = {viper}, number = {99.02}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {July}, abstract = {As human factor studies over the last thirty years have shown, response time is a very important factor for the usability of an interactive system, especially on the world wide web. In particular, response times of under one second are often specified as a usability requirement \cite{Nie97}. This paper compares several methods for improving the evaluation time in a content-based image retrieval system (CBIRS) which uses inverted file technology. The use of the inverted file technology facilitates search pruning in a variety of ways, as is shown in this paper. For large databases ($> 2000$ images) and a high number of possible features ($> 80000$), efficient and fast access is necessary to allow interactive querying and browsing. Parallel access to the inverted file can reduce the response time. This parallel access is very easy to implement with little communication overhead, and thus scales well. Other search pruning methods, similar to methods used in information retrieval, can also reduce the response time significantly without reducing the performance of the system. The performance of the system is evaluated using precision vs. recall graphs, which are an established evaluation method in information retrieval. A user survey was carried out in order to obtain relevance judgments for the queries reported in this work.}, keywords = {inverted file, content-based image retrieval, efficient access, search pruning, speed evaluation}, url = { http://vision.unige.ch/publications/postscript/99/VGTR99.02_MuellerSquireMuellerPun.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/VGTR99.02_MuellerSquireMuellerPun.pdf} } @INPROCEEDINGS{VG:MSM1999c, author = {Henning M{\"u}ller and David McG. Squire and Wolfgang M{\"u}ller and Thierry Pun}, title = {Efficient access methods for content-based image retrieval with inverted files}, booktitle = {Multimedia Storage and Archiving Systems IV (VV02)}, year = {1999}, vgclass = {refpap}, vgproject = {viper}, volume = {3846}, series = {SPIE Proceedings}, address = {Boston, Massachusetts, USA}, month = {20--22~September}, note = {(SPIE Symposium on Voice, Video and Data Communications)}, abstract = {As human factor studies over the last thirty years have shown, response time is a very important factor for the usability of an interactive system, especially on the world wide web. In particular, response times of under one second are often specified as a usability requirement \cite{Nie97}. This paper compares several methods for improving the evaluation time in a content-based image retrieval system (CBIRS) which uses inverted file technology. The use of the inverted file technology facilitates search pruning in a variety of ways, as is shown in this paper. For large databases ($> 2000$ images) and a high number of possible features ($> 80000$), efficient and fast access is necessary to allow interactive querying and browsing. Parallel access to the inverted file can reduce the response time. This parallel access is very easy to implement with little communication overhead, and thus scales well. Other search pruning methods, similar to methods used in information retrieval, can also reduce the response time significantly without reducing the performance of the system. The performance of the system is evaluated using precision vs. recall graphs, which are an established evaluation method in information retrieval. A user survey was carried out in order to obtain relevance judgments for the queries reported in this work.}, keywords = {inverted file, content-based image retrieval, efficient access, search pruning, speed evaluation}, url = { http://vision.unige.ch/publications/postscript/99/MuellerHSquireMuellerWPun_msasIV.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/MuellerHSquireMuellerWPun_msasIV.pdf} } @INPROCEEDINGS{VG:MSM1999d, author = {Henning M{\"u}ller and David McG. Squire and Wolfgang M{\"u}ller and Thierry Pun}, title = {Content-based image retrieval, bildinhaltsbasiertes Suchen in gro{\ss}en Bilddatenbanken}, booktitle = {Informatiktage 99}, year = {1999}, vgclass = {fullconf}, vgproject = {viper}, address = {Bad Schussenried, Germany}, month = {12--13~November}, abstract = {Dieser Artikel beschreibt einen neuen Ansatz im Bereich des content-based image retrieval (CBIR), dem bildinhaltsbasierten Suchen in Bilddatenbanken in der Regel ohne Annotationen. Gegen\"uber den herk\"ommlichen meist vektorbasierten Verfahren werden hier Methoden des Text oder Information Retrieval (IR) an die speziellen Bed\"urfnisse des Empfangs von Bildern angepasst. Benutzerexperimente belegen die Leistungsf\"ahigkeit und Flexibilit\"at des Verfahrens.}, url = { http://vision.unige.ch/publications/postscript/99/MuellerHSquireMuellerWPun_it99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/MuellerHSquireMuellerWPun_it99.pdf} } @INPROCEEDINGS{VG:IJCV03, author = {Henning M{\"u}ller and David McG. Squire and Thierry Pun}, title = {Learning from user behavior in image retrieval: application of the market basket analysis}, booktitle = {Int. J. of Comp. Vision, Special Issue on Content-Based Image Retrieval, to appear}, year = {2003}, vgclass = {refpap}, vgproject = {viper} } @PHDTHESIS{VG:Mul2001, author = {Wolfgang M{\"u}ller}, title = {Design and implementation of a flexible Content--Based Image Retrieval Framework - The GNU Image Finding Tool}, school = {Computer Vision and Multimedia Laboratory, University of Geneva}, year = {2001}, address = {Geneva, Switzerland}, month = {September}, vgproject = {viper} } @INPROCEEDINGS{VG:MMM2000c, author = {Wolfgang M{\"u}ller and St{\'e}phane Marchand-Maillet and Henning M{\"u}ller and Thierry Pun}, title = {Towards a fair benchmark for image browsers}, booktitle = {SPIE Photonics East, Voice, Video, and Data Communications}, year = {2000}, vgclass = {refpap}, vgproject = {viper}, address = {Boston, MA, USA}, month = {nov 5--8}, abstract = {The recent literature has shown that the principal difficulty in multimedia retrieval is the bridging of the "semantic gap" between the user's wishes and his ability to fomulate queries. This insight has spawned two main directions of research: Query By Example (QBE) with relevance feedback (i.e. learning to improve the result of a previsously formulated query) and the research in query formulation techniques, like browsing or query by sketch. Browsing techniques try to help the user in finding his target image, or an image which is sufficiently close to the desired result that it can be used in a subsequent QBE query. From the feature space viewpoint, each browsing system tries to permit the user to move consciously in feature space and eventually reach the target image. How to provide this functionality to the user is presently an open question. In fact even obtaining objective performance evaluation and comparison of these browsing paradigms is difficult. We distinguish here between deterministic browsers, which try to optimise the possibility for the user to learn how the system behaves, and stochastic browsers based on more sophisticated Monte-Carlo algorithms thus sacrificing reproducibility to a better performance. Presently, these two browsing paradigms are practically incomparable, except by large scale user studies. This makes it infeasible for research groups to evaluate incremental improvement of browsing schemes. Moreover, automated benchmarks in the current literature simulate a user by a model derived directly from the distance measures used within the tested systems. Such a circular reference cannot provide a serious alternative to real user tests. In this paper, we present an automatic benchmark which uses user-annotated collections for simulating the semantic gap, thus providing a means for automatic evaluation and comparison of the different browsing paradigms. We use a very precise annotation of few words together with a thesaurus to provide sufficiently smooth behaviour of the annotation-based user model. We discuss the design and evaluation of this annotation as well as the implementation of the benchmark in an MRML-compliant script with pluggable modules which allow testing of new interaction schemes (see http://www.mrml.net).}, url = { http://vision.unige.ch/publications/postscript/2000/MuellerWMarchandMuellerHPun_spie2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/MuellerWMarchandMuellerHPun_spie2000.pdf} } @ARTICLE{VG:MMMSP2001a, author = {Wolfgang M{\"u}ller and St{\'e}phane Marchand-Maillet and Henning M{\"u}ller and David McG. Squire and Thierry Pun}, title = {Evaluating Image Browsers Using Structured Annotation}, journal = {Journal of American for Information Science and Technology (JASIST)}, year = {2001}, volume = {52}, vgclass = {refpap}, vgproject = {viper}, number = {11} } @TECHREPORT{VG:MMM2000, author = {Wolfgang M{\"u}ller and Henning M{\"u}ller and St{\'e}phane Marchand-Maillet and Thierry Pun and David McG. Squire and Zoran Pe\u{c}enovi\'{c} and Christoph Giess and Arjen P. de Vries}, title = {{MRML}: A Communication Protocol for Content-Based Image Retrieval}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {2000}, vgclass = {report}, vgproject = {viper}, number = {00.02}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {mar}, abstract = {In this paper we introduce and describe the Multimedia Retrieval Markup Language (MRML). This XML-based markup language is the basis for an open communication protocol for content-based image retrieval systems (CBIRSs). MRML was initially designed as a means of separating CBIR engines from their user interfaces. It is, however, also extensible as the basis for standardized performance evaluation procedures. Such a tool is essential for the formulation and implementation of common benchmarks for CBIR. A common protocol can also bring new dynamics to the CBIR field---it makes the development of new systems faster and more efficient, and opens the door of the CBIR research field to other disciplines such as Human-Computer Interaction. The MRML specifications, as well as the first MRML-compliant applications, are freely available and are introduced in this paper.}, url = { http://vision.unige.ch/publications/postscript/2000/VGTR00.02_MuellerWMuellerHMarchandPunSquireGiessVries.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/VGTR00.02_MuellerWMuellerHMarchandPunSquireGiessVries.pdf} } @INPROCEEDINGS{VG:MMM2000a, author = {Wolfgang M{\"u}ller and Henning M{\"u}ller and St{\'e}phane Marchand-Maillet and Thierry Pun and David McG. Squire and Zoran Pe\u{c}enovi\'{c} and Christoph Giess and Arjen P. de Vries}, title = {{MRML}: A Communication Protocol for Content-Based Image Retrieval}, booktitle = {International Conference on Visual Information Systems (Visual 2000)}, year = {2000}, vgclass = {refpap}, vgproject = {viper}, address = {Lyon, France}, month = {nov 2--4}, abstract = {In this paper we introduce and describe the Multimedia Retrieval Markup Language (MRML). This XML-based markup language is the basis for an open communication protocol for content-based image retrieval systems (CBIRSs). MRML was initially designed as a means of separating CBIR engines from their user interfaces. It is, however, also extensible as the basis for standardised performance evaluation procedures. Such a tool is essential for the formulation and implementation of common benchmarks for CBIR. A common protocol can also bring new dynamics to the CBIR field --- it makes the development of new systems faster and more efficient, and opens the door of the CBIR research field to other disciplines such as Human-Computer Interaction. The MRML specifications, as well as the first MRML-compliant applications, are freely available and are introduced in this paper.}, url = { http://vision.unige.ch/publications/postscript/2000/MuellerWMuellerHMarchandPunSquireGiessVries_visual2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/MuellerWMuellerHMarchandPunSquireGiessVries_visual2000.pdf} } @INPROCEEDINGS{VG:MMM2000d, author = {Wolfgang M{\"u}ller and Henning M{\"u}ller and St{\'e}phane Marchand-Maillet and Thierry Pun and David McG. Squire and Zoran Pecenovic and Christof Giess and Arjen P. de Vries}, title = {MRML: A communication protocol for content-based multimedia retrieval}, booktitle = {Proposal, ISO/IEC JTC1/SC29/WG11, MPEG00/M6099, Int. Organiz. for Standardization, Coding of Moving Pictures and Associated Audio}, year = {2000}, vgclass = {fullconf}, vgproject = {viper}, address = {Geneva}, month = {May 30 - June 2} } @TECHREPORT{VG:MPV1999, author = {Wolfgang M{\"u}ller and Zoran Pe\u{c}enovi\'{c} and Arjen P. de Vries and David McG. Squire and Henning M{\"u}ller and Thierry Pun}, title = {{MRML}: Towards an extensible standard for multimedia querying and benchmarking (Draft Proposal)}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1999}, vgclass = {report}, vgproject = {viper}, number = {99.04}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {October}, url = { http://vision.unige.ch/publications/postscript/99/VGTR99.04_WMuellerPecenovicdeVriesSquireHMuellerPun.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/VGTR99.04_WMuellerPecenovicdeVriesSquireHMuellerPun.pdf} } @INPROCEEDINGS{VG:MPM2000, author = {Wolfgang M{\"u}ller and Zoran Pecenovic and Henning M{\"u}ller and St{\'e}phane Marchand-Maillet and Thierry Pun and David McG. Squire and Arjen P. De Vries and Christoph Giess}, title = {MRML: An Extensible Communication Protocol for Interoperability and Benchmarking of Multimedia Information Retrieval Systems}, booktitle = {SPIE Photonics East - Voice, Video, and Data Communications}, year = {2000}, vgclass = {refpap}, vgproject = {viper}, address = {Boston, MA, USA}, month = {nov 5--8}, abstract = {While in the area of relational databases interoperability is ensured by common communication protocols (e.g. ODBC/JDBC using SQL), Content Based Image Retrieval Systems (CBIRS) and other multimedia retrieval systems are lacking both a common query language and a common communication protocol. Besides its obvious short term convenience, interoperability of systems is crucial for the exchange and analysis of user data. In this paper, we present and describe an extensible XML-based query markup language, called MRML (Multimedia Retrieval Markup Language). MRML is primarily designed so as to ensure interoperability between different content based multimedia retrieval systems. Further, MRML allows researchers to preserve their freedom in extending their system as needed. MRML encapsulates multimedia queries in a way that enables multimedia (MM) query languages, MM content descriptions, MM query engines, and MM user interfaces to grow independently from each other, reaching a maximum of interoperability while ensuring a maximum of freedom for the developer. For benefiting from this, only a few simple design principles have to be respected when extending MRML for one's private needs. The design of extensions within the MRML framework will be described in detail in the paper. MRML has been implemented and tested for the CBIRS Viper, using the user interface SnakeCharmer. Both are under GNU Public License and can be downloaded at http://viper.unige.ch/download/}, url = { http://vision.unige.ch/publications/postscript/2000/MuellerWPecenovicMuellerHMarchandPunSquireDeVriesGiess_spie2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/MuellerWPecenovicMuellerHMarchandPunSquireDeVriesGiess_spie2000.pdf} } @TECHREPORT{VG:MSM1999a, author = {Wolfgang M{\"u}ller and David McG. Squire and Henning M{\"u}ller and Thierry Pun}, title = {Hunting moving targets: an extension to {B}ayesian methods in multimedia databases}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1999}, vgclass = {report}, vgproject = {viper}, number = {99.03}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {July}, abstract = {It has been widely recognised that the difference between the level of abstraction of the formulation of a query (by example) and that of the desired result (usually an image with certain semantics) calls for the use of learning methods that try to bridge this gap. Cox \emph{et al.}~have proposed a Bayesian method to learn the user's preferences during each query. Cox \emph{et al.}\'s system, \texttt{PicHunter}, is designed for optimal performance when the user is searching for a fixed target image. The performance of the system was evaluated using target testing, which ranks systems according to the number of interaction steps required to find the target, leading to simple, easily reproducible experiments. There are some aspects of image retrieval, however, which are not captured by this measure. In particular, the possibility of query drift (i.e.~a moving target) is completely ignored. The algorithm proposed by Cox \emph{et al.}~does not cope well with a change of target at a late query stage, because it is assumed that user feedback is noisy, but consistent. In the case of a moving target, however, the feedback is noisy \emph{and} inconsistent with earlier feedback. In this paper we propose an enhanced Bayesian scheme which selectively forgets inconsistent user feedback, thus enabling both the program and the user to ``change their minds''. The effectiveness of this scheme is demonstrated in moving target tests on a database of heterogeneous real-world images.}, keywords = {relevance feedback, query drift, target testing, Bayesian methods, user modelling}, url = { http://vision.unige.ch/publications/postscript/99/VGTR99.03_MuellerSquireMuellerPun.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/VGTR99.03_MuellerSquireMuellerPun.pdf} } @INPROCEEDINGS{VG:MSM1999b, author = {Wolfgang M{\"u}ller and David McG. Squire and Henning M{\"u}ller and Thierry Pun}, title = {Hunting moving targets: an extension to {B}ayesian methods in multimedia databases}, booktitle = {Multimedia Storage and Archiving Systems IV (VV02)}, year = {1999}, vgclass = {refpap}, vgproject = {viper}, volume = {3846}, series = {SPIE Proceedings}, address = {Boston, Massachusetts, USA}, month = {20--22~September}, note = {(SPIE Symposium on Voice, Video and Data Communications)}, abstract = {It has been widely recognised that the difference between the level of abstraction of the formulation of a query (by example) and that of the desired result (usually an image with certain semantics) calls for the use of learning methods that try to bridge this gap. Cox \emph{et al.}~have proposed a Bayesian method to learn the user's preferences during each query. Cox \emph{et al.}\'s system, \texttt{PicHunter}, is designed for optimal performance when the user is searching for a fixed target image. The performance of the system was evaluated using target testing, which ranks systems according to the number of interaction steps required to find the target, leading to simple, easily reproducible experiments. There are some aspects of image retrieval, however, which are not captured by this measure. In particular, the possibility of query drift (i.e.~a moving target) is completely ignored. The algorithm proposed by Cox \emph{et al.}~does not cope well with a change of target at a late query stage, because it is assumed that user feedback is noisy, but consistent. In the case of a moving target, however, the feedback is noisy \emph{and} inconsistent with earlier feedback. In this paper we propose an enhanced Bayesian scheme which selectively forgets inconsistent user feedback, thus enabling both the program and the user to ``change their minds''. The effectiveness of this scheme is demonstrated in moving target tests on a database of heterogeneous real-world images.}, keywords = {relevance feedback, query drift, target testing, Bayesian methods, user modelling}, url = { http://vision.unige.ch/publications/postscript/99/MuellerWSquireMuellerHPun_msasIV.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/MuellerWSquireMuellerHPun_msasIV.pdf} } @INPROCEEDINGS{VG:CBMI03c, author = {Henning M{\"}uller and Antoine Geissbuhler and St{\'e}phane Marchand-Maillet}, title = {Extension to the Multimedia Retrieval Markup Language: A communication protocol for content-based image retrieval}, booktitle = {Proceedings of the 3rd International Workshop on Content-Based Multimedia Indexing, CBMI'03}, year = {2003}, vgclass = {refpap}, vgproject = {viper}, address = {Rennes, France}, month = {September} } @TECHREPORT{VG:Nar1990, author = {Philippe Narbel}, title = {An analytical and critical review of shape-from-shading}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1990}, vgclass = {report}, vgproject = {unspecified}, number = {90.04}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {October} } @TECHREPORT{VG:Nar1990a, author = {Philippe Narbel}, title = {Lo{G} zero-crossings and their limitations}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1990}, vgclass = {report}, vgproject = {unspecified}, number = {90.05}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {October} } @MISC{VG:Nar1988, vgclass = {diploma}, vgproject = {unspecified}, author = {Philippe Narbel}, title = {Perception des formes: que faire de toutes ces lueurs, de toutes ces ombres? {O}ui, qu'en faire? {L}a m\'ethode du Shape-from-shading}, howpublished = {Diploma thesis, University of Geneva}, month = {December}, year = {1988} } @TECHREPORT{VG:NaP19, author = {Philippe Narbel and Thierry Pun}, title = {Journey through scale-space}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1989}, vgclass = {report}, vgproject = {unspecified}, number = {89.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {October} } @INPROCEEDINGS{VG:NaP1989, author = {Philippe Narbel and Thierry Pun}, title = {Searching for resolution focusing: a journey through scale-spaces}, booktitle = {1st SGAICO Conference, Computer Vision Workshop, Yverdon-Les-Bains, Switzerland}, year = {1989}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October} } @INPROCEEDINGS{VG:Pallotta04towards, author = {Vincenzo Pallotta and Afzal Ballim and St{\'e}phane Marchand-Maillet and Agnes Lisowska}, title = {Towards Meeting Information Sytems: Meeting Knowledge Management}, booktitle = {Proceedings of the International Conference on Enterprise Information Sytems {(ICEIS 04)}}, year = {2004}, vgclass = {refpap}, vgproject = {viper}, address = {Porto, Portugal} } @INPROCEEDINGS{Grave2003:HBM2003:DNIBCI, author = {R. Grave de Peralta Menendez and S. Gonzalez Andino and J. Millan and Thierry Pun}, title = {Direct non-invasive brain computer interfaces}, booktitle = {Human Brain Mapping}, year = {2003}, vgclass = {refpap}, vgproject = {bmi}, address = {New York, USA}, month = {June 18-22} } @PHDTHESIS{VG:Peir2000, author = {Shelby Pereira}, title = {Robust Digital Image Watermarking}, school = {Computer Vision Group -CUI - University of Geneva}, year = {2000}, address = {Geneva, Switzerland}, abstract = {Invisible Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyright material. While a myriad of algorithms have appeared in recent years, a number of problems remain. In this thesis we develop methods for robustly embedding and extracting 60 to 100 bits of information from an image. These bits can be used to link a buyer and a seller to a given image and consequently be used for copyright protection. When embedding the watermark, a fundamental tradeoff must be made between robustness, visibility and capacity. Robustness refers to the fact that the watermark must survive against attacks from potential pirates. Visibility refers to the requirement that the watermark be imperceptible to the eye. Finally, capacity refers to the amount of information that the watermark must carry. We present 2 fundamentally different approaches. The first approach is based on the Discrete Fourier Transform (DFT), the magnitude of which is used for embedding bits. Affine transformations on an image lead to corresponding affine transformations in the DFT which suggests that the DFT can be used to recover watermarks which have undergone such transformations. We propose the use of a template consisting of peaks in the DFT domain. If the image is transformed, the peaks are detected and the transformation is detected by solving a point matching problem. In order to ensure that the watermark is invisible, a noise visibility function is calculated in the spatial domain and after the embedding is performed in the DFT domain, the pixels are modulated in the spatial domain to ensure invisibility. Our results indicate that the proposed method successfully recovers watermarks from transformed images, but is relatively weak against compression and cropping. In recent years it has been recognized that embedding information in a transform domain leads to more robust watermarks. A major difficulty in watermarking in a transform domain lies in the fact that constraints on the allowable distortion at any pixel are usually specified in the spatial domain. Consequently the second approach consists of a general framework for optimizing the watermark strength in the trans- form domain when the visibility constraints are specified in the spatial domain. The main idea is to structure the watermark embedding as a linear programming prob- lem in which we wish to maximize the strength of the watermark subject to a set of linear constraints on the pixel distortions as determined by a masking function. We consider the special cases of embedding in the DCT domain and wavelet domainusing the Haar wavelet and Daubechies 4-tap filter in conjunction with a masking function based on a non-stationary Gaussian model, but the algorithm is applicable to any combination of transform and masking functions. Unfortunately the algorithm is not applicable to the DFT since the computational complexity of global transfor- mations is overwhelming. Our results indicate that the proposed approach performs well against lossy compression such as JPEG and other types of filtering which do not change the geometry of the image, however at this time the watermark cannot be recovered from images which have undergone an affine transformation. As a second aspect of the thesis we also develop robust evaluation methods. This consists of two parts. Firstly we develop a new approach for evaluating watermark visibility based on the Watson metric. The results indicate that the perceptual quality as measured by the Watson metric is consistently more accurate than that provided by the typically used PSNR criterion. We also define a new benchmark consisting of attacks which take into account prior information about the watermark and the image. These attacks are much more powerful than the ones available in other bench- marking tools which do not use prior information, but rather perform general image processing operations. Our results relative tothe proposed benchmark indicate that the optimized non-linear embedding approach we developed performs markedly better than existing commercial software which suggests that future research should consist of pursuing these lines rather than the linear additive watermarking paradigm dealt with in the bulk of the literature.}, url = { http://vision.unige.ch/publications/postscript/2000/Pereira_thesis2000.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2000/Pereira_thesis2000.ps.gz}, vgclass = {thesis}, vgproject = {watermarking} } @INPROCEEDINGS{VG:POD1999, author = {Shelby Pereira and Joe J. K. {{\'O}~Ruanaidh} and Fr{\'e}d{\'e}ric Deguillaume and Gabriella Csurka and Thierry Pun}, title = {Template based recovery of Fourier-based watermarks using log-polar and log-log maps}, booktitle = {IEEE Multimedia Systems 99, International Conference on Multimedia Computing and Systems}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, volume = {1}, pages = {870--874}, address = {Florence, Italy}, month = {7--11~June}, abstract = {Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyrighted material. This paper describes a method for the secure and robust copyright protection of digital images. We present an approach for embedding a digital watermark into an image using the fast Fourier transform. To this watermark is added a template in the Fourier transform domain to render the method robust against rotations and scaling, or aspect ratio changes. We detail a new algorithm based on the log-polar or log-log maps for the accurate and efficient recovery of the template in a rotated and scaled image. We also present results which demonstrate the robustness of the method against some common image processing operations such as compression, rotation, scaling and aspect ratio changes.}, url = { http://vision.unige.ch/publications/postscript/99/PereiraORuanaidhDeguillaumeCsurkaPun_icmcs99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/PereiraORuanaidhDeguillaumeCsurkaPun_icmcs99.pdf} } @ARTICLE{VG:PeP2000, author = {Shelby Pereira and Thierry Pun}, title = {An Iterative Template Matching Algorithm Using the Chirp-Z Transform for Digital Image Watermarking}, journal = {Pattern Recognition}, year = {2000}, volume = {33}, pages = {173-175}, vgclass = {refpap}, vgproject = {watermarking}, number = {1}, month = {jan}, abstract = {Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyrighted material. This paper describes a method for the secure and robust copyright protection of digital images. The key contribution lies in the development of a fast iterative template matching algorithm based on log-log or log-polar maps. The algorithm exploits the properties of the Chirp-Z transform to obtain the accuracy needed in the detection of transformations in realistic watermarking applications. Test results verify the robustness of the method.}, url = { http://vision.unige.ch/publications/postscript/2000/PereiraPun_PR2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/PereiraPun_PR2000.pdf} } @INPROCEEDINGS{VG:PeP2000a, author = {Shelby Pereira and Thierry Pun}, title = {A framework for optimal adaptive DCT watermarks}, booktitle = {Tenth European Signal Processing Conference (EUSIPCO'2000)}, year = {2000}, vgclass = {refpap}, vgproject = {watermarking}, address = {Tampere, Finland}, month = {sep 5--8}, abstract = {In this paper we address the problem of robustly embedding 64 bits into an image while taking into account the HVS. The proposed method is general in that any mask can be adopted. The main advantage of the framework we present is that we demonstrate how to optimally embed a watermark given the constraints imposed by the mask in the spatial domain. This is in sharp contrast with the bulk of publications which embed a watermark in the DCT domain and then truncate or modulate in the spatial domain in order to satisfy masking con- straints. The problem with these approaches is that spatial domain truncation or modulation leads inevitably to the degradation of the watermark in the DCT domain. Results indicate that our proposed approach is robust against JPEG compression at a quality factor of 30 images of size 64 by 64.}, url = { http://vision.unige.ch/publications/postscript/2000/PereiraPun_eusipco2000.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2000/PereiraPun_eusipco2000.ps.gz} } @INPROCEEDINGS{VG:PeP1999, author = {Shelby Pereira and Thierry Pun}, title = {Fast robust template matching for affine resistant image watermarking}, booktitle = {International Workshop on Information Hiding}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, volume = {LNCS 1768}, series = {Lecture Notes in Computer Science}, pages = {200--210}, address = {Dresden, Germany}, month = {29~September~--1~October}, publisher = {Springer Verlag}, abstract = {Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyrighted material. This paper describes a method for the secure and robust copyright protection of digital images. We present an approach for embedding a digital watermark into an image using the Fourier transform. To this watermark is added a template in the Fourier transform domain to render the method robust against general linear transformations. We detail a new algorithm for the accurate and efficient recovery of the template in an image which has undergone a general affine transformation. Furthermore we demonstrate how the template can be used as a tool for asserting the presence of a watermark. We also systematically evaluate the algorithm and present results which demonstrate the robustness of the method against some common image processing operations such as compression, rotation, scaling and aspect ratio changes.}, url = { http://vision.unige.ch/publications/postscript/99/PereiraPun_wih99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/PereiraPun_wih99.pdf} } @INPROCEEDINGS{VG:POP1999, author = {Shelby Pereira and Joe J. K. {\'O}~Ruanaidh and Thierry Pun}, title = {Secure robust digital watermarking using the {L}apped {O}rthogonal {T}ransform}, booktitle = {IS\&T/SPIE 11th Annual Symposium, Electronic Imaging '99: Security and Watermarking of Multimedia Contents}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, editor = {Wah Wong, Ping and Edward J. Delp}, volume = {3657}, series = {SPIE Proceedings}, pages = {21--30}, address = {San Jose, California USA}, month = {23--29~January}, note = {Paper EI 3657-03 (Program on Multimedia Processing and Applications)}, abstract = {Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyright material. One approach to Transform Domain image watermarking is to divide the image into separate blocks and compute the transform of each block. The watermark is inserted in the transform domain and the inverse transform is then computed. Such an approach is particularly effective against JPEG compression where 8 x 8 blocks are used in conjunction with the DCT. Using small blocks allows the watermark to be embedded adaptively as a function of the luminance and texture. However for small block sizes blocking artifacts are observed when the strength of the watermark is increased. In order to circumvent this problem, we propose a new approach based on Lapped Orthogonal Transforms (LOT) in which the watermark is inserted adaptively into the LOT domain. Robustness of the watermark to operations such as lossy compression is achieved by using a spread spectrum signal which is added in the LOT domain. The keys used to embed the spread spectrum signal are generated, certified, authenticated and securely distributed using a public key infrastructure containing an electronic copyright office and a certification authority. In addition to the above we propose using an invisible template to reverse the effects of rotation, rescaling and cropping on a watermarked image. This separate invisible template is based on the properties of the Fourier Transform. Finally, we objectively evaluate the performance of the proposed algorithm in order to demonstrate the robustness of the proposed technique with respect to a number of common image processing operations including JPEG compression, rotation, scaling and cropping.}, keywords = {image processing, electronic commerce, pattern recognition}, url = { http://vision.unige.ch/publications/postscript/99/PereiraORuanaidhPun_eiswmc99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/PereiraORuanaidhPun_eiswmc99.pdf} } @INPROCEEDINGS{VG:PVM2001a, author = {Shelby Pereira and Sviatoslav Voloshynovskiy and Maribel Madue{\~n}o and St{\'e}phane Marchand-Maillet and Thierry Pun}, title = {Second generation benchmarking and application oriented evaluation}, booktitle = {Information Hiding Workshop}, year = {2001}, vgclass = {refpap}, vgproject = {watermarking}, address = {Pittsburgh, PA, USA}, month = {apr}, url = { http://vision.unige.ch/publications/postscript/2001/PereiraVoloshynovskiyMaduenoMarchandPun_ihw2001.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2001/PereiraVoloshynovskiyMaduenoMarchandPun_ihw2001.ps.gz} } @INPROCEEDINGS{VG:PVP2000, author = {Shelby Pereira and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Optimized wavelet domain watermark embedding strategy using linear programming}, booktitle = {Wavelet Applications VII (part of SPIE AeroSense 2000)}, year = {2000}, vgclass = {refpap}, vgproject = {watermarking}, editor = {Harold H. Szu and Martin Vetterli}, address = {Orlando, Florida USA}, month = {April 26--28}, abstract = {Invisible Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyright material. In recent years it has been recognized that embedding information in a transform domain leads to more robust watermarks. In particular, several approaches based on the Wavelet Transform have been proposed to address the problem of image watermarking. The advantage of the wavelet transform relative to the DFT or DCT is that it allows for localized watermarking of the image. A major di culty, however, in watermarking in any transform domain lies in the fact that constraints on the allowable distortion at any pixel are speci ed in the spatial domain. In order to insert an invisible watermark, the current trend has been to model the Human Visual System (HVS) and specify a masking function which yields the allowable distortion for any pixel. This complex function combines contrast, luminance, color, texture and edges. The watermark is then inserted in the transform domain and the inverse transform computed. The watermark is nally adjusted to satisfy the constraints on the pixel distortions. However this method is highly suboptimal since it leads to irreversible losses at the embedding stage because the watermark is being adjusted in the spatial domain with no care for the consequences in the transform domain. The central contribution of the paper is the proposal of an approach which takes into account the spatial domain constraints in an optimal fashion. The main idea is to structure the watermark embedding as a linear programming problem in which we wish to maximize the strength of the watermark subject to a set of linear constraints on the pixel distortions as determined by amasking function. We consider the Haar wavelet and Daubechies 4-tap filter in conjunction with a masking function based on a non-stationary Gaussian model, but the algorithm is applicable to any combination of transform and masking functions. Our results indicate that the proposed approach performs well against lossy compression such as JPEG and other types of filtering which do not change the geometry of the image.}, url = { http://vision.unige.ch/publications/postscript/2000/PereiraVoloshynovskiyPun_spie2000.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2000/PereiraVoloshynovskiyPun_spie2000.ps.gz} } @ARTICLE{VG:PVP2001, author = {Shelby Pereira and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Optimal transform domain watermark embedding via linear programming}, journal = {Signal Processing, Special Issue: Information Theoretic Issues in Digital Watermarking}, year = {2001}, vgclass = {refpap}, vgproject = {watermarking}, note = {(to appear)}, abstract = {Invisible Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyright material. In recent years it has been recognized that embedding information in a transform domain leads to mo re robust watermarks. A major difficulty inwatermarking in a transform domain lies in the fact that constraints on the allowable distortion at any pixel may be speci ed in the spatial domain. The central contribution of the paper is the proposal of an approach which takes into account spatial domain constraints in an optimal fashion. The main idea is to structure the watermark embedding as a linear programming problem in which we wish to maximize the strength of the watermark subject to a set of lin- ear constraints on the pixel distortions as determined by a masking function. We consider the special cases of embedding in the DCT domain and wavelet domain using the Haar wavelet and Daubechies 4-tap lter in conjunction with a masking function based on a non-stationary Gaussian model, but the algorithm is applicable to any combination of transform and masking functions. Our results indicate that the proposed approach performs well against lossy compression such as JPEG and other types of ltering which do not change the geometry of the image.}, url = { http://vision.unige.ch/publications/postscript/2001/PereiraVoloshynovskiyPun_sigProc2001.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2001/PereiraVoloshynovskiyPun_sigProc2001.ps.gz} } @INPROCEEDINGS{VG:PVP2000a, author = {Shelby Pereira and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Effective channel coding for DCT watermarks}, booktitle = {IEEE International Conference on Image Processing ICIP 2000}, year = {2000}, vgclass = {refpap}, vgproject = {watermarking}, address = {Vancouver, Canada}, month = {September 10--13}, abstract = {We describe effective channel coding strategies which can be used in conjunction with linear programming optimization techniques for the embedding of robust perceptually adaptive DCT domain watermarks. The main contributions lie in the proposal of a coding strategy based on the magnitude of a DCT coefficient, the use of turbo codes for effec-tive error correction, and finally the incorporation of JPEG quantization tables at embedding.}, url = { http://vision.unige.ch/publications/postscript/2000/PereiraVoloshynovskiyPun_icip2000.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2000/PereiraVoloshynovskiyPun_icip2000.ps.gz} } @MISC{VG:PVP2000b, vgclass = {patent}, vgproject = {watermarking}, author = {Shelby Pereira and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {A method for generating and decoding image dependant watermarks}, howpublished = {European Patent Application PCT/IB00/00494}, month = {Filed April 20}, year = {2000} } @INPROCEEDINGS{PerezFreire:MMSP2004, author = {L. Perez-Freire and F. Perez-Gonzalez and Sviatoslav Voloshynovskiy}, title = {Revealing the true achievable rates of scalar Costa scheme}, booktitle = {IEEE International Workshop on Multimedia Signal Processing (MMSP)}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, address = {Siena, Italy}, month = {September 29 - October 1}, url = {http://vision.unige.ch/publications/postscript/2004/PerezFreirePerezGonzalezVoloshynovskiy_MMSP2004.pdf} } @MISC{VG:Per1988, vgclass = {licence}, vgproject = {unspecified}, author = {Ren{\'e} Perrier}, title = {Labo {I}mage: conception et r\'ealisation d'un logiciel de morphologie math\'ematique \`a niveaux de gris}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {July}, year = {1988} } @MISC{VG:Per1997, vgclass = {diploma}, vgproject = {watermarking}, author = {Adrian Perrig}, title = {A copyright protection environment for digital images}, howpublished = {Diploma thesis, University of Geneva}, month = {March}, year = {1997}, note = {(work conducted in collaboration with: r3 Security Engineering, Switzerland, and the Operating Systems Laboratory, EPF-Lausanne, Switzerland)} } @TECHREPORT{VG:POR1997, author = {Adrian Perrig and Joe {{\'O}~Ruanaidh} and Christian Rauber and Alexander Herrigel and Thierry Pun}, title = {The design of a digital watermarking application}, institution = {Computer Vision Group, Computing Centre, University of Geneva and {R3} Security Engineering}, year = {1997}, vgclass = {report}, vgproject = {watermarking}, number = {97.07}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {January} } @MISC{VG:Pet1997, vgclass = {diploma}, vgproject = {dvp,cbir}, author = {Lori Petrucci}, title = {Interfaces d'archivage et de recherche pour la post-production de documents vid\'eo}, howpublished = {Diploma thesis, University of Geneva}, month = {October}, year = {1997} } @INPROCEEDINGS{VG:PHR2000, author = {Lori Petrucci and Eric Harth and Patrick Roth and Andr{\'e} Assimacopoulos and Thierry Pun}, title = {{WebSound}: a generic {W}eb sonification tool, and its application to an auditory {W}eb browser for blind and visually impaired users}, booktitle = {Proceedings of the Sixth International Conference on Auditory Display (ICAD 2000)}, year = {2000}, vgclass = {refpap}, vgproject = {abweb}, month = {2--5~apr}, abstract = {The inherent visual nature of Internet browsers makes the Web inaccessible to the visually impaired. Although several non-visual browsers have been developed, they usually transform the visual content of HTML documents into textual information only, that can be rendered by a text-to-speech converter or a Braille device. The loss of spatial layout and of textual attributes should be avoided since they often bear visually important information. Moreover, typical non-visual Internet browsers do not allow visually impaired and sighted individuals to easily work together using the same environment. This paper presents WebSound, a new generic Web sonification tool and its application to a 3D audio augmented Internet browser (Internet Explorer 5.0) developed by the Computer Vision Group at the University of Geneva.}, url = { http://vision.unige.ch/publications/postscript/2000/PetrucciHarthRothAssimacopoulosPun_icad2000.pdf} } @INPROCEEDINGS{VG:PHR2000a, author = {Lori Petrucci and Eric Harth and Patrick Roth and Andr{\'e} Assimacopoulos and Thierry Pun}, title = {{WebSound}: a generic {W}eb sonification tool allowing {HCI} researchers to dynamically create new access modalities}, booktitle = {Proceedings of the Conference on Human Factors in Computing Systems (CHI 2000)}, year = {2000}, vgclass = {refpap}, vgproject = {abweb}, month = {1--6~apr}, abstract = {The World Wide Web (WWW) has recently become the main source of digital information accessible everywhere and by everyone. Nevertheless, the inherent visual nature of Internet browsers makes the Web inaccessible to the visually impaired. To solve this problem, non-visual browsers have been developed. One of the new problems, however, with those non-visual browsers is that they often transform the visual content of HTML documents into textual information only, that can be restituted by a text-to-speech converter or a Braille device. The loss of spatial layout, and textual attributes such as boldface, italic, underline, color or even size should be avoided since they often bear visually important information. Moreover, typical non-visual Internet browsers do not allow visually impaired and sighted individuals to easily work together using the same environment. These new problems have to be solved with new alternative non-visual display techniques. This paper presents WebSound, a new generic Web sonification tool and its application to a 3D audio augmented Internet browser (Internet Explorer 5.0) developed at the University of Geneva.}, url = { http://vision.unige.ch/publications/postscript/2000/PetrucciHarthRothAssimacopoulosPun_chi2000.pdf} } @INPROCEEDINGS{VG:PRA1999, author = {Lori Petrucci and Patrick Roth and Andre Assimacopoulos and Thierry Pun}, title = {An audio browser for increasing access to World Wide Web sites for blind and visually impaired computer users}, booktitle = {8th International Conference on Human-Computer Interaction, HCI'99}, year = {1999}, vgclass = {refpap}, vgproject = {abweb}, address = {Munich, Germany}, month = {22--27~August} } @MISC{VG:Pfu2001, vgclass = {licence}, vgproject = {viper}, author = {Thomas Pfund}, title = {Cr\'eation D'une Interface Web Dynamique Pour L'annotation D'images}, howpublished = {Licence thesis (BSc), University of Geneva}, month = {October}, year = {2001}, url = {http://viper.unige.ch/annotate} } @INPROCEEDINGS{VG:PMM2002, author = {Thomas Pfund and St{\'e}phane Marchand-Maillet}, title = {A Dynamic Multimedia Annotation Tool}, booktitle = {Proccedings of {SPIE} Photonics West, Electronic Imaging 2002, Internet Imaging {III}}, year = {2002}, vgclass = {refpap}, vgproject = {viper}, editor = {G. Beretta and R. Schettini Eds}, address = {San Jose, USA} } @INPROCEEDINGS{Pignat:2007:fMRI, author = {J.-M. Pignat and Oleksiy Koval and Sviatoslav Voloshynovskiy and Thierry Pun}, title = {From non-stationary Gaussian modelling to independent component analysis: an fMRI study}, booktitle = {Lemanic-Neuroscience Annual Meeting}, year = {2007}, vgclass = {fullconf}, vgproject = {watermarking}, address = {Les Diablerets, Switzerland}, month = {September 14--15}, owner = {beekhof}, timestamp = {2007.08.29} } @INPROCEEDINGS{Pignat:Brain2005:NGSPMFD, author = {J.-M. Pignat and Sviatoslav Voloshynovskiy and Oleksiy Koval and V. Ibanez and Thierry Pun}, title = {Non-stationary Gaussian spatio-temporal modeling of fMRI data}, booktitle = {Brain'05 {\&} BrainPET'05, XXIInd International Symposium on Cerebral Blood Flow, Metabolism, and Function and VIIth International Conference on Quantification of Brain Function with PET, June 7-11, 2005, Vrije Universiteit Amsterdam, The Netherlands}, year = {2005}, vgclass = {fullconf}, vgproject = {bmi} } @INPROCEEDINGS{Pignat:Diablerets2004:NGSPMFD, author = {J.-M. Pignat and Sviatoslav Voloshynovskiy and Oleksiy Koval and V. Ibanez and Thierry Pun}, title = {Non-stationary Gaussian spatio-temporal modeling of fMRI data}, booktitle = {First Meeting of the Lemanic Neuroscience Programs, UniGe/UNIL Doctoral School in Neuroscience and the EPFL Doctoral Program}, year = {2004}, vgclass = {fullconf}, vgproject = {bmi}, address = {Les Diablerets, Switzerland}, month = {27-28 September} } @MISC{VG:Pin1994, vgclass = {licence}, vgproject = {unspecified}, author = {Nicolas Pinaud}, title = {Traitement d'images bas-niveaux: interfa\c cage entre cam\'era couleur, carte d'acquisition Matrox et logiciel de vision par ordinateur {KBV}ision}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {May}, year = {1994} } @ARTICLE{Pingault2003, author = {M. Pingault and E. Bruno and D. Pellerin}, title = {A Robust Multiscale B-spline Function Decomposition Process to Motion Transparency Estimation}, journal = {IEEE Transactions on Image Processing }, year = {2003}, volume = {12}, pages = {1416- 1426}, number = {11}, month = {November}, owner = {beekhof}, timestamp = {2007.10.09}, url = {http://ieeexplore.ieee.org/xpl/abs_free.jsp?isNumber=27803\&prod=JNL\&arnumber=1240108\&arSt=+1416\&ared=+1426\&arAuthor=+Pingault,+M.;++Bruno,+E.;++Pellerin,+D.\&arNumber=1240108\&a_id0=1240098\&a_id1=1240099\&a_id2=1240100\&a_id3=1240101\&a_id4=1240102\&a_id5=1240103\&a_id6=1240104\&a_id7=1240105\&a_id8=1240106\&a_id9=1240107\&a_id10=1240108\&a_id11=1240109\&count=12} } @MISC{VG:Pin1991, vgclass = {diploma}, vgproject = {unspecified}, author = {Sujiva Pinnagoda}, title = {Vision par ordinateur: {E}tude et d\'etection des propri\'et\'es non-accidentelles}, howpublished = {Diploma thesis, University of Geneva}, month = {December}, year = {1991} } @ARTICLE{VG:PVSHL2001, author = {I. Prudyus and Sviatoslav Voloshynovskiy and A. Synyavskyy and T. Holotyak and L. Lazko}, title = { Generalized radar/radiometry imaging problems }, journal = { Journal of Telecommunications and Information Technology }, year = {2001}, volume = {4}, pages = {15-20}, vgclass = {refpap}, vgproject = {watermarking}, url = {http://vision.unige.ch/publications/postscript/2001/GeneralizedRadarRadiometryImagingProblems.pdf} } @MISC{VG:Pug2001, vgclass = {licence}, vgproject = {watermarking}, author = {Laurent Pugin}, title = {Superposition de Partitions Muicales}, howpublished = {Licence thesis (BSc), University of Geneva}, month = {November}, year = {2001} } @INCOLLECTION{VG:Pun1992, author = {Thierry Pun}, title = {Electromagnetic models for perceptual grouping}, booktitle = {Advances in Machine Vision: Strategies and Applications}, publisher = {World Scientific Publishing Co.}, year = {1992}, editor = {C. Archibald and E. Petriu}, pages = {129--149}, url = { http://vision.unige.ch/publications/postscript/92/Pun_MachVis_EMGrp.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/92/Pun_MachVis_EMGrp.pdf}, vgclass = {refpap}, vgproject = {unspecified} } @INPROCEEDINGS{VG:Pun1995, author = {Thierry Pun}, title = {De la reconnaissance des formes \`a la vision artificielle}, booktitle = {La Relation \`a l'Environnement: des R\'eseaux Informatiques aux R\'eseaux Biologiques}, year = {1995}, vgclass = {fullconf}, vgproject = {unspecified}, pages = {23--24}, address = {Centre d'Ecologie Humaine et des Sciences de l'Environnement, Gen\`eve, Switzerland}, month = {March} } @INPROCEEDINGS{VG:Pun1994, author = {Thierry Pun}, title = {Vision et cybern\'etique}, booktitle = {Symposium de Neuro-ophtalmologie et de R\'eadaptation pour D\'eficients Visuels, Gen\`eve, Switzerland}, year = {1994}, vgclass = {fullconf}, vgproject = {unspecified}, month = {April} } @ARTICLE{VG:Pun1993, author = {Thierry Pun}, title = {2{D} and 3{D} imaging in medicine}, journal = {Physica Medica}, year = {1993}, volume = {9}, pages = {127--134}, vgclass = {refpap}, vgproject = {unspecified}, number = {2} } @ARTICLE{VG:Pun1993a, author = {Thierry Pun}, title = {Robotique agricole: Op\'eration Patate, ``{G}eneva Vision System''}, journal = {Cahiers de la Facult\'e des Sciences, Universit\'e de Gen\`eve}, year = {1993}, vgclass = {otherjournals}, vgproject = {unspecified} } @MISC{Pun92b, vgclass = {refpap}, vgproject = {unspecified}, author = {Thierry Pun}, title = {Robotique agricole: Op\'eration Patate}, howpublished = {{\em Geneva Vision System}, Cahiers de la Facult\'e des Sciences, Universit\'e de Gen\`eve}, year = {1992} } @INPROCEEDINGS{VG:Pun1992a, author = {Thierry Pun}, title = {2{D} and 3{D} graphical methods: applications in medical imaging}, booktitle = {4th International Conference on Applications of Physics in Medicince and Biology - Advanced Detectors for Medical Imaging, Trieste, Italy}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, month = {September} } @ARTICLE{VG:Pun1991, author = {Thierry Pun}, title = {How to keep in touch electronically?}, journal = {{IAPR} Newsletter}, year = {1991}, volume = {14}, vgclass = {otherjournals}, vgproject = {unspecified}, number = {1} } @ARTICLE{VG:Pun1991a, author = {Thierry Pun}, title = {Scientific communications within {SGAICO}}, journal = {SI-Information, Bulletin of the Swiss Association for Computer Science}, year = {1991}, volume = {31}, pages = {7--8}, vgclass = {otherjournals}, vgproject = {unspecified}, month = {May} } @ARTICLE{VG:Pun1991b, author = {Thierry Pun}, title = {Computer interpretation of complex tridimensional scenes, with application to the visual guidance of industrial robots}, journal = {SI-Information, Bulletin of the Swiss Association for Computer Science}, year = {1991}, vgclass = {otherjournals}, vgproject = {unspecified}, note = {(abstract)} } @TECHREPORT{VG:Pun1990, author = {Thierry Pun}, title = {The {G}eneva Vision System: modules, integration and primal access}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1990}, vgclass = {report}, vgproject = {unspecified}, number = {90.06}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {December} } @INPROCEEDINGS{VG:Pun1989, author = {Thierry Pun}, title = {Les m\'ethodes classiques de l'analyse d'images en vision artificielle}, booktitle = {Intelligence Artificielle et Robotique}, year = {1989}, vgclass = {fullconf}, vgproject = {unspecified}, pages = {147--161}, month = {June}, organization = {DIP-Valais and Dalle Molle Foundation} } @INPROCEEDINGS{VG:Pun1989a, author = {Thierry Pun}, title = {Low-level vision: some principles, paradigms and issues}, booktitle = {1st SGAICO Conference, Computer Vision Workshop, Yverdon-Les-Bains, Switzerland}, year = {1989}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October} } @INPROCEEDINGS{VG:Pun1988, author = {Thierry Pun}, title = {Vision artificielle: l'apport des m\'ethodes classiques}, booktitle = {Journ\'ees d'Intelligence artificielle et robotique, Sion, Switzerland}, year = {1988}, vgclass = {fullconf}, vgproject = {unspecified}, month = {November}, organization = {DIP-Valais and Dalle Molle Foundation} } @ARTICLE{VG:Pun1988a, author = {Thierry Pun}, title = {Le Laboratoire Image du Centre universitaire d'informatique ({CUI}): un environnement de stations de travail pour l'enseignement en traitement d'images et infographie}, journal = {Informatique-Informations}, year = {1988}, volume = {2}, pages = {11--12}, vgclass = {otherjournals}, vgproject = {unspecified}, month = {January}, note = {Geneva} } @INPROCEEDINGS{VG:Pun1988b, author = {Thierry Pun}, title = {Current activities in the {AI} and {V}ision group of the {U}niversity of {G}eneva}, booktitle = {{SGAICO} - Swiss Group of {AI} and Cognitive Sciences Annual Conference on Artificial Intelligence in Manufacturing, Assembly, and Robotics, Bern}, year = {1988}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October}, note = {(written in cooperation with the researchers of the group)} } @TECHREPORT{BMI:0501, author = {Thierry Pun and Teodor Iuilian Alecu and Guillaume Chanel and Jullien Kronegg and Sviatoslav Voloshynovskiy}, title = {Brain-computer interaction research at the Computer Vision and Multimedia Laboratory, University of Geneva}, institution = {Computer Vision and Multimedia Laboratory, Computing Centre, University of Geneva}, year = {2005}, vgclass = {report}, vgproject = {bmi}, number = {05.01}, address = {Rue G\'en\'eral Dufour, 24, CH-1211, Geneva, Switzerland} } @INPROCEEDINGS{Pun:BCI:RBCI-CVML, author = {Thierry Pun and Teodor Iulian Alecu and Guillaume Chanel and Julien Kronegg and Sviatoslav Voloshynovskiy}, title = {Research in Brain-computer interaction, Multimodal Interaction Group, Computer Vision and Multimedia Laboratory, University of Geneva}, booktitle = {BCI 2005, Brain-Computer Interface Technology: Third International Meeting}, year = {2005}, vgclass = {refpap}, vgproject = {bmi}, address = {Rensselaerville, NY, USA}, month = {June 14--19} } @TECHREPORT{Pun:TechRep:RBCI-CVML, author = {Thierry Pun and Teodor Iulian Alecu and Guillaume Chanel and Julien Kronegg and Sviatoslav Voloshynovskiy}, title = {Research in Brain-computer interaction, Multimodal Interaction Group, Computer Vision and Multimedia Laboratory, University of Geneva}, institution = {Technical report TR0501, Computer Science Department, University of Geneva}, year = {2005}, vgclass = {report}, vgproject = {bmi}, number = {05.01}, month = {June} } @ARTICLE{Pun:NSRE:BCI-CVML, author = {Thierry Pun and Teodor Iulian Alecu and Guillaume Chanel and Sviatoslav Voloshynovskiy}, title = {Brain-computer interaction research at the Computer Vision and Multimedia Laboratory, University of Geneva}, journal = {IEEE transactions on neural systems and rehabilitation engineering, Special Issue on Brain-Computer Interaction}, year = {2006}, volume = {14}, vgclass = {refpap}, vgproject = {bmi}, number = {2}, month = {June} } @INPROCEEDINGS{PuA98, author = {Thierry Pun and Andr{\'e} Assimacopoulos}, title = {{ABW}eb: Active audio Internet browser for visually impaired and blind users}, booktitle = {Proceedings of the Conference of the Swiss Priority Programme on Information and Communication Structures (SPP ICS)}, year = {1998}, vgclass = {fullconf}, vgproject = {abweb}, address = {Irchel Campus, Z\"urich University, Z\"urich}, month = {13~July} } @INPROCEEDINGS{VG:PAP2000, author = {Thierry Pun and Andr{\'e} Assimacopoulos and Lori Petrucci and Patrick Roth}, title = {{ABW}eb: Active audio Internet browser for visually impaired and blind users}, booktitle = {SPP-ICS Closing Conference, Swiss Priority Program on Information and Communication Structures}, year = {2000}, vgclass = {fullconf}, vgproject = {abweb}, pages = {97-99}, address = {Fribourg, Switzerland}, month = {mar 15} } @ARTICLE{VG:PAP1999, author = {Thierry Pun and Andr{\'e} Assimacopoulos and Lori Petrucci and Patrick Roth}, title = {{AB-Web}: {A}ctive audio Internet browser for visually impaired and blind users}, journal = {Informatik - Informatique, Swiss Informaticians Society}, year = {1999}, pages = {45--46}, vgclass = {otherjournals}, vgproject = {abweb}, number = {5}, month = {October}, abstract = {In the Internet world, the widespread use of graphical user interfaces (GUIs) increasingly bars visually handicapped people from accessing digital information. In this context our project aims at providing sight handicapped people with alternative access modalities to various types of GUIs and graphic intensive programs, in order for instance to facilitate usage of Web services.}, url = { http://vision.unige.ch/publications/postscript/99/PunAssimacopoulosPetrucciRoth_informatik.pdf}, url1 = { http://vision.unige.ch/publications/postscript/99/PunAssimacopoulosPetrucciRoth_informatik.ps.gz} } @MISC{VG:PuB1993, vgclass = {otherjournals}, vgproject = {unspecified}, author = {Thierry Pun and C. Baur}, title = {Interpr\'etation par ordinateur de sc\`enes tridimensionnelles complexes, avec application au guidage visuel de robots industriels}, howpublished = {Press release}, month = {October}, year = {1993} } @ARTICLE{VG:PuB1990, author = {Thierry Pun and E. Blake}, title = {Relationships between image synthesis and analysis: towards unification?}, journal = {Computer Graphics Forum}, year = {1990}, volume = {9}, pages = {149--163}, vgclass = {refpap}, vgproject = {unspecified}, number = {2}, month = {July}, url = { http://vision.unige.ch/publications/postscript/90/PunBl_CGF_Common.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/90/PunBl_CGF_Common.pdf} } @INPROCEEDINGS{VG:PBM1994, author = {Thierry Pun and Jean-Marc Bost and Ruggero Milanese and Christian Rauber and Serguei Startchik}, title = {Selecting relevant information and delaying irrelevant data for objects recognition}, booktitle = {AAAI Fall Symposium Series, Relevance Workshop, New Orleans, Louisiana}, year = {1994}, vgclass = {refpap}, vgproject = {unspecified}, pages = {168--172}, month = {November}, publisher = {AAAI Press}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/rauber/94.11.AAAIpaper.ps.Z} } @TECHREPORT{VG:PBM1994a, author = {Thierry Pun and Jean-Marc Bost and Ruggero Milanese and Christian Rauber and Serguei Startchik}, title = {Selecting relevant information and delaying irrelevant data for objects recognition}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {94.03}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {March}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/rauber/94.03.Report.ps.Z} } @INPROCEEDINGS{VG:PuB1989, author = {Thierry Pun and Pierre-Yves Burgi}, title = {Perceptual grouping of image primitives using a potential and field approach}, booktitle = {6th Scandinavian Conference on Image Analysis, Oulu, Finland}, year = {1989}, vgclass = {refpap}, vgproject = {unspecified}, pages = {317--324}, month = {June}, key = {SCIA'89} } @INPROCEEDINGS{VG:PuD1992, author = {Thierry Pun and J.-D. Dessimoz}, title = {Computer interpretation of complex tridimensional scenes, with application to the visual guidance of industrial robots}, booktitle = {National Research Program NFP/PNR 23, Third Program Status Report, Bern, Switzerland}, year = {1992}, vgclass = {fullconf}, vgproject = {unspecified}, month = {July} } @INPROCEEDINGS{VG:PuD1991, author = {Thierry Pun and J.-D. Dessimoz}, title = {Computer interpretation of complex tridimensional scenes, with application to the visual guidance of industrial robots}, booktitle = {National Research Program NFP/PNR 23, Second Program Status Report, Bern, Switzerland}, year = {1991}, vgclass = {fullconf}, vgproject = {unspecified}, month = {July} } @INPROCEEDINGS{VG:PuD1990, author = {Thierry Pun and J.-D. Dessimoz}, title = {Computer interpretation of complex tridimensional scenes, with application to the visual guidance of industrial robots}, booktitle = {National Research Program NFP/PNR 23, First Program Status Report, Bern, Switzerland}, year = {1990}, vgclass = {fullconf}, vgproject = {unspecified}, month = {June} } @INCOLLECTION{VG:PuG1995, author = {Thierry Pun and Catherine De Garrini}, title = {Cybern\'etique et vision par ordinateur}, booktitle = {Le D\'eficit Visuel, de la Neurophysiologie \`a la Pratique de la R\'eadaptation}, publisher = {Masson}, year = {1995}, editor = {A. B. Safran and Andr{\'e} Assimacopoulos}, pages = {213--224}, address = {Paris, France}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/degarrin/95.05.ophtalmo.ps.Z}, vgclass = {refpap}, vgproject = {unspecified} } @ARTICLE{VG:PGR1994, author = {Thierry Pun and G. Gerig and O. S. Ratib}, title = {Image analysis and computer vision in medicine}, journal = {Computerized Medical Imaging and Graphics}, year = {1994}, volume = {18}, pages = {85--96}, vgclass = {refpap}, vgproject = {unspecified}, number = {2}, note = {(Special Issue: Multimedia Techniques in the Medical Environment)}, url = { http://vision.unige.ch/publications/postscript/94/PunGR_CMIG_CVMedic.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/94/PunGR_CMIG_CVMedic.pdf} } @INPROCEEDINGS{VG:PGL1993, author = {Thierry Pun and Sylvia Gil and Marc Lefebvre and Ruggero Milanese and C. Baur and M.-A. Glassey and E. Natonek and C. Burckhardt and J.-D. Dessimoz}, title = {Computer interpretation of complex tridimensional scenes, with application to the visual guidance of industrial robots}, booktitle = {Proceedings Symposium on Artificial Intelligence and Robotics, Z\"urich, Switzerland}, year = {1993}, vgclass = {fullconf}, vgproject = {unspecified}, editor = {R. Bless}, series = {National Research Program NFP/PNR 23}, pages = {85--99}, month = {October} } @INPROCEEDINGS{PuH98, author = {Thierry Pun and Alexander Herrigel}, title = {Krypict: a software environment for copyrighting, authenticating, archiving and retrieving pictorial documents in multimedia databases}, booktitle = {Proceedings of the Conference of the Swiss Priority Programme on Information and Communication Structures (SPP ICS)}, year = {1998}, vgclass = {fullconf}, vgproject = {watermarking}, address = {Irchel Campus, Z\"urich University, Z\"urich}, month = {13~July} } @INPROCEEDINGS{VG:PHT2000, author = {Thierry Pun and Alexander Herrigel and P. Tschudin}, title = {Krypict: a software environment for copyrighting, authenticating, archiving and retrieving pictorial documents in multimedia databases}, booktitle = {SPP-ICS Closing Conference, Swiss Priority Program on Information and Communication Structures}, year = {2000}, vgclass = {fullconf}, vgproject = {watermarking}, pages = {82-85}, address = {Fribourg, Switzerland}, month = {mar 15} } @ARTICLE{VG:PHT1999, author = {Thierry Pun and Alexander Herrigel and Peter Tschudin}, title = {{K}ry{P}ict: a software environment for copyrighting, authenticating, archiving and retrieving pictorial documents in multimedia databases}, journal = {Informatik - Informatique, Swiss Informaticians Society}, year = {1999}, pages = {26--27}, vgclass = {otherjournals}, vgproject = {watermarking}, number = {2}, month = {April} } @ARTICLE{VG:PHA1988, author = {Thierry Pun and D. Hochstrasser and R. Appel and M. Funk and V. Villars-Augsburger and C. Pellegrini}, title = {Computerized classification of two-dimensional gel electrophoretograms by correspondence analysis and ascendant hierarchical clustering}, journal = {Applied and Theoretical Electrophoresis}, year = {1988}, volume = {1}, pages = {3--9}, vgclass = {refpap}, vgproject = {unspecified}, number = {1} } @INPROCEEDINGS{VG:PHP1988, author = {Thierry Pun and D. Hochstrasser and Christian Pellegrini}, title = {Correspondance analysis and hierarchical classification of complex images: application to two-dimensional gel electrophoretograms}, booktitle = {{EUSIPCO} 88, 4th European Signal Processing Conference, Grenoble, France}, year = {1988}, vgclass = {refpap}, vgproject = {unspecified}, month = {September}, note = {(also in Signal Processing IV, theories and applications, J. L. Lacoume, A. Chehikian, N. Martin and J. Malbos, Eds., North-Holland, 1988.)} } @INPROCEEDINGS{VG:PLG1991, author = {Thierry Pun and Marc Lefebvre and Sylvia Gil and Denis Brunet and Jean-Daniel Dessimoz and Paul Gugerli}, title = {The {P}otato {O}peration: computer vision for agricultural robotics}, booktitle = {Machine Vision Architectures, Integration and Applications}, year = {1991}, vgclass = {refpap}, vgproject = {unspecified}, editor = {Bruce G. Batchelor and Michael J. Chen and Frederick M. Waltz}, volume = {1615}, series = {SPIE Proceedings}, pages = {320--331}, address = {Boston, USA}, month = {November}, note = {(SPIE Conference on Advances in Intelligent Robotic Systems)}, abstract = {Each year at harvest time millions of seed potatoes are checked for the presence of viruses by means of an Elisa test. The Potato Operation aims at automatizing the potato manipulation and pulp sampling procedure, starting from bunches of harvested potatoes and ending with the deposit of potato pulp into Elisa containers. Automatizing these manipulations addresses several issues, linking robotic and computer vision. The paper reports on the current status of this project. It first summarizes the robotic aspects, which consist of locating a potato in a bunch, grasping it, positioning it into the camera field of view, pumping the pulp sample and depositing it into a container. The computer vision aspects are then detailed. They concern locating particular potatoes in a bunch and finding the position of the best germ where the drill has to sample the pulp. The emphasis is put on the germ location problem. A general overview of the approach is given, which combines the processing of both frontal and silhouette views of the potato, together with movements of the robot arm (active vision). Frontal and silhouette analysis algorithms are then presented. Results are shown that confirm the feasibility of the approach.}, url = { http://vision.unige.ch/publications/postscript/91/PunLGBDG_SPIE_Pdt.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/91/PunLGBDG_SPIE_Pdt.pdf} } @INPROCEEDINGS{VG:PuM1995, author = {Thierry Pun and Ruggero Milanese}, title = {Computer vision and multimedia information systems}, booktitle = {Proceedings of the International Workshop on Multimedia Information Systems and Hypermedia}, year = {1995}, vgclass = {refpap}, vgproject = {unspecified}, editor = {M. Sakauchi and R. Jain}, pages = {29--37}, address = {Tokyo, Japan}, month = {March}, note = {(invited paper)}, url = {http://vision.unige.ch/publications/postscript/95/PunMil_CVMis.ps.gz}, url1 = {http://vision.unige.ch/publications/postscript/95/PunMil_CVMis.pdf} } @INPROCEEDINGS{VG:PRS1994, author = {Thierry Pun and Christian Rauber and Serguei Startchik}, title = {Unified knowledge representation and asynchronous processing for a versatile computer vision system}, booktitle = {Proceedings of the Swiss Priority Programme Informatics, Information Conf. Module, Yverdon-les-Bains, Switzerland}, year = {1994}, vgclass = {fullconf}, vgproject = {unspecified}, pages = {26--35}, month = {December}, publisher = {Swiss National Science Foundation Press}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/rauber/94.12.Yverdon.ps.Z} } @INPROCEEDINGS{VG:PRS1996, author = {Thierry Pun and Christian Rauber and Serguei Startchik and Ruggero Milanese}, title = {Unified knowledge representation and asynchronous processing for a versatile computer vision system}, booktitle = {Proceedings Closing Conference Swiss Priority Programme Informatics, Lausanne, Switzerland}, year = {1996}, vgclass = {fullconf}, vgproject = {unspecified}, pages = {23--25}, month = {March}, publisher = {Swiss National Science Foundation Press} } @INPROCEEDINGS{VG:PRS1995, author = {Thierry Pun and Christian Rauber and Serguei Startchik and Ruggero Milanese}, title = {Transforming an image into dataflows of relevant primitives for objects location, reconstruction and indexing}, booktitle = {Proceedings of Vision Interface 95}, year = {1995}, vgclass = {refpap}, vgproject = {unspecified}, pages = {203--211}, address = {Quebec City, Canada}, month = {May}, organization = {Canadian Image Processing and Pattern Recognition Society}, note = {(presented by Ch. Rauber)}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/rauber/95.05.VI.ps.Z} } @INPROCEEDINGS{VG:PRN1991, author = {Thierry Pun and M. Regamey and Philippe Narbel and J. Mosig}, title = {Perceptual grouping and directionality determination using an electromagnetic model}, booktitle = {Proceedings Vision Interface'91, Calgary, Canada}, year = {1991}, vgclass = {refpap}, vgproject = {unspecified}, pages = {81--88}, month = {June} } @TECHREPORT{VG:PRN1990, author = {Thierry Pun and M. Regamey and Philippe Narbel and J. Mosig}, title = {Perceptual grouping and directionality determination using an electromagnetic model}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1990}, vgclass = {report}, vgproject = {unspecified}, number = {90.02}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April} } @INPROCEEDINGS{VG:PRP1998, author = {Thierry Pun and Patrick Roth and Lori Petrucci}, title = {An image-capable audio internet browser for facilitating blind user access to digital libraries}, booktitle = {Digital Libraries '98 - The Third {ACM} Conference on Digital Libraries}, year = {1998}, vgclass = {refpap}, vgproject = {abweb}, address = {Pittsburgh, PA, USA}, month = {June}, abstract = {The Internet now permits widespread access to textual and pictorial material from digital libraries. The widespread use of graphical user interfaces, however, increasingly bars visually handicapped people from using such material. We present here our current work aimed at the adaptation of an Internet browser to facilitate blind user access to digital libraries. The main distinguishing characteristics of this browser are: (1) active user interaction, both for the macro-analysis and micro-analysis of screen objects of interest; (2) use of a touch-sensitive screen to facilitate user interaction; (3) generation of a virtual sound space into which the screen information is mapped; (4) transcription into sounds not only of text, but also of images. Several prototypes have been implemented, and are being evaluated by blind users.} } @ARTICLE{VG:PuS1996, author = {Thierry Pun and David McG. Squire}, title = {Statistical structuring of pictorial databases for content-based image retrieval systems}, journal = {Pattern Recognition Letters}, year = {1996}, volume = {17}, pages = {1299--1310}, vgclass = {refpap}, vgproject = {viper}, abstract = {This letter presents a two-stage statistical approach for ``exploring and explaining'' a pictorial database, for content-based image retrieval systems. First, we describe how correspondence analysis provides images classes, as well as facilitates the understanding of the role of image primatives and attributes used to index pictures. Such understanding allows an intelligent choice of features, and thus computational savings, to be made. Second, ascendant heirarchical classification permits the structuring of the database, in order to ease picture indexing and retrieval.}, keywords = {image databases, content-based image retrieval systems, exploratory statistics, correspondence analysis, ascendant hierarchical classification}, url = { http://vision.unige.ch/publications/postscript/96/PuS96_prl_corran.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/96/PuS96_prl_corran.pdf} } @ARTICLE{PerezFreire:AA:IFS2006, author = {Luis P{\'e}rez-Freire and Fernando P{\'e}rez-Gonz{\'a}lez and Sviatoslav Voloshynovskiy}, title = {An Accurate Analysis of Scalar Quantization-Based Data Hiding}, journal = {IEEE Transactions on Information Forensics and Security}, year = {2006}, volume = {1}, pages = {80--86}, vgclass = {refpap}, vgproject = {watermarking}, number = {1}, month = {March}, booktitle = {IEEE Transactions on Information Forensics and Security}, url = {http://vision.unige.ch/publications/postscript/2005/PerezFreirePerezGonzalezVoloshynovskiy_IFS2006.pdf} } @MISC{VG:Que1989, vgclass = {diploma}, vgproject = {unspecified}, author = {Denis Queille}, title = {Un syst\`eme d'acquisition d'images astronomiques par {CCD}}, howpublished = {Diploma thesis, University of Geneva}, month = {April}, year = {1989} } @MISC{VG:Rai1989, vgclass = {licence}, vgproject = {unspecified}, author = {Pascale Raisin}, title = {D\'eveloppement d'un outil d'analyse de gels \'electrophor\'etiques \`a une dimension}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {September}, year = {1989} } @MISC{VG:Rak1999, vgclass = {diploma}, vgproject = {viper}, author = {Jilali Raki}, title = {Utilisation d'un protocole de communication et d'une structure de fichier invers\'e pour la recherche dans une base de donn\'ees d'images}, howpublished = {Diploma thesis, University of Geneva}, month = {April}, year = {1999}, abstract = {Ce document d\'ecrit le proc\'ed\'e et la mani\`ere utilis\'es pour archiver des images dans une base de donn\'ees et rechercher celles qui sont les plus similaires \`a une requ\^ete d'images. La technique d'archivage des images est inspir\'ee de celle utilis\'ee pour archiver et rechercher du texte. Les points essentiels des chapitres trait\'es dans le manuel sont: \begin{itemize} \item Un survol du syst\`eme Viper, qui est le nom de bapt\^eme donn\'e au syst\`eme de recherche d'images \`a r\'ealiser. Dans ce chapitre, la description des caract\'eristiques de couleur et de texture utilis\'ees dans le syst\`eme et la mani\`ere de calculer la similarit\'e entre une image d'une requ\^ete et les images de la base donn\'ees sont abord\'ees. \item La sp\'ecification d'un protocole de communication pour l'\'echange de messages entre la base de donn\'ees et une interface utilisateur graphique. Diff\'erents types de messages sont d\'ecrits et la grammaire du protocole de communication est sp\'ecifi\'ee. \item L'introduction de la grammaire avec les outils de compilation JavaCup et JLex pour le langage Java et avec les outils Yacc et Lex pour le langage C++. La mani\`ere de g\'en\'erer les analyseurs syntaxiques et lexicaux correspondants \`a la grammaire avec ces outils est d\'ecrite. Du fait que JavaCup et Jlex sont moins connus que Lex et Yacc, une explication plus d\'etaill\'ee de ces outils est donn\'ee dans ce chapitre. \item La mani\`ere de construire l'interface graphique de l'utilisateur et une description de ses diff\'erentes fonctionnalit\'es. On explique dans ce chapitre la mani\`ere d'implanter l'interface afin de communiquer avec un serveur li\'e \`a la base de donn\'ees et d'analyser les messages du protocole de communication. \item L'archivage des images dans une structure de donn\'ees appel\'ee "Inverted File" ou fichier invers\'e. Cette structure est d\'ecrite dans ce chapitre ainsi que la mani\`ere d'implanter le serveur de la base de donn\'ees afin de communiquer avec l'interface et d'analyser les messages du protocole de communication. \end{itemize} Apr\`es ces chapitres, des r\'esultats de requ\^etes de recherche d'images similaires sont pr\'esent\'es afin de les comparer aux r\'esultats d'autres syst\`emes.}, url = {http://vision.unige.ch/publications/postscript/99/Raki_diploma.ps.gz}, url1 = {http://vision.unige.ch/publications/postscript/99/Raki_diploma.pdf} } @MISC{VG:Rak1997, vgclass = {licence}, vgproject = {cbir}, author = {J. Raki}, title = {Parall\'elisation de la recherche d'images de filigranes}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {February}, year = {1997} } @PHDTHESIS{VG:Rau1998, author = {Christian Rauber}, title = {Acquisition, archivage et recherche de documents accessibles par le contenu: application \`a la gestion d'une base de donn\'ees d'images de filigranes}, school = {University of Geneva}, year = {1998}, type = {{P}h.{D}. {D}issertation {N}o. 2988}, address = {Switzerland}, month = {March}, url = {http://cui.unige.ch/~rauber/these/index.htm}, vgclass = {thesis}, vgproject = {cbir} } @MISC{VG:Rau1990, vgclass = {diploma}, vgproject = {unspecified}, author = {Christian Rauber}, title = {La transform\'ee de {G}abor et ses applications}, howpublished = {Diploma thesis, University of Geneva}, month = {April}, year = {1990} } @INPROCEEDINGS{VG:ROP1997, author = {Christian Rauber and Joe J. K. {{\'O}~Ruanaidh} and Thierry Pun}, title = {Secure distribution of watermarked images for a digital library of ancient papers}, booktitle = {Second ACM Conference on Digital Libraries}, year = {1997}, vgclass = {refpap}, vgproject = {watermarking,cbir}, pages = {123--130}, address = {Philadelphia, PA}, month = {July}, abstract = {The electronic publishing, storage and distribution of documents is growing increasingly important and will have profound implications for our economy, culture and society. The multimedia digitalisation of libraries and the distribution of the contents of museums is revolutionising these organisations and will make these resources available to a much wider audience than was previously possible. The main goal of our MEDIA project (Mobile Electronic Documents with Interacting Agents) is the development of a system for the archival, retrieval, and distribution of electronic documents. For this purpose, a mobile agent platform is used to securely distribute these documents. Information is accessed by a search mechanism that allows the retrieval of text and images according to their content. An important feature of the system is a digital watermarking tool which embeds hidden signatures in images. This provides copyright protection and helps to ensure that the image will not be copied and sold and without proper authorisation. The management of the database of documents and images is accomplished by an extensible object relational database management system. In addition, documents and data can be accessed through the World Wide Web network.} } @INPROCEEDINGS{VG:RGM1995, author = {Christian Rauber and Catherine De Garrini and Ruggero Milanese and Serguei Startchik and Thierry Pun}, title = {Saillance, zone d'int\'er\^et, mise en correspondance: trois techniques pour la localisation et la reconnaissance d'objets en couleur sur fond fortement textur\'e}, booktitle = {Fifteenth GRETSI Symposium on Signal and Image Processing}, year = {1995}, vgclass = {refpap}, vgproject = {unspecified}, pages = {709--712}, address = {Juan les Pins}, month = {September} } @TECHREPORT{VG:RMS1994, author = {Christian Rauber and Ruggero Milanese and Serguei Startchik and Thierry Pun}, title = {Data selection mechanisms for object recognition}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {94.06}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/rauber/94.06.Report.ps.Z} } @INPROCEEDINGS{VG:RPT1997, author = {Christian Rauber and Thierry Pun and Peter Tschudin}, title = {Retrieval of images from a library of watermarks for ancient paper identification}, booktitle = {Proceedings of EVA 97, Elektronische Bildverarbeitung und Kunst, Kultur, Historie, Berlin, Germany}, year = {1997}, vgclass = {refpap}, vgproject = {watermarking,cbir}, month = {November}, publisher = {GFaI, Gesellschaft zur Foerderung angewandter Informatik e.V.} } @ARTICLE{VG:RTP1997, author = {Christian Rauber and Peter Tschudin and Thierry Pun}, title = {Syst\`eme d'archivage et de recherche de filigranes}, journal = {Gazette du Livre M\'edieval}, year = {1997}, volume = {31}, pages = {31--40}, vgclass = {refpap}, vgproject = {cbir} } @INCOLLECTION{VG:RTS1996b, author = {Christian Rauber and Peter Tschudin and Serguei Startchik and Thierry Pun}, title = {Archival and retrieval for large image databases: application to an historical watermarks archive}, booktitle = {Objects Applications}, publisher = {University of Geneva}, year = {1996}, editor = {D. Tsichritzis}, pages = {19--26}, vgclass = {report}, vgproject = {cbir} } @INPROCEEDINGS{VG:RTS1996, author = {Christian Rauber and Peter Tschudin and Serguei Startchik and Thierry Pun}, title = {Archivage et recherche d'images de filigranes}, booktitle = {CNED'96, 4\`eme Coll. National sur l'Ecrit et le Document}, year = {1996}, vgclass = {refpap}, vgproject = {cbir}, pages = {69--76}, address = {Nantes, France}, month = {July} } @INPROCEEDINGS{VG:RTS1996a, author = {Christian Rauber and Peter Tschudin and Serguei Startchik and Thierry Pun}, title = {Archival and retrieval of historical watermark images}, booktitle = {ICIP'96, IEEE International Conference on Image Processing}, year = {1996}, vgclass = {refpap}, vgproject = {watermarking,cbir}, volume = {2}, pages = {773--776}, address = {Lausanne, Switzerland}, month = {September}, note = {Special Session ``Images in Digital Libraries''} } @MISC{VG:Reg1990, vgclass = {diploma}, vgproject = {unspecified}, author = {Michel Regamey}, title = {Utilisation de mod\`eles \'electromagn\'etiques pour l'\'etude de la vision bas-niveau}, howpublished = {Diploma thesis, University of Geneva}, month = {April}, year = {1990} } @ARTICLE{VG:RPH1989, author = {C. Roch and Thierry Pun and D. F. Hochstrasser and Christian Pellegrini}, title = {Automatic learning strategies}, journal = {Computerized Medical Imaging and Graphics}, year = {1989}, volume = {13}, pages = {383--391}, vgclass = {refpap}, vgproject = {unspecified}, number = {5} } @PHDTHESIS{VG:Roth2002, author = {Patrick Roth}, title = {Repr{\'e}sentation multimodale d'images digitales dans des syst{\'e}mes informatiques multim{\'e}dias pour utilisateurs non-voyants}, school = {Computer Vision and Multimedia Laboratory, University of Geneva}, year = {2002}, address = {Geneva, Switzerland}, month = {September}, vgproject = {viper} } @MISC{VG:Rot1997, vgclass = {diploma}, vgproject = {abweb}, author = {Patrick Roth}, title = {Interface {W}eb pour non-voyants}, howpublished = {Diploma thesis, University of Geneva}, month = {September}, year = {1997} } @INPROCEEDINGS{VG:RGP2001, author = {Patrick Roth and Christoph Giess and Lori Petrucci and Thierry Pun}, title = {Adapting Haptic Game Devices for non-visual Graph Rendering}, booktitle = {HCI 2001, International Symposium on Signal Processing and its Applications}, year = {2001}, vgclass = {refpap}, vgproject = {abweb}, address = {New Orleans, LA, USA}, month = {August 5-10} } @ARTICLE{Roth:JVIB2002:CTNMPSG, author = {Patrick Roth and Hesham Kamel and Lori Petrucci and Thierry Pun}, title = {A comparison of three nonvisual methods for presenting scientific graphs}, journal = {Journal of Visual Impairment and Blindness}, year = {2002}, volume = {96}, pages = {420--428}, vgclass = {refpap}, vgproject = {abweb}, number = {6}, month = {June} } @INPROCEEDINGS{Roth:HCI2003:RDIABCU, author = {Patrick Roth and Julien Kronegg and Thierry Pun}, title = {Rendering digital images accessible for blind computer users}, booktitle = {HCI International 2003, 10th International Conference on Human-Computer Interaction}, year = {2003}, vgclass = {refpap}, vgproject = {abweb}, address = {Crete, Greece}, month = {June 22-27} } @INPROCEEDINGS{VG:RPA2000a, author = {Patrick Roth and Lori Petrucci and Andr{\'e} Assimacopoulos and Thierry Pun}, title = {Audio-Haptic Internet Browser and Associated Tools for Blind Users and Visually Impaired Computer Users}, booktitle = {COST 254 Intelligent Terminals, Workshop on Friendly Exchanging Through the Net}, year = {2000}, vgclass = {refpap}, vgproject = {abweb}, editor = {C. Germain and O. Lavialle and E. Grivel}, pages = {57-62.}, address = {Bordeaux, France}, month = {mar 22-24}, abstract = {In the Internet world, the widespread use of graphical user interfaces (GUIs) increasingly bars visually handicapped people from accessing digital information. In this context our project aims at providing sight handicapped people with alternative access modalities to various types of GUIs and graphic intensive programs, in order for instance to facilitate usage of Web services. We describe in this paper AB-Web, a 3D-audio Web browser that allows blind computer users to explore Web pages, fill in forms, etc., using a 3D sonic rendering. We also present WebSound, a generic tool that permits to associate with each HTML tag a given sonic object (earcon or auditory icon). Finally, we describe a series of associated programs composed of the family of sonic games From Dots to Shapes, as well as of IDEA, a tool that lets users comprehend simple drawings, as well as to create graphics.}, url = { http://vision.unige.ch/publications/postscript/2000/RothPetrucciAssimacopoulosPun_cost2000.pdf} } @INPROCEEDINGS{VG:RPA2000, author = {Patrick Roth and Lori Petrucci and Andre Assimacopoulos and Thierry Pun}, title = {Concentration game: an audio adaptation for blind people}, booktitle = {CSUN's 15th Annual International Conference ``Technology and Persons with Disabilities''}, year = {2000}, vgclass = {refpap}, vgproject = {abweb}, address = {Los Angeles, CA, USA}, month = {20--25~mar}, url1 = {http://www.csun.edu/cod/conf2000/proceedings/0011Roth.html} } @INPROCEEDINGS{VG:RPA2000b, author = {Patrick Roth and Lori Petrucci and Andr{\'e} Assimacopoulos and Thierry Pun}, title = {From Dots to Shapes: an auditory haptic game platform for teaching geometry to blind pupils}, booktitle = {ICCHP 2000, International Conference on Computers Helping people with special Needs}, year = {2000}, vgclass = {refpap}, vgproject = {abweb}, pages = {603--610}, address = {Karlsruhe, Germany}, month = {jul 17-21}, abstract = {This paper describes "From Dots to Shapes" (FDTS), an auditory platform composed by three classic games ( Simon , Point Connecting and concentration game ) for blind and visually impaired pupils. Each game was adapted to work on a concept of the Euclidean geometry (e.g. ) The tool, , is based on sonic and haptic interaction, and therefore could be used by special educators as a help for teaching basic planar geometry.}, url = { http://vision.unige.ch/publications/postscript/2000/RothPetrucciAssimacopoulosPun_ICCHP2000.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2000/RothPetrucciAssimacopoulosPun_ICCHP2000.ps.gz} } @INPROCEEDINGS{VG:RPA1999, author = {Patrick Roth and Lori Petrucci and Andre Assimacopoulos and Thierry Pun}, title = {Auditory browser for blind and visually impaired users}, booktitle = {ACM SIGCHI Computer Human Interaction 99, Conference on Human Factors in Computing Systems}, year = {1999}, vgclass = {refpap}, vgproject = {abweb}, pages = {218--219}, address = {Pittsburgh, PA, USA}, month = {15--20~May}, abstract = {This paper presents our work on the development of a multimodal auditory interface which permits blind users to work more easily and efficiently with GUI browsers. A macro-analysis phase, which can be either passive or active, informs on the global layout of HTML documents. A subsequent active micro-analysis phase allows to explore particular elements of the document. The interface is based on: ( 1) a mapping of the graphical HTML document into a 3D virtual sound space environment, where non-speech auditory cues differentiate HTML elements; (2) the transcription into sound not only of text, but also of images; (3) the use of a touch-sensitive screen to facilitate user interaction. Moreover, in order to validate the sonification model of the images, we have created an audio "memory game", that can be used as a pedagogical tool to help blind pupils learn spatial exploration cues.}, url = { http://vision.unige.ch/publications/postscript/99/RothPetrucciAssimacopoulosPun_chi99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/RothPetrucciAssimacopoulosPun_chi99.pdf} } @INPROCEEDINGS{VG:RPA1997, author = {Patrick Roth and Lori Petrucci and Andr{\'e} Assimacopoulos and Thierry Pun}, title = {Techniques interactives et passives de restitution d'information graphique pour les non-voyants}, booktitle = {S\'eminaire Technique et Cognition: Finitude, Situation et Inscription Corporelle}, year = {1998}, vgclass = {fullconf}, vgproject = {abweb}, address = {Universit\'e de Technologie de Compi\`egne, France}, month = {January} } @INPROCEEDINGS{VG:RPA1998, author = {Patrick Roth and Lori Petrucci and Andr{\'e} Assimacopoulos and Thierry Pun}, title = {{AB-Web}: {A}ctive audio browser for visually impaired and blind users}, booktitle = {International Conference on Auditory Display (ICAD'98)}, year = {1998}, vgclass = {refpap}, vgproject = {abweb}, address = {Glasgow, UK}, month = {November}, abstract = {The Internet now permits easy access to textual and pictorial material from an exponentially growing number of sources. The widespread use of graphical user interfaces, however, increasingly bars visually handicapped people from using such material. In this context, our project aims at providing sight handicapped people with alternative access modalities to pictorial documents. More precisely, our goal is to develop an augmented Internet browser to facilitate blind users access to the World Wide Web. The main distinguishing characteristics of this browser are : (1) generation of a virtual sound space into which the screen information is mapped; (2) transcription into sounds not only of text, but also of images; (3) active user interaction, both for the macro-analysis and micro-analysis of screen objects of interest; (4) use of a touch-sensitive screen to facilitate user interaction. Several prototypes have been implemented, and are being evaluated by blind users.}, keywords = {WWW, blind user access, sound space, image analysis}, url = { http://vision.unige.ch/publications/postscript/98/RothPetrucciAssimacopoulosPun_icad98.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/RothPetrucciAssimacopoulosPun_icad98.pdf} } @INPROCEEDINGS{VG:ICHCI2003, author = {Patrick Roth and Thierry Pun}, title = {Rendering digital images accessible for blind computer users}, booktitle = {10th International Conference on Human-Computer Interaction}, year = {2003}, vgclass = {refpap}, vgproject = {viper}, address = {Crete, Greece}, month = {June}, url = {http://vision.unige.ch/publications/postscript/2003/RothPun-ICHCI2003.doc} } @INPROCEEDINGS{VG:RRP2001, author = {Patrick Roth and David Richoz and Lori Petrucci and Thierry Pun}, title = {An Audio-Haptic Tool For Non-Visual Image Representation}, booktitle = {ISSPA 2001, International Conference on Human-Computer Interaction (Special Session: Enhanced user interfaces for non-visual image display)}, year = {2001}, vgclass = {refpap}, vgproject = {abweb}, address = {Kuala Lumpur, Malaysia}, month = {aug}, note = {(to appear)} } @INPROCEEDINGS{VG:ICIPHCI2003, author = {Patrick Roth and D. Richoz and Thierry Pun}, title = {A multimodal system for the non-visual exploration of digital pictures}, booktitle = {Interact 2003, 9th ICIP TC13 Int. Conf. on Human-Computer Interaction}, year = {2003}, vgclass = {refpap}, vgproject = {viper}, address = {Zuerich, Switzerland}, month = {September 1-5}, url = {http://vision.unige.ch/publications/postscript/2003/Paper.Submitted.030122.Roth.doc} } @INPROCEEDINGS{OPP98, author = {Joe J. K. {\'O}~Ruanaidh and Shelby Pereira and Thierry Pun and Alexander Herrigel and Nazanin Baumg{\"a}rtner and T. Mittelholzer}, title = {Secure copyright protection techniques for digital images}, booktitle = {Proceedings of the Conference of the Swiss Priority Programme on Information and Communication Structures (SPP ICS)}, year = {1998}, vgclass = {fullconf}, vgproject = {watermarking}, address = {Irchel Campus, Z\"urich University, Z\"urich}, month = {13~July} } @ARTICLE{VG:OPH1999, author = {Joe J. K. {\'O}~Ruanaidh and Holger Petersen and Alexander Herrigel and Shelby Pereira and Thierry Pun}, title = {Cryptographic copyright protection for digital images based on watermarking techniques}, journal = {Theoretical Computer Science}, year = {1999}, volume = {226}, pages = {117--142}, vgclass = {refpap}, vgproject = {watermarking}, number = {1--2}, month = {17~September}, note = {(Special Issue: Cryptography, C. Ding, Ed.)}, abstract = {In this paper we present a new approach for the secure and robust copyright protection of digital images. We describe a system for generating digital watermarks and for trading watermarked images. The system is based on a new watermarking technique, which is \emph{robust} against image transformation techniques such as \emph{compression, rotation, translation, scaling} and \emph{cropping}. It uses modulation of the magnitude components in Fourier space to embed a watermark and an accompanying template and, during watermark extraction, reads a template in the log polar transform of the frequency domain. The template is used for analyzing scaling and rotation suffered by the watermarked stego-image. The detection of the watermarks is also possible without any need for the original cover-image. In addition, the system applies asymmetric cryptographic protocols for different purposes, namely embedding/detecting the watermark and transferring watermarked data. The public key technique is applied for the construction of a one-way watermark embedding and the verification function to identify and prove the uniqueness of the watermark. Legal dispute resolution is supported for the multiple watermarking of a digital image without revealing the confidential keying information.}, url = { http://vision.unige.ch/publications/postscript/99/ORuanaidhPetersenHerrigelPereiraPun_tcs99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/ORuanaidhPetersenHerrigelPereiraPun_tcs99.pdf} } @INPROCEEDINGS{Rytsar:2007:EMBC, author = {Romana Rytsar and Thierry Pun}, title = {Computational aspects of the EEG forward problem solutions for real head model using finite element method}, booktitle = {Proceedings of the 29th Annual Internatinal Conference IEEE Engineering in Medicine and Biology Society}, year = {2007}, vgclass = {refpap}, vgproject = {bmi}, address = {Lyon, France}, month = {August 23--26}, owner = {beekhof}, timestamp = {2007.08.29} } @INPROCEEDINGS{Rytsar:2007:VipIMAGE, author = {Romana Rytsar and Thierry Pun}, title = {Human head models for the EEG forward problem}, booktitle = {Proceedings of the International ECCOMAS Thematic Conference VipIMAGE 2007, Computational Vision and Medical Image Processing}, year = {2007}, vgclass = {refpap}, vgproject = {bmi}, address = {Porto, Portugal}, month = {17--19th October}, organization = {FEUP}, owner = {beekhof}, timestamp = {2007.08.29} } @INPROCEEDINGS{Rytsar:Diablerets006:FEMDSE, author = {Romana Rytsar and Thierry Pun}, title = {Finite elements modelling of the dipole source in EEG}, booktitle = {Lemanic-Neurosciences Annual Meeting}, year = {2006}, vgclass = {fullconf}, vgproject = {bmi}, address = {Les Diablerets, Switzerland}, month = {September 8--9} } @INPROCEEDINGS{Rytsar:EBC2006:FESFEMDS, author = {Romana Rytsar and Thierry Pun}, title = {The forward EEG solutions: finite elements modelling of the dipole source}, booktitle = {European Bioalpine Convention}, year = {2006}, vgclass = {fullconf}, vgproject = {bmi}, address = {Grenoble, France}, month = {October 6} } @INPROCEEDINGS{YRytsar:CSIT2005:TDDH-SMP, author = { Y. Rytsar and Fr\'{e}d\'{e}ric Deguillaume and Sviatoslav Voloshynovskiy and E. Rivera and Thierry Pun}, title = {Text document data-hiding: security and multimedia perspectives}, booktitle = {5th International Conference on Computer Science and Information Technologies {CSIT 2005}}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Yerevan, Armenia}, month = {September 19-23}, note = {accepted paper} } @INPROCEEDINGS{VG:SPIE2004c, author = {Y. Rytsar and Sviatoslav Voloshynovskiy and F. Ehrler and Thierry Pun}, title = {Interactive segmentation with hidden object based annotations: towards smart media}, booktitle = {Proceedings of SPIE Electronic Imaging, Storage and Retrieval Methods and Applications for Multimedia}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January}, url = {http://vision.unige.ch/publications/postscript/2004/SPIE2004_InteractiveSegmentationWithHiddenObjectBasedAnnotations.pdf} } @INPROCEEDINGS{Rytsar:SPIE2006, author = {Yuriy Rytsar and Sviatoslav Voloshynovskiy and Oleksiy Koval and Fr\'{e}d\'{e}ric Deguillaume and Emre Topak and Sergei Startchik and Thierry Pun}, title = {Tangible interactive system for document browsing and visualisation of multimedia data}, booktitle = {Proceedings of SPIE Photonics West, Electronic Imaging 2006, Multimedia Content Analysis, Management, and Retrieval 2006 (EI122)}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 15-19} } @INPROCEEDINGS{Chanel:ENT:EDLBFI, author = {Arman Savran and Koray Ciftci and Guillame Chanel and Javier Cruz Mota and Luong Hong Viet and Blent Sankur and Lale Akarun and Alice Caplier and Michele Rombaut}, title = {Emotion Detection in the Loop from Brain Signals and Facial Images}, booktitle = {Proceedings of the eNTERFACE 2006 Workshop}, year = {2006}, vgclass = {refpap}, vgproject = {bmi}, address = {Dubrovnik, Croatia}, month = {July -- August} } @MISC{VG:Sch2001, vgclass = {diploma}, vgproject = {abweb}, author = {Pascal Schmid}, title = {Reconnaissance Vocale: Int\'egration D'une Interface Modale Dans {WebSound}}, howpublished = {Diploma thesis (MSc), University of Geneva}, month = {June}, year = {2001} } @MISC{VG:Shu1990, vgclass = {diploma}, vgproject = {unspecified}, author = {Vrinda Shukla}, title = {A critical study of {L}abo{I}mage 2.0 and development of {L}abo{I}mage 3.0 (Etude critique de {L}abo{I}mage 2.0 et d\'eveloppement de {L}abo{I}mage 3.0)}, howpublished = {Diploma thesis, University of Geneva}, month = {August}, year = {1990} } @INCOLLECTION{VG:Squ1997, author = {David McG. Squire}, title = {Invariance Signatures for two-dimensional contours}, booktitle = {Machine Learning and Image Interpretation}, publisher = {Plenum Press}, year = {1997}, editor = {Terry Caelli and Walter F. Bischof}, series = {Advances in Computer Vision and Machine Intelligence, Series editor: Martin D. Levine}, chapter = {7}, pages = {255--308}, address = {New York}, abstract = {Invariant pattern recognition is an important problem in many areas of computer vision. In this chapter, a new invariant feature of two-dimensional contours is introduced: the Invariance Signature (IS). The IS is a measure of the degree to which a contour is invariant under a variety of transformations, derived from the theory of Lie transformation groups. It is shown that a Model-Based Neural Network (MBNN) can be constructed which computes the IS of a contour, and classifies patterns on this basis. MBNNs, whilst retaining the structure and advantages of traditional neural networks (TNNs), enable explicit modeling of the target system. This can result in greatly improved generalization, and representation in lower-dimensional state spaces. MBNNs can be trained with much smaller training sets than are required by TNNs. This means that MBNNs are much less computationally-expensive to train than TNNs. Experiments demonstrate that such Invariance Signature networks can be employed successfully for shift-, rotation- and scale-invariant optical character recognition.}, isbn = {0-306-45761-X}, vgclass = {refpap}, vgproject = {unspecified} } @ARTICLE{VG:Squ2000, author = {David McG. Squire}, title = {Distance Learning Networks: learning a similarity-based distance measure for content--based image retrieval}, journal = {Journal of Visual Communication and Image Representation}, year = {2000}, vgclass = {refpap}, vgproject = {viper}, abstract = {In this paper we employ human judgments of image similarity to learn a distance measure for content--based image retrieval. We first derive a statistic, $\kappa_B$, for measuring the agreement between two partitionings of an image set into unlabeled subsets. We then use the results of experiments in which human subjects partition a set of images into unlabeled subsets to define a similarity measure for pairs of images based on the frequency with which they are judged to be similar. We show that, when this measure is used to partition an image set using a clustering technique, the resultant clustering agrees better with those produced by human subjects than any of the feature space-based techniques investigated. Finally, we show that a learning technique based on an extension of a Kohonen network allows a mapping from a numerical feature space to this perceptual similarity space to be learnt which results in partitionings in excellent agreement with those produced by human subjects.} } @TECHREPORT{VG:Squ1998, author = {David McG. Squire}, title = {Generalization performance of factor analysis techniques used for image database organization}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1998}, vgclass = {report}, vgproject = {viper}, number = {98.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {January}, abstract = {The goal of this paper is to evaluate the generalization performance of a variety of factor analysis techniques in an image database environment. Factor analysis techniques, such as Principal Components Analysis, have been proposed as means of reducing the dimensionality of the data stored in image retrieval systems. These techniques compute a transformation which is applied to vectors of image features to produce vectors of lower dimensionality which still characterize the original data well. Computing such transformations for very large numbers of images is computationally expensive, especially if this calculation must be repeated each time new images are added to the database. It is to be hoped, therefore, that a transformation computed using a subset of all possible images will perform well when applied to images not used in its derivation. To evaluate this generalization ability, we measure the agreement between partitionings of image sets computed using such transformations with those produced by human subjects.}, url = { http://vision.unige.ch/publications/postscript/98/VGTR98.01_Squire.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/VGTR98.01_Squire.pdf} } @TECHREPORT{VG:Squ1998a, author = {David McG. Squire}, title = {Learning a similarity-based distance measure for image database organization from human partitionings of an image set}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1998}, vgclass = {report}, vgproject = {viper}, number = {98.03}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April}, abstract = {In this paper we employ human judgments of image similarity to improve the organization of an image database. We first derive a statistic, $\kappa_B$ which measures the agreement between two partitionings of an image set. $\kappa_B$ is used to assess agreement both amongst and between human and machine partitionings. This provides a rigorous means of choosing between competing image database organization systems, and of assessing the performance of such systems with respect to human judgments. Human partitionings of an image set are used to define an similarity value based on the frequency with which images are judged to be similar. When this measure is used to partition an image set using a clustering technique, the resultant partitioning agrees better with human partitionings than any of the feature-space-based techniques investigated. Finally, we investigate the use multilayer perceptrons and a \emph{Distance Learning Network} to learn a mapping from feature space to this perceptual similarity space. The Distance Learning Network is shown to learn a mapping which results in partitionings in excellent agreement with those produced by human subjects.}, url = { http://vision.unige.ch/publications/postscript/98/VGTR98.03_Squire.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/VGTR98.03_Squire.pdf} } @INPROCEEDINGS{VG:Squ1998b, author = {David McG. Squire}, title = {Learning a similarity-based distance measure for image database organization from human partitionings of an image set}, booktitle = {Fourth IEEE Workshop on Applications of Computer Vision (WACV'98)}, year = {1998}, vgclass = {refpap}, vgproject = {viper}, pages = {88--93}, address = {Princeton, NJ, USA}, month = {October}, abstract = {In this paper we employ human judgments of image similarity to improve the organization of an image database. We first derive a statistic, $\kappa_B$ which measures the agreement between two partitionings of an image set. $\kappa_B$ is used to assess agreement both amongst and between human and machine partitionings. This provides a rigorous means of choosing between competing image database organization systems, and of assessing the performance of such systems with respect to human judgments. Human partitionings of an image set are used to define an similarity value based on the frequency with which images are judged to be similar. When this measure is used to partition an image set using a clustering technique, the resultant partitioning agrees better with human partitionings than any of the feature-space-based techniques investigated. Finally, we investigate the use of multilayer perceptrons and a \emph{Distance Learning Network} to learn a mapping from feature space to this perceptual similarity space. The Distance Learning Network is shown to learn a mapping which results in partitionings in excellent agreement with those produced by human subjects.}, url = { http://vision.unige.ch/publications/postscript/98/Squire_wacv98.ps.gz}, url1 = {http://vision.unige.ch/publications/postscript/98/Squire_wacv98.pdf} } @INPROCEEDINGS{VG:Squ1998c, author = {David McG. Squire}, title = {Using human partitionings of image sets to learn a similarity-based distance measure for the organization of image databases}, booktitle = {Multimedia Storage and Archiving Systems III (VV02)}, year = {1998}, vgclass = {refpap}, vgproject = {viper}, volume = {3527}, series = {SPIE Proceedings}, pages = {80--88}, address = {Boston, Massachusetts, USA}, month = {November}, note = {(SPIE Symposium on Voice, Video and Data Communications)}, abstract = {In this paper our goal is to employ human judgments of image similarity to improve the organization of an image database for content-based retrieval. We first derive a statistic, $\kappa_B$ for measuring the agreement between two partitionings of an image set into unlabeled subsets. This measure can be used both to measure the degree of agreement between pairs of human subjects, and also between human and machine partitionings of an image set. It also allows a direct comparison of database organizations, as opposed to the indirect measure available via precision and recall measurements. This provides a rigorous means of selecting between competing image database organization systems, and assessing how close the performance of such systems is to that which might be expected from a database organization done by hand. We then use the results of experiments in which human subjects are asked to partition a set of images into unlabeled subsets to define a similarity measure for pairs of images based on the frequency with which they were judged to be similar. We show that, when this measure is used to partition an image set using a clustering technique, the resultant clustering agrees better with those produced by human subjects than any of the feature space-based techniques investigated. Finally, we investigate the use of machine learning techniques to discover a mapping from a numerical feature space to this perceptual similarity space. Such a mapping would allow the ground truth knowledge abstracted from the human judgments to be generalized to unseen images. We show that a learning technique based on an extension of a Kohonen network allows a similarity space to be learnt which results in partitionings in excellent agreement with those produced by human subjects.}, keywords = {image databases, database organization, similarity, learning, agreement} } @ARTICLE{VG:SqC2000, author = {David McG. Squire and Terry M. Caelli}, title = {Invariance Signatures: Characterizing contours by their departures from invariance}, journal = {Computer Vision and Image Understanding}, year = {2000}, volume = {77}, pages = {284--316}, vgclass = {refpap}, vgproject = {viper}, number = {3}, month = {mar}, abstract = {In this paper, a new invariant feature of two-dimensional contours is reported: the Invariance Signature. The Invariance Signature is a measure of the degree to which a contour is invariant under a variety of transformations, derived from the theory of Lie transformation groups. It is shown that the Invariance Signature is itself invariant under shift, rotation and scaling of the contour. Since it is derived from local properties of the contour, it is well-suited to a neural network implementation. It is shown that a Model-Based Neural Network (MBNN) can be constructed which computes the Invariance Signature of a contour, and classifies patterns on this basis. Experiments demonstrate that Invariance Signature networks can be employed successfully for shift-, rotation- and scale-invariant optical character recognition.}, url = { http://vision.unige.ch/publications/postscript/99/SquireCaelli_cviu99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/SquireCaelli_cviu99.pdf} } @TECHREPORT{VG:SqC1997, author = {David McG. Squire and Terry M. Caelli}, title = {Invariance Signatures: Characterizing contours by their departures from invariance}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1997}, vgclass = {report}, vgproject = {unspecified}, number = {97.04}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April}, url = { http://vision.unige.ch/publications/postscript/97/VGTR97.04_SquireCaelli.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/VGTR97.04_SquireCaelli.pdf} } @TECHREPORT{VG:SMM1999b, author = {David McG. Squire and Henning M{\"u}ller and Wolfgang M{\"u}ller}, title = {Improving Response Time by Search Pruning in a Content-Based Image Retrieval System, Using Inverted File Techniques}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1999}, vgclass = {report}, vgproject = {viper}, number = {99.01}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {February}, abstract = {This paper describes several methods for improving query evaluation speed in a content-based image retrieval system (CBIRS). Response time is an extremely important factor in determining the usefulness of any interactive system, as has been demonstrated by human factors studies over the past thirty years. In particular, response times of less than one second are often specified as a usability requirement. It is shown that the use of inverted files facilitates the reduction of query evaluation time without significantly reducing the accuracy of the response. The performance of the system is evaluated using precision \vs recall graphs, which are an established evaluation method in information retrieval (IR), and are beginning to be used by CBIR researchers.}, keywords = {content-based image retrieval, search pruning, inverted file, response time}, url = { http://vision.unige.ch/publications/postscript/99/VGTR99.01_SquireMuellerMueller.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/VGTR99.01_SquireMuellerMueller.pdf} } @INPROCEEDINGS{VG:SMM1999c, author = {David McG. Squire and Henning M{\"u}ller and Wolfgang M{\"u}ller}, title = {Improving Response Time by Search Pruning in a Content-Based Image Retrieval System, Using Inverted File Techniques}, booktitle = {IEEE Workshop on Content-based Access of Image and Video Libraries (CBAIVL-99)}, year = {1999}, vgclass = {refpap}, vgproject = {viper}, pages = {45--49}, address = {Fort Collins, Colorado, USA}, month = {22~June}, abstract = {This paper describes several methods for improving query evaluation speed in a content-based image retrieval system (CBIRS). Response time is an extremely important factor in determining the usefulness of any interactive system, as has been demonstrated by human factors studies over the past thirty years. In particular, response times of less than one second are often specified as a usability requirement. It is shown that the use of inverted files facilitates the reduction of query evaluation time without significantly reducing the accuracy of the response. The performance of the system is evaluated using precision \vs recall graphs, which are an established evaluation method in information retrieval (IR), and are beginning to be used by CBIR researchers.}, url = { http://vision.unige.ch/publications/postscript/99/SquireMuellerMueller_cbaivl99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/SquireMuellerMueller_cbaivl99.pdf} } @INBOOK{VG:SMM2001, chapter = {7}, pages = {125--151}, title = {Design and Evaluation of a Content-based Image Retrieval System}, publisher = {Idea Group Publishing}, year = {2001}, editor = {Syed M Rahman}, author = {David McG. Squire and Henning M{\"u}ller and Wolfgang M{\"u}ller and St{\'e}phane Marchand-Maillet and Thierry Pun}, abstract = {The growth in size and accessibility of multimedia databases have changed our approach to information retrieval. Classical text-based systems show their limitations in the context of multimedia retrieval. In this chapter, we address the problem of conceiving and evaluating a content-based image retrieval system. First, we investigate the use of the query-by-example (QBE) paradigm as a base paradigm for the development of a content-based image retrieval system (CBIRS). We show that it should be considered as a complement to the classical textual-based paradigms. We then evaluate the capabilities of the most up-to-date computer vision techniques in contributing to the realisation of such a system. Further, beyond the necessity of accurate image understanding techniques, we show that the amount of data involved by the process of describing image content should also be considered as an important issue. This aspect of our study is largely based on the experience acquired by the text retrieval (TR) community, which we adapt to the context of CBIR. Similarly, the text retrieval community has also developed a significant experience in evaluating retrieval systems, where judgements include subjectivity and context dependency. Extending this experience, we study a coherent framework for performing the evaluation of a CBIRS. As a practical example, we use our Viper CBIR system, using a novel communication protocol called MRML to pinpoint the importance of the sharing of resource in facilitating the evaluation and therefore the development of CBIRS.}, booktitle = {Design and Management of Multimedia Information Systems: Opportunities and Challenges}, vgclass = {refpap}, vgproject = {viper} } @INPROCEEDINGS{VG:SMM1999a, author = {David McG. Squire and Wolfgang M{\"u}ller and Henning M{\"u}ller}, title = {Relevance feedback and term weighting schemes for content-based image retrieval}, booktitle = {Third International Conference On Visual Information Systems}, year = {1999}, vgclass = {refpap}, vgproject = {viper}, pages = {549--556}, address = {Amsterdam, The Netherlands}, month = {2--4~June}, abstract = {This paper describes the application of techniques derived from text retrieval research to the content-based querying of image databases. Specifically, the use of inverted files, frequency-based weights and relevance feedback are investigated. The use of inverted files allows very large numbers ($\geq \mathcal{O}(104)$) of \emph{possible} features to be used. since search is limited to the subspace spanned by the features present in the query image(s). A variety of weighting schemes used in text retrieval are employed, yielding different results. We suggest possibles modifications for their use with image databases. The use of relevance feedback was shown to improve the query results significantly, as measured by precision and recall, for all users.}, url = { http://vision.unige.ch/publications/postscript/99/SquireMuellerMueller_vis99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/SquireMuellerMueller_vis99.pdf} } @TECHREPORT{VG:SMM1998a, author = {David McG. Squire and Wolfgang M{\"u}ller and Henning M{\"u}ller}, title = {Relevance feedback and term weighting schemes for content-based image retrieval}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1998}, vgclass = {report}, vgproject = {viper}, number = {98.05}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {December}, abstract = {This paper describes the application of techniques derived from text retrieval research to the content-based querying of image databases. Specifically, the use of inverted files, frequency-based weights and relevance feedback are investigated. The use of inverted files allows very large numbers ($\geq \mathcal{O}(104)$) of \emph{possible} features to be used. since search is limited to the subspace spanned by the features present in the query image(s). A variety of weighting schemes used in text retrieval are employed, yielding different results. We suggest possibles modifications for their use with image databases. The use of relevance feedback was shown to improve the query results significantly, as measured by precision and recall, for all users.}, url = { http://vision.unige.ch/publications/postscript/98/VGTR98.05_SquireMuellerMueller.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/VGTR98.05_SquireMuellerMueller.pdf} } @ARTICLE{VG:SMM2000a, author = {David McG. Squire and Wolfgang M{\"u}ller and Henning M{\"u}ller and Thierry Pun}, title = {Content-based query of image databases: inspirations from text retrieval}, journal = {Pattern Recognition Letters (Selected Papers from The 11th Scandinavian Conference on Image Analysis SCIA '99)}, year = {2000}, volume = {21}, pages = {1193-1198}, vgclass = {refpap}, vgproject = {viper}, number = {13-14}, note = {B.K. Ersboll, P. Johansen, Eds.}, abstract = {This paper reports the application of techniques inspired by text retrieval research to content-based image retrieval. In particular, we show how the use of an inverted file data structure permits the use of an extremely high-dimensional feature-space, by restricting search to the subspace spanned by the features present in the query. A suitably sparse set of colour and texture features is proposed. A weighting scheme based on feature frequencies is used to combine disparate features in a compatible manner, and naturally extends to incorporate relevance feedback queries. The use of relevance feedback is shown consistently to improve system performance.}, url = {http://www.elsevier.nl/gej-ng/10/35/61/45/36/34/article.pdf} } @INPROCEEDINGS{VG:SMM1999, author = {David McG. Squire and Wolfgang M{\"u}ller and Henning M{\"u}ller and Jilali Raki}, title = {Content-based query of image databases, inspirations from text retrieval: inverted files, frequency-based weights and relevance feedback}, booktitle = {The 11th Scandinavian Conference on Image Analysis}, year = {1999}, vgclass = {refpap}, vgproject = {viper}, pages = {143--149}, address = {Kangerlussuaq, Greenland}, month = {jun 7--11}, abstract = {In this paper we report the application of techniques inspired by text retrieval research to the content-based query of image databases. In particular, we show how the use of an inverted file data structure permits the use of a feature space of $\mathcal{O}(104)$ dimensions, by restricting search to the subspace spanned by the features present in the query. A suitably sparse set of colour and texture features is proposed. A scheme based on the frequency of occurrence of features in both individual images and in the whole collection provides a means of weighting possibly incommensurate features in a compatible manner, and naturally extends to incorporate relevance feedback queries. The use of relevance feedback is shown consistently to improve system performance, as measured by precision and recall.}, url = { http://vision.unige.ch/publications/postscript/99/SquireMuellerMuellerRaki_scia99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/SquireMuellerMuellerRaki_scia99.pdf} } @TECHREPORT{VG:SMM1998, author = {David McG. Squire and Wolfgang M{\"u}ller and Henning M{\"u}ller and Jilali Raki}, title = {Content-based query of image databases, inspirations from text retrieval: inverted files, frequency-based weights and relevance feedback}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1998}, vgclass = {report}, vgproject = {viper}, number = {98.04}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {November}, abstract = {In this paper we report the application of techniques inspired by text retrieval research to the content-based query of image databases. In particular, we show how the use of an inverted file data structure permits the use of a feature space of $\mathcal{O}(104)$ dimensions, by restricting search to the subspace spanned by the features present in the query. A suitably sparse set of colour and texture features is proposed. A scheme based on the frequency of occurrence of features in both individual images and in the whole collection provides a means of weighting possibly incommensurate features in a compatible manner, and naturally extends to incorporate relevance feedback queries. The use of relevance feedback is shown consistently to improve system performance, as measured by precision and recall.}, url = { http://vision.unige.ch/publications/postscript/98/VGTR98.04_SquireMuellerMuellerRaki.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/VGTR98.04_SquireMuellerMuellerRaki.pdf} } @INPROCEEDINGS{VG:SqP1997, author = {David McG. Squire and Thierry Pun}, title = {A Comparison of Human and Machine Assessments of Image Similarity for the Organization of Image Databases}, booktitle = {The 10th Scandinavian Conference on Image Analysis}, year = {1997}, vgclass = {refpap}, vgproject = {viper}, editor = {Michael Frydrych and Jussi Parkkinen and Ari Visa}, pages = {51--58}, address = {Lappeenranta, Finland}, month = {June}, abstract = {There has recently been a significant interest in the organization and \emph{content-based} querying of large images databases. Most frequently, the underlying hypothesis is that image similarity can be characterized by low-level image features, without further abstraction. This assumes that there is sufficient agreement between machine and human measures of image similarity for the database to be useful. We wish to assess the veracity of this assumption. To this end, we develop measures of the agreement between two partitionings of an image set; we show that it is vital to take chance agreements into account. We then use these measures to assess the agreement between human subjects and a variety of machine clustering techniques on a set of images. The results can be used to select and refine image distance measures for querying and organizing image databases.}, keywords = {image similarity, image database organization, agreement statistics, VG:SqP1997key}, url = { http://vision.unige.ch/publications/postscript/97/SquirePun_scia97.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/SquirePun_scia97.pdf} } @ARTICLE{VG:SqP1998, author = {David McG. Squire and Thierry Pun}, title = {Assessing Agreement Between Human and Machine Clusterings of Image Databases}, journal = {Pattern Recognition}, year = {1998}, volume = {31}, pages = {1905--1919}, vgclass = {refpap}, vgproject = {viper}, number = {12}, abstract = {There is currently much interest in the organization and \emph{content-based} querying image databases. The usual hypothesis is that image similarity can be characterized by low-level features, without further abstraction. This assumes that agreement between machine and human measures of similarity is sufficient for the database to be useful. To assess this assumption, we develop measures of the agreement between partitionings of an image set, showing that chance agreements \emph{must} be considered. These measures are used to assess the agreement between human subjects and several machine clustering techniques on an image set. The results can be used to select and refine distance measures for querying and organizing image databases.}, url = {http://vision.unige.ch/publications/postscript/98/SquirePun_pr.ps.gz}, url1 = {http://vision.unige.ch/publications/postscript/98/SquirePun_pr.pdf} } @TECHREPORT{VG:SqP1997a, author = {David McG. Squire and Thierry Pun}, title = {Assessing Agreement Between Human and Machine Clusterings of Image Databases}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1997}, vgclass = {report}, vgproject = {viper}, number = {97.03}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April}, abstract = {There is currently much interest in the organization and \emph{content-based} querying image databases. The usual hypothesis is that image similarity can be characterized by low-level features, without further abstraction. This assumes that agreement between machine and human measures of similarity is sufficient for the database to be useful. To assess this assumption, we develop measures of the agreement between partitionings of an image set, showing that chance agreements \emph{must} be considered. These measures are used to assess the agreement between human subjects and several machine clustering techniques on an image set. The results can be used to select and refine distance measures for querying and organizing image databases.}, url = { http://vision.unige.ch/publications/postscript/97/VGTR97.03_SquirePun.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/VGTR97.03_SquirePun.pdf} } @TECHREPORT{VG:SqP1997b, author = {David McG. Squire and Thierry Pun}, title = {Using human partitionings of an image set to learn a similarity-based distance measure}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {1997}, vgclass = {report}, vgproject = {viper}, number = {97.06}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {November}, abstract = {In this paper our goal is to employ human judgments of image similarity to improve the organization of an image database for content-based retrieval. We first derive a statistic, $\kappa_B$ for measuring the agreement between two partitionings of an image set into unlabeled subsets. This measure can be used both to measure the degree of agreement between pairs of human subjects, and also between human and machine partitionings of an image set. This provides a rigorous means of selecting between competing image database organization systems, and assessing how close the performance of such systems is to that which might be expected from a database organization done by hand. We then use the results of experiments in which human subjects are asked to partition a set of images into unlabeled subsets to define a similarity measure for pairs of images based on the frequency with which they were judged to be similar. We show that, when this measure is used to partition an image set using a clustering technique, the resultant clustering agrees better with those produced by human subjects than any of the feature space-based techniques investigated. Finally, we investigate the use of machine learning techniques to discover a mapping from a numerical feature space to this perceptual similarity space. Such a mapping would allow the ground truth knowledge abstracted from the human judgments to be generalized to unseen images.}, url = { http://vision.unige.ch/publications/postscript/97/VGTR97.06_SquirePun.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/97/VGTR97.06_SquirePun.pdf} } @MISC{VG:Sta1988, vgclass = {licence}, vgproject = {unspecified}, author = {Jos Stam}, title = {Rendu r\'ealiste de surfaces par la m\'ethode du ray tracing}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {October}, year = {1988} } @PHDTHESIS{VG:Sta1998, author = {Sergei Startchik}, title = {Geometric and Illumination Invariant Object Representation: Application to Content-based Image Retrieval}, school = {University of Geneva}, year = {1998}, type = {{P}h.{D}. {D}issertation {N}o. 3009}, address = {Switzerland}, month = {July}, note = {Thesis Jury: Prof. Thierry Pun (Geneva, CH), Prof. Roger Mohr (INP Grenoble, F), Serge Ayer (EPF-Lausanne, CH), Prof. Christian Pellegrini (Geneva, CH)}, abstract = {This work addresses several issues in the field of computer vision. In particular, attention is focussed on the problem of the representation of an object from its appearance in an image. Several advances are proposed for the representation of planar shapes, which are thus suitable for representing planar and faceted objects. The representation developed is employed for content-based retrieval from an image database. The proposed projectively invariant description for groups of planar disjoint contours as a simultaneous polar reparametrization of multiple curves. Its origin is an invariant point and, for each ray orientation, the cross-ratio of the intersections with the closest curves gives the radius. The sequence of cross-ratio values for all orientations forms a signature. With respect to other methods, this representation is less reliant on individual curve properties, both for the construction of the reference frame and for the calculation of the signature. At the same time, this representation is local and integrates information from multiple curves, guaranteeing robustness to curve discontinuities and partial occlusions. Chromatic information is introduced into the representation and offers two advantages. First, the representation provides a more complete description of the shape and thus becomes more discriminative. Secondly, the chromatic description is illumination invariant under a diagonal chromaticity model and one more acquisition variable is therefore removed. The proposed representation was originally developed for planar shapes, but an extension has been proposed and validated for trihedral corners. [truncated]}, abstract2 = {A complete system architecture has been implemented, composed of the following stages: feature extraction, reference frame construction, signature evaluation and indexing. The feature extraction stage provides a set of image contours approximated by splines. Joint invariant properties of curves are used to define the center point of the reference frame and the associated rays. Invariant signatures are computed from a combination of local properties of multiple curves. These signatures are used as a multidimensional index into a database of signatures and a subset of plausible object models is thus obtained. The invariant signature method has been used for object representation in the context of content-based retrieval from image databases. In particular, we focus on images which portray man-made objects with planar facets or trihedral corners, which contain trademarks. The database consist of 203 images of 41 such objects. Images were taken from different viewpoints under various illumination conditions. Experimental evaluation has shown that the method is stable to those realistic variations and its performance in this framework is satisfactory. In conclusion, we believe that this approach is an important extension of shape representation methods to a much broader class of objects.}, url = {http://cui.unige.ch/~startchi/PhD/}, vgclass = {thesis}, vgproject = {cbir} } @TECHREPORT{VG:Sta1994, author = {Serguei Startchik}, title = {Automatic construction of invariant geometric representation for object recognition}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {94.07}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {July} } @MISC{VG:Sta1994a, vgclass = {diploma}, vgproject = {unspecified}, author = {S. Startchik}, title = {Automatic construction of invariant geometric representation for object recognition}, howpublished = {Diploma thesis, University of Geneva}, month = {July}, year = {1994} } @TECHREPORT{VG:SBR1994, author = {Serguei Startchik and Jean-Marc Bost and Christian Rauber and Ruggero Milanese and Thierry Pun}, title = {Automatic construction of invariant geometric representation for object recognition}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1994}, vgclass = {report}, vgproject = {unspecified}, number = {94.05}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/startchi/94.05.Report.ps.gz} } @TECHREPORT{VG:SLP1991, author = {Serguei Startchik and Marc Lefebvre and Thierry Pun}, title = {Calibration d'une cam\'era par filtrage \'etendu de {K}alman; reconstruction tridimensionnelle}, institution = {AI and Vision Group, Computing Centre, University of Geneva}, year = {1991}, vgclass = {report}, vgproject = {unspecified}, number = {91.04}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {April} } @INPROCEEDINGS{VG:SMP1998a, author = {Serguei Startchik and Ruggero Milanese and Thierry Pun}, title = {Projective and illumination invariant representation of disjoint shapes}, booktitle = {Computer Vision -- ECCV 98}, year = {1998}, vgclass = {refpap}, vgproject = {cbir}, editor = {H. Burkhardt and B. Neumann}, number = {1406}, series = {Lecture Notes in Computer Science}, pages = {264--280}, address = {Freiburg, Germany}, month = {June}, publisher = {Springer-Verlag}, note = {(Proceedings of the Fifth European Conference on Computer Vision)}, abstract = {We describe a new projectively invariant representation of disjoint contour groups which is suitable for shape-based retrieval from an image database. It consists of simultaneous polar reparametrization of multiple curves where an invariant point is used as the origin. For each ray orientation, a cross-ratio of its intersections with other curves is taken as a value associated to the radius. With respect to other methods this representation is less reliant on single curve properties, both for the construction of the projective basis and for calculating the signature. It is therefore more robust to contour gaps and image noise and is better suited to describing complex planar shapes defined by multiple disjoint curves. The proposed representation has been originally developed for planar shapes, but an extension is proposed and validated for 3D faceted objects. Moreover, we show that illumination invariance fits well within the proposed framework and can easily be introduced in the representation in order to make it more appropriate for shape-based retrieval. Experiments are reported on a database of real trademarks.}, comment = {volume 1, but can't have both volume \& number for proc.}, url = { http://vision.unige.ch/publications/postscript/98/StartchikMilanesePun_eccv98.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/StartchikMilanesePun_eccv98.pdf} } @ARTICLE{VG:SMP1998, author = {Serguei Startchik and Ruggero Milanese and Thierry Pun}, title = {Projective and photometric invariant representation of planar disjoint shapes}, journal = {Image and Vision Computing}, year = {1998}, volume = {16}, pages = {713--723}, vgclass = {refpap}, vgproject = {cbir}, number = {9--10}, month = {July}, abstract = {We describe a new projectively invariant representation of disjoint contour groups which is suitable for shape-based retrieval from an image database. It consists of simultaneous polar reparametrization of multiple curves where an invariant point is used as the origin. For each ray orientation, a cross-ratio of its intersections with other curves is taken as a value associated to the radius. With respect to other methods this representation is less reliant on single curve properties, both for the construction of the projective basis and for calculating the signature. It is therefore more robust to contour gaps and image noise and is better suited to describing complex planar shapes defined by multiple disjoint curves. Moreover, we show that illumination invariance fits well within the proposed framework and can easily be introduced in the representation in order to make it more appropriate for shape-based retrieval. Experiments are reported on a database of real trademarks. Keywords: Projective invariance, Cross-ratio, Geometry, Illumination invariance, Shape-based retrieval, Object representation.}, url = { http://vision.unige.ch/publications/postscript/98/StartchikMilanesePun_ivc98.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/98/StartchikMilanesePun_ivc98.pdf} } @INCOLLECTION{VG:SMR1997, author = {Serguei Startchik and Ruggero Milanese and Christian Rauber and Thierry Pun}, title = {Planar shape databases with affine invariant search}, booktitle = {Image Databases and Multi-media search}, publisher = {World Scientific}, year = {1997}, editor = {A. W. M. Smeulders and R. Jain}, series = {Software Engineering and Knowledge Engineering (S. K. Chang, ed.)}, pages = {285--292}, note = {(originally appeared in: First {IAPR} International Workshop on Image Databases and Multi-Media Search, Amsterdam, NL, 202--209, August 1996)}, vgclass = {refpap}, vgproject = {cbir} } @INPROCEEDINGS{VG:SRP1995, author = {Serguei Startchik and Christian Rauber and Thierry Pun}, title = {Recognition of planar objects over complex backgrounds using line invariants and relevance measures}, booktitle = {GMICV'95, Proceedings of the International Workshop on Geometric Modelling and Invariance for Computer Vision, Xi'an, China}, year = {1995}, vgclass = {refpap}, vgproject = {unspecified}, editor = {R. Mohr and W. Chengke}, pages = {301--306}, month = {April}, publisher = {Xidian University Press}, url = {ftp://cui.unige.ch/PUBLIC/vision/papers/startchi/95.04.GMICV.ps.gz} } @MISC{VG:Ste1998, vgclass = {diploma}, vgproject = {unspecified}, author = {St{\'e}phane Stepien}, title = {R\'eseau d'oscillateurs neuronaux pour la segmentation d'images}, howpublished = {Diploma thesis, University of Geneva}, month = {April}, year = {1998} } @ARTICLE{VG:SVP2001, author = {A. Synyavskyy and Sviatoslav Voloshynovskiy and I. Prudyus}, title = {Wavelet-Based {MAP} Image Denoising Using Provably Better Class of Stochastic I.I.D. Image Models}, journal = {Facta Universitatis (Nis)}, year = {2001}, volume = {14}, vgclass = {refpap}, vgproject = {watermarking}, url = { http://vision.unige.ch/publications/postscript/2001/SynyavskyyVoloshynovskiyPrudyus_FU2001.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2001/SynyavskyyVoloshynovskiyPrudyus_FU2001.pdf} } @MISC{VG:Tat1995, vgclass = {diploma}, vgproject = {unspecified}, author = {Moni Tat}, title = {D\'efinition d'une interface homme-machine pour un robot industriel ({G}estion d'un bras manipulateur)}, howpublished = {Diploma thesis, University of Geneva}, month = {January}, year = {1995} } @INPROCEEDINGS{BMI:IM22003:BMI, author = {BMI Team}, title = {Brain machine interfaces}, booktitle = {NCCR (IM)2 Interactive Multimodal Information Management Workshop}, year = {2003}, vgclass = {fullconf}, vgproject = {bmi}, address = {Martigny / Crans-Montana, Switzerland}, month = {October 6--8} } @INPROCEEDINGS{Topak:SPIE2006:GA, author = {Emre Topak and Sviatoslav Voloshynovskiy and Oleksiy Koval and M. E. Haroutunian and J.E. Vila-Forc{\'e}n and Thierry Pun}, title = {E-capacity analysis of data-hiding channels with geometrical attacks}, booktitle = {Proceedings of SPIE Electronic Imaging 2006, Security, Steganography, and Watermarking of Multimedia Contents VIII (EI121)}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 15-19}, url = {http://vision.unige.ch/publications/postscript/2005/TopakVoloshynovskiyKovalHaroutunianVilaPun_SPIE06_Ecap.ps} } @INPROCEEDINGS{Topak:SPIE2005, author = {Emre Topak and Sviatoslav Voloshynovskiy and Oleksiy Koval and M.K. Mihcak and Thierry Pun}, title = {Security analysis of robust data hiding with geometrically structured codebooks}, booktitle = {Proceedings of SPIE Photonics West, Electronic Imaging 2005, Security, Steganography, and Watermarking of Multimedia Contents VII (EI120)}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 16-20}, url = {http://vision.unige.ch/publications/postscript/2005/spie_topak_voloshynovskiy_koval.pdf}, url1 = {http://vision.unige.ch/publications/postscript/2005/spie_topak_voloshynovskiy_koval.ps}, url2 = {http://vision.unige.ch/publications/postscript/2005/TopakVoloshynovskiyKovalMihcakPun_SPIE2005.ppt.pdf} } @ARTICLE{Topak:2005:ACM, author = {Emre Topak and Sviatoslav Voloshynovskiy and Oleksiy Koval and M. Kivanc Mihcak and Thierry Pun}, title = {Towards geometrically robust data-hiding with structured codebooks}, journal = {{ACM} Multimedia Systems Journal, Special Issue on Multimedia and Security}, year = {2005}, volume = {11}, pages = {121--132}, vgclass = {refpap}, vgproject = {watermarking}, number = {2}, month = {December}, note = {published online at http://www.springerlink.com/media/b0cyhc8uyk4jph8ugt33/contributions/f/4/3/9/f4392u5p824845t5.pdf}, url = {http://vision.unige.ch/publications/postscript/2005/TopakVoloshynovskiyKovalMihcakPun_ACM2005.pdf} } @INPROCEEDINGS{ETopak:EUSIPCO2005, author = {Emre Topak and Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Achievable Rate Analysis of Geometrically Robust Data-Hiding Codes In Asymptotic Set-ups}, booktitle = {{EUSIPCO} 2005, 13th European Signal Processing Conference}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Antalya, Turkey}, month = {September 4-8}, url = {http://vision.unige.ch/publications/postscript/2005/TopakVoloshynovskiyKovalPun_EUSIPCO2005.pdf} } @INPROCEEDINGS{VG:EUSIPCO2004, author = {Emre Topak and Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Capacity analysis of periodical watermarking}, booktitle = {EUSIPCO-2004, 12th European Signal Processing Conference}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, address = {Vienna, Austria}, month = {September 6-10}, url = {http://vision.unige.ch/publications/postscript/2004/TopakVoloshynovskiyKovalPun_EUSIPCO2004.pdf} } @INPROCEEDINGS{VG:WIAMIS2005, author = {Emre Topak and Sviatoslav Voloshynovskiy and Oleksiy Koval and J. E. Vila-Forc{\'e}n and Thierry Pun}, title = {On Security of Geometrically-Robust Data-Hiding}, booktitle = {WIAMIS 2005, 6th International Workshop on Image Analysis for Multimedia Interactive Services}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Montreux, Switzerland}, month = {April 13-15}, url = {http://vision.unige.ch/publications/postscript/2005/TopakVoloshynovskiyKovalForcenPun_WIAMIS2005.pdf} } @ARTICLE{VG:TUP1992, author = {B. L. Trus and M. Unser and Thierry Pun and A. C. Steven}, title = {Digital image processing of electron micrographs: the {PIC} {S}ystem {II}}, journal = {Journal of Scanning Microscopy, Scanning Microscopy Supplement 6}, year = {1992}, pages = {441--451}, vgclass = {refpap}, vgproject = {unspecified}, note = {(published 1994)} } @INPROCEEDINGS{VG:TUP1991, author = {B. L. Trus and M. Unser and Thierry Pun and A. C. Steven}, title = {Digital Image Processing of Electron Micrographs: {T}he {PIC} System {II}}, booktitle = {10th Pfefferkorn Conference on Signal and Image Processing in Microscopy and Microanalysis, Pembroke College, Cambridge, UK}, year = {1991}, vgclass = {fullconf}, vgproject = {unspecified}, month = {September} } @INPROCEEDINGS{VG:Tsc1996, author = {P. F. Tschudin}, title = {{DOCSCAN} und {KRYPICT}: zwei Basisprojekte der historischen Disziplinen}, booktitle = {23rd. International Congress of the International Association of Paper Historians ({IPH})}, year = {1996}, vgclass = {refpap}, vgproject = {unspecified}, address = {Leipzig}, month = {August} } @ARTICLE{VG:UEP1987, author = {M. Unser and J. R. Ellis and Thierry Pun and M. Eden}, title = {Optimal background estimation in {EELS}}, journal = {Journal of Microscopy}, year = {1987}, volume = {145}, pages = {245--256}, vgclass = {refpap}, vgproject = {unspecified}, number = {3}, month = {March} } @MISC{VG:Ves1991, vgclass = {diploma}, vgproject = {unspecified}, author = {Thierry Vessereau}, title = {Extraction et repr\'esentation d'information iconique: application \`a la caract\'erisation de la couleur intrins\`eque des objets}, howpublished = {Diploma thesis, University of Geneva}, month = {October}, year = {1991} } @INPROCEEDINGS{VG:SPIE2004a, author = {J.E. Vila-Forc{\'e}n and Oleksiy Koval and Sviatoslav Voloshynovskiy}, title = {Distributed single source coding with side information}, booktitle = {Proceedings of SPIE Photonics West, Electronic Imaging 2004, Image Processing}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 18-22}, url = {http://vision.unige.ch/publications/postscript/2004/VilaKovalVoloshynovskiy_SPIE2004.pdf} } @INPROCEEDINGS{Vila:MMSP2004, author = {J.E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and F. Perez-gonzalez and Thierry Pun}, title = {Worst Case Additive Attack against Quantization-Based Watermarking Techniques}, booktitle = {IEEE International Workshop on Multimedia Signal Processing (MMSP)}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, address = {Siena, Italy}, month = {September 29 - October 1}, url = {http://vision.unige.ch/publications/postscript/2004/VilaVoloshynovskiyKovalPun_MMSP2004.pdf} } @ARTICLE{Vila:2004:EURASIP, author = {J.E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Facial Image Compression Based on Structured Codebooks in Overcomplete Domain}, journal = {{EURASIP} Journal on Applied Signal Processing, Frames and overcomplete representations in signal processing, communications, and information theory special issue}, year = {2006}, volume = {2006}, pages = {1--11}, vgclass = {refpap}, vgproject = {watermarking}, number = {Article {ID} 69042}, url = {http://vision.unige.ch/publications/postscript/2005/VilaKovalVoloshynovskiyPun_JASPcompression_final.pdf} } @INPROCEEDINGS{Vila:2005:ICIP, author = {J.E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Asymmetric spread spectrum data-hiding for Laplacian host data}, booktitle = {{IEEE} International Conference on Image Processing}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Genova, Italy}, month = {11-14 September}, url = {http://vision.unige.ch/publications/postscript/2005/VilaVoloshynovskiyKovalPun_ICIP2005.pdf} } @INPROCEEDINGS{Vila:SPIE2005, author = {J.E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and F. P{\'e}rez-Gonz{\'a}lez and Thierry Pun}, title = {Worst case additive attack against quantization-based data-hiding methods}, booktitle = {Proceedings of {SPIE} Photonics West, Electronic Imaging 2005, Security, Steganography, and Watermarking of Multimedia Contents {VII (EI120)}}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 16-20}, url = {http://vision.unige.ch/publications/postscript/2005/VilaVoloshynovskiyKovalPerezGonzalezPun_SPIE2005.pdf}, url2 = {http://vision.unige.ch/publications/postscript/2005/VilaVoloshynovskiyKovalPerezGonzalezPun_SPIE2005.ppt.pdf} } @INPROCEEDINGS{Vila:2005:IWDW, author = {J.E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and F. P{\'e}rez-Gon{\'a}lez and Thierry Pun}, title = {Practical Data-Hiding: Additive Attacks Performance Analysis}, booktitle = {International Workshop on Digital Watermarking}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, volume = {LNCS 3710}, series = {Lecture Notes in Computer Science}, pages = {244--259}, address = {Siena, Italy}, month = {September 15-17}, publisher = {Springer Verlag}, note = {Invited tutorial}, url = {http://vision.unige.ch/publications/postscript/2005/VilaVoloshynovskiyKovalPerezGonzalezPun_IWDW2005.pdf} } @ARTICLE{Vila:SP2005, author = {J.E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and F. P{\'e}rez-Gon{\'a}lez and Oleksiy Koval and Thierry Pun}, title = {Quantization-Based Methods: Additive Attacks Performance Analysis}, journal = {IEEE Transactions on Signal Processing}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, note = {(submitted)} } @INPROCEEDINGS{Vila:ICASSP2006:CPUCA, author = {J. E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Costa problem under channel ambiguity}, booktitle = {Proceedings of 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {Toulouse, France}, month = {May 14-19}, url = {http://vision.unige.ch/publications/postscript/2006/VilaVoloshynovskiyKovalPun_ICASSP06_CPUCA.pdf} } @INPROCEEDINGS{Vila:SPIE2006:UDQ, author = {J. E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Performance analysis of non-uniform quantization-based data-hiding}, booktitle = {Proceedings of SPIE Photonics West, Electronic Imaging 2006, Security, Steganography, and Watermarking of Multimedia Contents VIII (EI121)}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 15-19}, url = {http://vision.unige.ch/publications/postscript/2005/VilaVoloshynovskiyKovalPun_SPIE06_UDQ.pdf} } @INPROCEEDINGS{Vila:SPIE2006:ADH, author = {J. E. Vila-Forc{\'e}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and Emre Topak and Thierry Pun}, title = {Asymmetrically informed data-hiding optimization of achievable rate for Laplacian host}, booktitle = {Proceedings of SPIE Photonics West, Electronic Imaging 2006, Security,Steganography, and Watermarking of Multimedia Contents VIII (EI121)}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 15-19}, url = {http://vision.unige.ch/publications/postscript/2005/VilaVoloshynovskiyKovalTopakPun_SPIE06_Asym.pdf} } @INPROCEEDINGS{Villan:IFIP2005, author = {R. Vill{\'a}n and Sviatoslav Voloshynovskiy and Fr\'{e}d\'{e}ric Deguillaume and Y. Rytsar and Oleksiy Koval and Emre Topak and E. Rivera and Thierry Pun}, title = {A Theoretical Framework for Data-Hiding in Digital and Printed Text Documents}, booktitle = {Proceedings of 9th IFIP TC-6 TC-11 International Conference on Communications and Multimedia Security}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, volume = {LNCS 3677}, pages = {280--281}, address = {Salzburg, Austria}, month = {September 19--21}, url = {http://vision.unige.ch/publications/postscript/2005/VillanVoloshynovskiyDeguillaumeRytsarKovalTopakRiveraPun_CMS2005.pdf}, url1 = {http://vision.unige.ch/publications/postscript/2005/VillanVoloshynovskiyDeguillaumeRytsarKovalTopakRiveraPun_CMS2005.ps.gz}, url2 = {http://vision.unige.ch/publications/postscript/2005/VillanVoloshynovskiyDeguillaumeRytsarKovalTopakRiveraPun_CMS2005.ppt.pdf} } @INPROCEEDINGS{Villan:SPIE2007:RH, author = {Renato Vill{\'a}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and Fr\'{e}d\'{e}ric Deguillaume and Thierry Pun}, title = {Tamper-proofing of Electronic and Printed Text Documents via Robust Hashing and Data-Hiding}, booktitle = {Proceedings of {SPIE-IS{\&}T} Electronic Imaging 2007, Security, Steganography, and Watermarking of Multimedia Contents IX}, year = {2007}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {28 Jan. -- 1 Feb.}, abstract = {In this paper, we deal with the problem of authentication and tamper-proofing of text documents that can be distributed in electronic or printed forms. We advocate the combination of robust text hashing and text data-hiding technologies as an efficient solution to this problem. First, we consider the problem of text data-hiding in the scope of the Gel'fand-Pinsker data-hiding framework. For illustration, two modern text data-hiding methods, namely color index modulation (CIM) and location index modulation (LIM), are explained. Second, we study two approaches to robust text hashing that are well suited for the considered problem. In particular, both approaches are compatible with CIM and LIM. The first approach makes use of optical character recognition (OCR) and a classical cryptographic message authentication code (MAC). The second approach is new and can be used in some scenarios where OCR does not produce consistent results. The experimental work compares both approaches and shows their robustness against typical intentional/unintentional document distortions including electronic format conversion, printing, scanning, photocopying, and faxing.}, url = {http://vision.unige.ch/publications/postscript/2007/SPIE-EI-2007-Robust-Hashing-paper.pdf}, url1 = {http://vision.unige.ch/publications/postscript/2007/SPIE-EI-2007-Robust-Hashing-paper.ps.gz}, url2 = {http://vision.unige.ch/publications/postscript/2007/SPIE-EI-2007-Robust-Hashing-presentation.ppt.pdf} } @ARTICLE{Villan:TIFS2006, author = {Renato Vill{\'a}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Multilevel 2D Bar Codes: Towards High Capacity Storage Modules for Multimedia Security and Management}, journal = {IEEE Transactions on Information Forensics and Security}, year = {2006}, volume = {1}, pages = {405--420}, vgclass = {refpap}, vgproject = {watermarking}, number = {4}, month = {December}, abstract = {In this paper, we deal with the design of high-rate multilevel two-dimensional (2D) bar codes for the print-and-scan channel. Firstly, we introduce a framework for evaluating the performance limits of these codes by studying an inter-symbol interference (ISI) free, synchronous, and noiseless print-and-scan channel, where the input and output alphabets are finite and the printer device uses halftoning to simulate multiple gray levels. Secondly, we present a new model for the print-and-scan channel specifically adapted to the problem of communications via multilevel 2D bar codes. This model, inspired by our experimental work, assumes no ISI and perfect synchronization, but independence between the channel input and the noise is not supposed. We adapt the theory of multilevel coding with multistage decoding (MLC/MSD) to the print-and-scan channel. Finally, we present experimental results confirming the utility of our channel model, and showing that multilevel 2D bar codes using MLC/MSD can reliably achieve the high capacity storage requirements of many multimedia security and management applications.}, url = {http://vision.unige.ch/publications/postscript/2006/TIFS-multilevel-2D-barcodes.pdf}, url1 = {http://vision.unige.ch/publications/postscript/2006/TIFS-multilevel-2D-barcodes.ps.gz} } @INPROCEEDINGS{Villan:SPIE2005, author = {Renato Vill{\'a}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Multilevel 2D Bar Codes: Towards High Capacity Storage Modules for Multimedia Security and Management}, booktitle = {Proceedings of {SPIE-IS{\&}T} Electronic Imaging 2005, Security, Steganography, and Watermarking of Multimedia Contents VII}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, volume = {5681}, pages = {453--464}, address = {San Jose, USA}, month = {January 16--20}, abstract = {In this paper, we deal with the design of high-rate multilevel two-dimensional (2D) bar codes for the print-and-scan channel. Firstly, we derive an upper bound on the maximum achievable rate of these codes by studying an inter-symbol interference (ISI) free, perfectly synchronized, and noiseless print-and-scan channel, in which the printer device uses halftoning to simulate multiple gray levels. Secondly, we briefly review three state-of-the-art coded modulation techniques for the additive white Gaussian noise channel (AWGN) in the high signal-to-noise (SNR) ratio regime, namely, multilevel coding with multistage decoding (MLC/MSD), multilevel coding with parallel independent decoding (MLC/PID), and bit-interleaved coded modulation (BICM). Thirdly, we present a new model of the print-and-scan channel specifically adapted to the multilevel 2D bar code application. This model, inspired by our experimental work, assumes no ISI and perfect synchronization, but independence between the channel input and the noise is not supposed. We study the problem of finding the information capacity of our channel model and extend the theory of MLC/MSD to this type of channels. Finally, we present experimental results confirming the validity of our channel model, and showing that multilevel 2D bar codes using MLC/MSD can reliably achieve the high-rate storage requirements of many multimedia security and data management applications.}, url = {http://vision.unige.ch/publications/postscript/2005/VillanVoloshynovskiyKovalPun_SPIE2005.pdf}, url1 = {http://vision.unige.ch/publications/postscript/2005/VillanVoloshynovskiyKovalPun_SPIE2005.ps.gz}, url2 = {http://vision.unige.ch/publications/postscript/2005/VillanVoloshynovskiyKovalPun_SPIE2005.ppt.pdf} } @INPROCEEDINGS{Villan:SPIE2006:TE, author = {R. Vill{\'a}n and Sviatoslav Voloshynovskiy and Oleksiy Koval and J.E. Vila-Forc{\'e}n and Emre Topak and Fr\'{e}d\'{e}ric Deguillaume and Y. Rytsar and Thierry Pun}, title = {Text Data-Hiding for Digital and Printed Documents: Theoretical and Practical Considerations}, booktitle = {Proceedings of {SPIE-IS{\&}T} Electronic Imaging 2006, Security, Steganography, and Watermarking of Multimedia Contents VIII}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 15--19}, abstract = {In this paper, we propose a new theoretical framework for the data-hiding problem of digital and printed text documents. We explain how this problem can be seen as an instance of the well-known Gel'fand-Pinsker problem. The main idea for this interpretation is to consider a text character as a data structure consisting of multiple quantifiable features such as shape, position, orientation, size, color, etc. We also introduce color quantization, a new semi-fragile text data-hiding method that is fully automatable, has high information embedding rate, and can be applied to both digital and printed text documents. The main idea of this method is to quantize the color or luminance intensity of each character in such a manner that the human visual system is not able to distinguish between the original and quantized characters, but it can be easily performed by a specialized reader machine. We also describe halftone quantization, a related method that applies mainly to printed text documents. Since these methods may not be completely robust to printing and scanning, an outer coding layer is proposed to solve this issue. Finally, we describe a practical implementation of the color quantization method and present experimental results for comparison with other existing methods.}, url = {http://vision.unige.ch/publications/postscript/2006/SPIE-EI-2006-Text-Data-Hiding-paper.pdf}, url1 = {http://vision.unige.ch/publications/postscript/2006/SPIE-EI-2006-Text-Data-Hiding-paper.ps.gz}, url2 = {http://vision.unige.ch/publications/postscript/2006/SPIE-EI-2006-Text-Data-Hiding-presentation.ppt.pdf} } @MISC{Svolos:KAIST2002:RDW, vgclass = {fullconf}, vgproject = {watermarking}, author = {Sviatoslav Voloshynovskiy}, title = {Robust digital watermarking: state-of-the-art and benchmarking}, howpublished = {KAIST and ETRI seminar) - (Invited lecture)}, month = {February}, year = {2002}, note = {Korean Advanced Institute of Science and Technology} } @ARTICLE{VG:VAH2000, author = {Sviatoslav Voloshynovskiy and A. Allen and Z. Hrytskiv}, title = {Robust edge-preserving image restoration in the presence of non-Gaussian noise}, journal = {Electronics Letters}, year = {2000}, vgclass = {refpap}, vgproject = {watermarking}, note = {(accepted)} } @ARTICLE{Svolos:VG:ImageGraphics, author = {Sviatoslav Voloshynovskiy and Fr\'{e}d\'{e}ric Deguillaume and Oleksiy Koval and Thierry Pun}, title = {Information-theoretic data-hiding: Recent achievements and open problems}, journal = {International Journal of Image and Graphics}, year = {2005}, volume = {5}, pages = {1--31}, vgclass = {refpap}, vgproject = {watermarking}, number = {1}, url = {http://vision.unige.ch/publications/postscript/2005/VoloshynovskiyDeuillaumeKovalPun_ImageGraphics2005.pdf} } @INPROCEEDINGS{VG:TELSIKS2003, author = {Sviatoslav Voloshynovskiy and Fr{\'e}d{\'e}ric Deguillaume and Oleksiy Koval and Thierry Pun}, title = {Information-Theoretic Data-Hiding for Public Network Security, Services Control and Secure Communications}, booktitle = {6th International Conference on Telecommunications in Modern Satellite, Cable and Broadcasting Services (TELSIKS) 2003}, year = {2003}, vgclass = {refpap}, vgproject = {watermarking}, address = {Nis, Yugoslavia}, month = {October 1-4}, url = {http://vision.unige.ch/publications/postscript/2003/Voloshynovskiy-Deguillaume-Koval-Pun_Telsisks2003_03.07.07_Web.ps}, url1 = {http://vision.unige.ch/publications/postscript/2003/Voloshynovskiy-Deguillaume-Koval-Pun_Telsisks2003_03.07.07_Web.pdf} } @ARTICLE{VG:VDKP2003b, author = {Sviatoslav Voloshynovskiy and Fr{\'e}d{\'e}ric Deguillaume and Oleksiy Koval and Thierry Pun}, title = { Robust digital watermarking with channel state estimation: part I Approaching theoretical capacity }, journal = {Signal Processing}, year = {2003}, vgclass = {refpap}, vgproject = {watermarking}, note = {submitted}, url = { }, url1 = { } } @ARTICLE{VG:VDKP2003c, author = {Sviatoslav Voloshynovskiy and Fr{\'e}d{\'e}ric Deguillaume and Oleksiy Koval and Thierry Pun}, title = { Robust digital watermarking with channel state estimation: part II Applied robust watermarking}, journal = {Signal Processing}, year = {2003}, vgclass = {refpap}, vgproject = {watermarking}, note = {submitted}, url = { }, url1 = { } } @MISC{VG:VDPHP2000, vgclass = {patent}, vgproject = {watermarking}, author = { Sviatoslav Voloshynovskiy and Fr{\'e}d{\'e}ric Deguillaume and Shelby Pereira and Alexander Herrigel and Thierry Pun}, title = { Method for adaptive digital watermarking robust against geometric transforms }, howpublished = { European Patent Application PCT/IB00/01089}, month = {filed August 3, 2000}, year = {2000} } @INPROCEEDINGS{VG:VDP2001, author = {Sviatoslav Voloshynovskiy and Fr{\'e}d{\'e}ric Deguillaume and Shelby Pereira and Thierry Pun}, title = {Optimal adaptive diversity watermarking with channel state estimation}, booktitle = {SPIE Photonics West, Electronic Imaging 2001, Security and Watermarking of Multimedia Contents III}, year = {2001}, vgclass = {refpap}, vgproject = {watermarking}, number = {paper 4314-74}, address = {San Jose, CA, USA}, month = {January 21-26}, note = {. W. Wong, E. J. Delp, Eds.}, url = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyDeguillaumePereiraPun_spie2001.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyDeguillaumePereiraPun_spie2001.pdf} } @INPROCEEDINGS{VG:VDP2001a, author = {Svyatoslav Voloshynovskiy and Fr{\'e}d{\'e}ric Deguillaume and Thierry Pun}, title = {Multibit Digital Watermarking Robust Against Local Nonlinear Geometrical Distortions}, booktitle = {{IEEE} International Conference on Image Processing, {ICIP2001}}, year = {2001}, vgclass = {refpap}, vgproject = {watermarking}, pages = {999--1002}, address = {Thessaloniki, Greece}, abstract = {This paper presents an efficient method for the estimation and recovering from nonlinear or local geometrical distortions, such as the random bending attack and restricted projective transforms. The distortions are modeled as a set of local affine transforms, the watermark being repeatedly allocated into small blocks in order to ensure its locality. The estimation of the affine transform parameters is formulated as a robust penalized Maximum Likelihood (ML) problem, which is suitable for the local level as well as for global distortions. Results with the Stirmark benchmark confirm the high robustness of the proposed method and show its state-of-the-art performance.}, url = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyDeguillaumePun_ICIP2001.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyDeguillaumePun_ICIP2001.pdf} } @MISC{VG:VDP2001b, vgclass = {patent}, vgproject = {watermarking}, author = {Sviatoslav Voloshynovskiy and Fr{\'e}d{\'e}ric Deguillaume and Thierry Pun}, title = {Method for Digital Watermarking Robust Against Local and Global Geometrical Distortions and Projective Transforms}, howpublished = {U.S. Patent Application}, year = {2001} } @INPROCEEDINGS{VG:VDP2000, author = {Sviatoslav Voloshynovskiy and Fr{\'e}d{\'e}ric Deguillaume and Thierry Pun}, title = {Content adaptive watermarking based on a stochastic multiresolution image modeling}, booktitle = {Tenth European Signal Processing Conference (EUSIPCO'2000)}, year = {2000}, vgclass = {refpap}, vgproject = {watermarking}, address = {Tampere, Finland}, month = {sep 5--8}, url = { http://vision.unige.ch/publications/postscript/2000/VoloshynovskiyDeguillaumePun_es2000.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2000/VoloshynovskiyDeguillaumePun_es2000.pdf} } @MISC{Svolos:TCW2002:RWIA, vgclass = {fullconf}, vgproject = {watermarking}, author = {Sviatoslav Voloshynovskiy and Alexander Herrigel}, title = { Robustness of Watermarks and Intentional Attacks }, howpublished = { TCW Workshop on Digital Watermarking and Digital Rights Management) - (Invited presentation)}, month = {September}, year = {2002}, note = { Fraunhofer IGD, Darmstadt, Germany } } @INPROCEEDINGS{VG:VHB1999, author = {Sviatoslav Voloshynovskiy and Alexander Herrigel and Nazanin Baumg{\"a}rtner and Thierry Pun}, title = {A stochastic approach to content adaptive digital image watermarking}, booktitle = {International Workshop on Information Hiding}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, volume = {LNCS 1768}, series = {Lecture Notes in Computer Science}, pages = {212--236}, address = {Dresden, Germany}, month = {29~September~--1~October}, publisher = {Springer Verlag}, abstract = {This paper presents a new stochastic approach which can be applied with different watermark techniques. The approach is based on the computation of a Noise Visibility Function (NVF) that characterizes the local image properties, identifying textured and edge regions where the mark should be more strongly embedded. We present precise formulas for the NVF which enable a fast computation during the watermark encoding and decoding process. In order to determine the optimal NVF, we first consider the watermark as noise. Using a classical MAP image denoising approach, we show how to estimate the ``noise''. This leads to a general formulation for a texture masking function, that allows us to determine the optimal watermark locations and strength for the watermark embedding stage. We examine two such NVFs, based on either a non-stationary Gaussian model of the image, or a stationary Generalized Gaussian model. We show that the problem of the watermark estimation is equivalent to image denoising and derive content adaptive criteria. Results show that watermark visibility is noticeably decreased, while at the same time enhancing the energy of the watermark.}, url = { http://vision.unige.ch/publications/postscript/99/VoloshynovskiyHerrigelBaumgaertnerPun_wih99.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/99/VoloshynovskiyHerrigelBaumgaertnerPun_wih99.pdf} } @INPROCEEDINGS{VG:VHJ1999, author = {Sviatoslav Voloshynovskiy and Alexander Herrigel and Fr{\'e}d{\'e}ric Jordan and Nazanin Baumg{\"a}rtner and Thierry Pun}, title = {A noise removal attack for watermarked images}, booktitle = {Multimedia and Security Workshop}, year = {1999}, vgclass = {refpap}, vgproject = {watermarking}, editor = {J. Dittmann and K. Nahrstedt and P. Wohlmacher}, address = {Orlando, Florida, USA}, month = {30--31~October}, note = {(at the 7th ACM Multimedia Conference (Multimedia 99))} } @INPROCEEDINGS{VG:VHP2001, author = {Sviatoslav Voloshynovskiy and Alexander Herrigel and Thierry Pun}, title = {Blur/deblur attack against document protection systems based on digital watermarking}, booktitle = {Information Hiding Workshop}, year = {2001}, vgclass = {refpap}, vgproject = {watermarking}, address = {Pittsburgh, PA, USA}, month = {apr}, abstract = {A growing concern emerges regarding the possibility of coun- terfeiting currencies using digital imaging technologies. In order to help developing resistance against this new type of fraud, this paper presents possible attacking scenarios against supposedly sophisticated document protection systems based on digital watermarking. These new attacks, which would allow even an average counterfeiter to reproduce banknotes or passports created using systems with built-in watermark detector.}, url = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyHerrigelPun_ihw2001.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyHerrigelPun_ihw2001.ps.gz} } @INPROCEEDINGS{VG:VHRP2002, author = {Sviatoslav Voloshynovskiy and Alexander Herrigel and Yuriy Rytsar and Thierry Pun}, title = {{StegoWall}: Blind Statistical Detection of Hidden Data}, booktitle = {Proceedings of {SPIE} Photonics West, Electronic Imaging 2002, Security and Watermarking of Multimedia Contents {IV}}, year = {2002}, vgclass = {refpap}, vgproject = {watermarking}, editor = {E.J. Delp and P. W. Wong}, address = {San Jose, USA}, url = {http://vision.unige.ch/publications/postscript/2002/VoloshynovskiyHerrigelRytsarPun_SPIE2002.pdf} } @INPROCEEDINGS{Koval:IWMSP:2007b, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Fokko Beekhof and Thierry Pun}, title = {Robust perceptual hashing as classification problem: decision-theoretic and practical considerations}, booktitle = {Proceedings of the IEEE 2007 International Workshop on Multimedia Signal Processing}, year = {2007}, vgclass = {refpap}, vgproject = {watermarking}, address = {Chania, Crete, Greece}, month = {October 1--3} } @INPROCEEDINGS{Voloshynovskiy:NATO2005, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Fr\'{e}d\'{e}ric Deguillaume and Thierry Pun}, title = {Multimedia Security: open problems and solutions}, booktitle = {In Proceedings of NATO - Advanced Study Institute: Securitty Through Science Program, Nork, Yerevan, Armenia, 1-12 October, 2005}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Yerevan, Armenia}, month = {October 1-12}, url = {http://vision.unige.ch/publications/postscript/2005/Voloshynovskiy_Koval_Deguillaume_Pun_Nato_Armenia_2005.pdf} } @INPROCEEDINGS{VG:SPIE2004b, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Fr\'{e}d\'{e}ric Deguillaume and Thierry Pun}, title = {Visual communications with side information via distributed printing channels: extended multimedia and security perspectives}, booktitle = {Proceedings of SPIE Photonics West, Electronic Imaging 2004, Multimedia Processing and Applications}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 18-22}, url = {http://vision.unige.ch/publications/postscript/2004/VoloshynovskiyKovalDeguillaumePun.spie.printing.2004.pdf} } @INPROCEEDINGS{VG:VKDP2003b, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Fr{\'e}d{\'e}ric Deguillaume and Thierry Pun}, title = { Data hiding capacity-security analysis for real images based on stochastic non-stationary geometrical models }, booktitle = {SPIE Photonics West, Electronic Imaging 2003, Security and Watermarking of Multimedia Contents V}, year = {2003}, vgclass = {refpap}, vgproject = {watermarking}, address = {Santa Clara, CA, USA}, month = {January 20-24}, url = {http://vision.unige.ch/publications/postscript/2003/VoloshynovskiyKovalDeguillaumePun_SPIE2003.ps.gz}, url1 = {http://vision.unige.ch/publications/postscript/2003/VoloshynovskiyKovalDeguillaumePun_SPIE2003.pdf} } @ARTICLE{Volosynovskiy:2005:EPC, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and M. Kivanc Mihcak and Thierry Pun}, title = {The Edge Process Model and Its Application to Information Hiding Capacity Analysis}, journal = {IEEE Trans. on Signal Processing}, year = {2006}, volume = {54}, pages = {1813--1825}, vgclass = {refpap}, vgproject = {watermarking}, number = {5}, month = {May}, url = {http://vision.unige.ch/publications/postscript/2006/ieee-edge-process.pdf} } @MISC{Voloshynovskiy:2006:CVG, vgclass = {patent}, vgproject = {watermarking}, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {BRANDS PROTECTION AND PRODUCT AUTHENTICATION USING PORTABLE DEVICES}, howpublished = {US Patent Application}, year = {2006}, note = {(pending)} } @ARTICLE{Svolos:SP2005:IDEP, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Image denoising based on the edge-process model}, journal = {Signal Processing}, year = {2005}, volume = {85}, pages = {1950--1969}, vgclass = {refpap}, vgproject = {watermarking}, number = {10}, month = {October}, url = {http://vision.unige.ch/publications/postscript/2005/VoloshynovskiyKovalPun_SP2005.pdf} } @INPROCEEDINGS{VG:VKP2003a, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Thierry Pun}, title = {Wavelet-based image denoising using non-stationary stochastic geometrical image priors}, booktitle = {SPIE Photonics West, Electronic Imaging 2003, Image and Video Communications and Processing V}, year = {2003}, vgclass = {refpap}, vgproject = {watermarking}, address = {Santa Clara, CA, USA}, month = {January 20-24}, url = {http://vision.unige.ch/publications/postscript/2003/VoloshynovskiyKovalPun_SPIE2003.ps.gz}, url1 = {http://vision.unige.ch/publications/postscript/2003/VoloshynovskiyKovalPun_SPIE2003.pdf} } @ARTICLE{Svolos:2005:PSI, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Fernando P{\'e}rez-Gonz{\'a}lez and Kivanc Mihcak and Thierry Pun}, title = {Data-hiding with host state at the encoder and partial side information at the decoder}, year = {2004}, vgclass = {refpap}, vgproject = {watermarking}, month = {June}, note = {(preprint)}, url = {http://vision.unige.ch/publications/postscript/2005/VoloshynovskiyKovalPerezGonzalezMihcakPun_SP2005.pdf} } @INPROCEEDINGS{Svolos:EUSIPCO2005, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and F. P{\'e}rez-Gonz{\'a}lez and M. Kivanc Mihcak and J.E. Vila-Forc{\'e}n and Thierry Pun}, title = {Data-hiding with partially available side information}, booktitle = { {EUSIPCO} 2005, 13th European Signal Processing Conference}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Antalya}, month = {September 4-8}, url = {http://vision.unige.ch/publications/postscript/2005/VoloshynovskiyKovalPerezGonzalezMihcakVilaForcenPun_EUSIPCO2005.pdf} } @INPROCEEDINGS{Voloshynovskiy:ACM2006, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Emre Topak and J.E. Vila Forcen and Thierry Pun}, title = {On reversibility of random binning based data-hiding techniques: security perspectives}, booktitle = {ACM Multimedia and Security Workshop 2006}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {Geneva, Switzerland}, month = {September 26-27}, url = {http://vision.unige.ch/publications/postscript/2006/mmsec167-topak.ps} } @INPROCEEDINGS{Voloshynovskiy:WIC2006:Voloshynovskiy_wic2006, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Emre Topak and Thierry Pun}, title = {Message Communications And Channel State Estimation For State Dependent Channels}, booktitle = {Proceedings of 27-th Symposium on information theory in the Benelux}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {Noordwijk, The Netherlands}, month = { June 8-9, 2006, }, url = {http://vision.unige.ch/publications/postscript/2006/Voloshynovskiy_wic2006.pdf} } @INPROCEEDINGS{Voloshynovskiy:2005:RRB, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Emre Topak and J.E. Vila-Forc{\'e}n and P. Comesana and Thierry Pun}, title = {On reversibility of random binning techniques: multimedia perspectives}, booktitle = { 9th IFIP TC-6 TC-11 Conference on Communications and Multimedia Security (CMS 2005)}, year = {2005}, vgclass = {refpap}, vgproject = {watermarking}, address = {Salzburg, Austria}, month = {September}, url = {http://vision.unige.ch/publications/postscript/2005/cms2005.pdf}, url1 = {http://vision.unige.ch/publications/postscript/2005/cms2005.ps} } @ARTICLE{Voloshynovskiy:2007:SPIE-Biometric, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and Renato~Vill{\'a}n and Fokko Beekhof and Thierry Pun}, title = {Authentication of Biometric Identification Documents via Mobile Devices}, journal = {Journal of Electronic Imaging}, url = {http://cvml.unige.ch/publications/postscript/2008/ei2008.pdf}, year = {2008}, note={(accepted)}, vgclass = {refpap}, vgproject = {watermarking} } @INPROCEEDINGS{Svolos:SPIE2006:DA, author = {Sviatoslav Voloshynovskiy and Oleksiy Koval and R. Vill{\'a}n and Emre Topak and Jose Emilio Vila-Forc{\'e}n and Fr\'{e}d\'{e}ric Deguillaume and Yuriy Rytsar and Thierry Pun}, title = {Information-Theoretic Analysis of Electronic and Printed Document Authentication}, booktitle = {Proceedings of {SPIE-IS{\&}T} Electronic Imaging 2006, Security, Steganography, and Watermarking of Multimedia Contents VIII}, year = {2006}, vgclass = {refpap}, vgproject = {watermarking}, address = {San Jose, USA}, month = {January 15--19}, abstract = {In this paper we consider the problem of document authentication in electronic and printed forms. We formulate this problem from the information-theoretic perspectives and present the joint source-channel coding theorems showing the performance limits in such protocols. We analyze the security of document authentication methods and present the optimal attacking strategies with corresponding complexity estimates that, contrarily to the existing studies, crucially rely on the information leaked by the authentication protocol. Finally, we present the results of experimental validation of the developed concept that justifies the practical efficiency of the elaborated framework.}, url = {http://vision.unige.ch/publications/postscript/2006/VoloshynovskiyKovalVillanTopakVilaDeguillaumeRytsarPun_SPIE06_AuthTextDoc.pdf}, url2 = {http://vision.unige.ch/publications/postscript/2006/SPIE-EI-2006-Text-Authentication-presentation.ppt.pdf} } @INPROCEEDINGS{VG:VPH2000, author = {Sviatoslav Voloshynovskiy and Shelby Pereira and Alexander Herrigel and Nazanin Baumg{\"a}rtner and Thierry Pun}, title = {Generalized watermark attack based on watermark estimation and perceptual remodulation}, booktitle = {IS\&T/SPIE's 12th Annual Symposium, Electronic Imaging 2000: Security and Watermarking of Multimedia Content II}, year = {2000}, vgclass = {refpap}, vgproject = {watermarking}, editor = {Wah Wong, Ping and Edward J. Delp}, volume = {3971}, series = {SPIE Proceedings}, address = {San Jose, California USA}, month = {23--28jan}, note = {(Paper EI 3971-34) - slides}, abstract = {Digital image watermarking has become a popular technique for authentication and copyright protection. For verifying the security and robustness of watermarking algorithms, specific attacks have to be applied to test the proposed algorithms. In contrast to the known Stirmark attack, which degrades the quality of the image while destroying the watermark, this paper presents a new approach which is based on the estimation of a watermark and the exploitation of the properties of Human Visual System (HVS). The new attack satisfies two important requirements. First, image quality after the attack as perceived by the HVS is not worse than the quality of the stego image. Secondly, the attack uses all available prior information about the watermark and cover image statistics to perform the best watermark removal or damage. The proposed attack is based on a stochastic formulation of the watermark removal problem considering the embedded watermark as additive noise with some probability distribution. The attack scheme consists of two main stages: watermark estimation based a Maximum a Posteriori (MAP) approach and watermark alteration through addition of the noise to the filtered image taking into account the statistics of the embedded watermark and exploiting HVS characteristics. Experiments on a number of real world and computer generated images show the high efficiency of the proposed attack against several known academic and commercial methods: the watermark is completely destroyed in all tested images without altering the image quality. The approach can be used against watermark embedding schemes that operate either in coordinate domain, or transform domains like Fourier, DCT or wavelet.}, url = { http://vision.unige.ch/publications/postscript/2000/VoloshynovskiyPereiraHerrigelBaumgartnerPun_spie2000.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2000/VoloshynovskiyPereiraHerrigelBaumgartnerPun-slides-spie2000.pdf} } @ARTICLE{VG:VPI2001, author = {Sviatoslav Voloshynovskiy and Shelby Pereira and Victor Iquise and Thierry Pun}, title = {Attack modelling: Towards a second generation benchmark}, journal = {Signal Processing}, year = {2001}, volume = {81}, pages = {1177-1214}, vgclass = {refpap}, vgproject = {watermarking}, number = {6}, month = {June}, note = {Special Issue: Information Theoretic Issues in Digital Watermarking, 2001. V. Cappellini, M. Barni, F. Bartolini, Eds.}, abstract = {Digital image watermarking techniques for copyright protection have become increasingly robust. The best algorithms perform well against the now standard benchmark tests included in the Stirmark package. However the stirmark tests are limited since in general they do not properly model the watermarking process and consequently are limited in their potential to removing the best watermarks. Here we propose a stochastic formulation of watermarking attacks using an estimationbased concept. The proposed attacks consist of two main stages: a) watermark or cover data estimation; b) modification of stego data aiming at disrupting the watermark detection and of resolving copyrights, taking into account the statistics of the embedded watermark and exploits features of human visual system. In the second part of the paper we propose a "second generation benchmark". We follow the model of the Stirmark benchmark and propose the 6 following categories of tests: denoising attacks and wavelet compression, watermark copy attack, synchronization removal, denoising/compression with following perceptual remodulation, denoising and random bending. Our results indicate that even though some algorithms perform well against the Stirmark benchmark, almost all algorithms perform poorly against our benchmark. This indicates that much work remains to be done before claims about "robust" watermarks can be made. We also propose a new method of evaluating image quality based on the Watson metric which overcomes the limitations of the PSNR.}, url = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyPereiraIsquizPun_SP2001.ps.gz}, url1 = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyPereiraIsquizPun_SP2001.pdf} } @TECHREPORT{VG:VPI2000, author = {Sviatoslav Voloshynovskiy and Shelby Pereira and Victor Iquise and Thierry Pun}, title = {Attack Modelling: Towards a Second Generation Watermarking Benchmark}, institution = {Computer Vision Group, Computing Centre, University of Geneva}, year = {2000}, vgclass = {report}, vgproject = {watermarking}, number = {00.05}, address = {rue G\'en\'eral Dufour, 24, CH-1211 Gen\`eve, Switzerland}, month = {may}, abstract = {Digital image watermarking techniques for copyright protection have become increasingly robust. The best algorithms perform well against the now standard benchmark tests included in the Stirmark package. However the stirmark tests are limited since in general they do not properly model the watermarking process and consequently are limited in their potential to removing the best watermarks. Here we propose a stochastic formulation of the watermark removal problem, considering the embedded watermark as additive noise with some probability distribution. The attack scheme consists of two main stages: a) watermark estimation and partial removal by a filtering based on a Maximum a Posteriori (MAP) approach; b) watermark alteration and hiding through addition of noise to the filtered image, taking into account the statistics of the embedded watermark and exploiting HVS characteristics. In a second stage we propose a ``second generation benchmark''. We follow the model of the Stirmark tests and propose the 6 following categories of tests: denoising attacks, wavelet compression, denoising/compression with following perceptual remodulation, template/ACF (synchronization) removal, denoising and random banding, the watermark copy attack. Our results indicate that even though some algorithms perform well against the stirmark benchmark, all algorithms perform poorly against our benchmark. This indicates that much work remains to be done before claims about ``robust'' watermarks can be made. We also propose a new method of evaluating image quality based on the Watson metric which overcomes the limitations of PSNR.} } @INPROCEEDINGS{VG:VPP1999, author = {Sviatoslav Voloshynovskiy and Shelby Pereira and Thierry Pun}, title = {Watermark attacks}, booktitle = {Erlangen Watermarking Workshop}, year = {1999}, vgclass = {fullconf}, vgproject = {watermarking}, address = {Erlangen, Germany}, month = {5--6~October}, note = {(invited presentation)}, url = { http://vision.unige.ch/publications/postscript/99/VoloshynovskiyPereiraPun_eww99.pdf} } @ARTICLE{VG:VPP2001, author = {Sviatoslav Voloshynovskiy and Shelby Pereira and Thierry Pun and J. Eggers and J. Su}, title = {Attacks on Digital Watermarks: Classification, Estimation-based Attacks and Benchmarks}, journal = {IEEE Communications Magazine (Special Issue on Digital watermarking for copyright protection: a communications perspective)}, year = {2001}, volume = {39}, pages = {118-127}, vgclass = {refpap}, vgproject = {watermarking}, number = {8}, note = {M. Barni, F. Bartolini, I.J. Cox, J. Hernandez, F. P\'erez-Gonz\'alez, Guest Eds. Invited paper.}, abstract = {Watermarking is a potential method for protection of ownership rights on digital audio, image and video data. Benchmarks are used to evaluate the performance of different watermarking algorithms. For image watermarking, the Stirmark package is the most popular benchmark, and the best current algorithms perform well against it. However, results obtained by the Stirmark benchmark have to be handled carefully since Stirmark does not properly model the watermarking process and consequently is limited in its potential for impairing sophisticated image watermarking schemes. In this context, the goal of this article is threefold. First, we give an overview of the current attacking methods. Second, we describe attacks exploiting knowledge about the statistics of the original data and the embedded watermark. We propose a stochastic formulation of estimation-based attacks. Such attacks consist of two main stages: a) watermark estimation; b) exploitation of the estimated watermark to trick watermark detection or create ownership ambiguity. The full strength of estimation-based attacks can be achieved by introducing additional noise, where the attacker tries to combine the estimated watermark and the additive noise to impair watermark communication as much as possible while fulfilling a quality constraint on the attacked data. With a sophisticated quality constraint it is also possible to exploit human perception, e.g., the human auditory system in case of audio watermarks and the human visual system (HVS) in case of image and video watermarks. Third, we discuss the current status of image watermarking benchmarks. We briefly present Fabien Petitcolas' Stirmark benchmarking tool [1]. Next, we consider the benchmark proposed by the University of Geneva Vision Group that contains more deliberate attacks. Finally, we summerize the current work of the European Certimark project, whose goal is to accelerate efforts from a number of research groups and companies in order to produce an improved ensemble of benchmarking tools.}, url = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyPereiraPunEggersSun_IEEEComMag2001.pdf}, url1 = { http://vision.unige.ch/publications/postscript/2001/VoloshynovskiyPereiraPunEggersSun_IEEEComMag2001.ps.gz} } @INPROCEEDINGS{VG:VP2002, author = { Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Capacity-security analysis of data hiding technologies}, booktitle = {Proceedings of IEEE International Conference on Multimedia and Expo (ICME2002)}, year = {2002}, vgclass = {refpap}, vgproject = {watermarking}, address = {Lausanne, Switzerland}, month = {August 26-29}, url = {http://vision.unige.ch/publications/postscript/2002/VoloshynovskiyPun_ICME2002.pdf} } @INPROCEEDINGS{VG:VoP2001, author = {Sviatoslav Voloshynovskiy and Thierry Pun}, title = {Stochastic Digital Image Watermarking}, booktitle = {{IEEE/ISSPA} {ISSPA} 2001, 6th Int. Symposium on Signal Processing and its Applications}, year = {2001}, vgclass = {fullconf}, vgproject = {watermarking}, address = {Kuala-Lumpur, Malaysia}, note = {Thierry Pun, invited plenary lecture} } @MISC{VG:Wal1993, vgclass = {licence}, vgproject = {unspecified}, author = {Daniel Walther}, title = {R\'ealisation d'un logiciel d'analyse quantitative d'images bas\'e sur la morphologie math\'ematique}, howpublished = {Licence thesis (B.Sc.), University of Geneva}, month = {January}, year = {1993} } @INPROCEEDINGS{VG:WPR1988, author = {D. Weber and Thierry Pun and C. Roch and C. Rosu and Christian Pellegrini}, title = {{M}\'elanie: {M}edical {E}lectrophoresis {A}nalysis, {I}nteractive {E}xpert {S}ystem}, booktitle = {{SGAICO} - Swiss Group of {AI} and Cognitive Sciences Annual Conference on Artificial Intelligence in Manufacturing, Assembly, and Robotics, Bern}, year = {1988}, vgclass = {fullconf}, vgproject = {unspecified}, month = {October} } @INPROCEEDINGS{VG:OTM03, author = {Y.Rytsar and S.Voloshynovskiy and T.Pun}, title = {Metadata Representation for Semantic-Based Multimedia Security and Management}, booktitle = {On The Move to Meaningful Internet Systems 2003: OTM 2003 Workshops}, year = {2003}, vgclass = {refpap}, vgproject = {watermarking}, volume = {2889 / 2003}, series = {Lecture Notes in Computer Science}, pages = {769--778}, address = {Catania, Italy}, month = {November}, publisher = {Springer Berlin / Heidelberg}, url = {http://vision.unige.ch/publications/postscript/2003/WMS2003_MetadataRepresentationForSemanticBasedMultiMediaSecurityAndManagement.pdf} } @MISC{VG:Zan1994, vgclass = {diploma}, vgproject = {unspecified}, author = {Sandra Zanella}, title = {Outils de segmentation et de mesure du volume pour l'analyse d'images m\'edicales multimodalit\'e}, howpublished = {Diploma thesis, University of Geneva}, month = {June}, year = {1994}, note = {(Travail r\'ealis\'e \`a l'Unit\'e d'imagerie num\'erique, H\^opital cantonal universitaire, Y. Ligier, O. Ratib)} } @INPROCEEDINGS{VG:ZBN1995, author = {T. Zimmerman and C. Baur and E. Natonek and Thierry Pun and Marc Lefebvre}, title = {The {P}otato {O}peration: robotics apparatus using active vision for automatic potato pulp sampling}, booktitle = {4th International Conference on Automation, Robotics and Artficial Intelligence Applied to Analytical Chemistry and Laboratory Medicine, Montreux, Switzerland}, year = {1995}, vgclass = {fullconf}, vgproject = {unspecified}, month = {February} }