Approche interactive de la recherche d'images par le contenu

Cet article traite du probleme de l'indexation et de la recherche d'images par le contenu dans les bases generalistes. Le fosse semantique qui separe l'information bas niveau extraite de l'image et la requete semantique de l'utilisateur est la limite majeure rencontree dans le domaine. L'aspect indexation est aborde sous l'angle de l'optimisation hors ligne de la taille et de la pertinence des signatures calculees sur l'image. Nous proposons une strategie de recherche interactive originale permettant l'exploration de la base. Le processus repose sur la construction d'une requete multiple et sur une competition de modeles pour le raffinement de la mesure de similarite. Une evaluation des performances est realisee sur deux bases generalistes afin d'illustrer et de valider notre approche.

[1]  Murat Kunt,et al.  Content-based retrieval from image databases: current solutions and future directions , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[2]  Aleksandra Mojsilovic,et al.  Capturing image semantics with low-level descriptors , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[3]  Matthieu Cord,et al.  Long-term similarity learning in content-based image retrieval , 2002, Proceedings. International Conference on Image Processing.

[4]  Alberto Del Bimbo,et al.  Visual information retrieval , 1999 .

[5]  Ingemar J. Cox,et al.  The Bayesian image retrieval system, PicHunter: theory, implementation, and psychophysical experiments , 2000, IEEE Trans. Image Process..

[6]  Sylvie Philipp-Foliguet,et al.  Fuzzy segmentation of color images and indexing of fuzzy regions , 2002, CGIV.

[7]  Marcel Worring,et al.  Filter Image Browsing - Exploiting Interaction in Image Retrieval , 1999, VISUAL.

[8]  Alberto Del Bimbo,et al.  Visual Querying By Color Perceptive Regions , 1998, Pattern Recognit..

[9]  Ben A. M. Schouten,et al.  Show Me What You Mean! Pariss: A CBIR-Interface that Learns by Example , 2000, VISUAL.

[10]  John R. Smith,et al.  Image Classification and Querying Using Composite Region Templates , 1999, Comput. Vis. Image Underst..

[11]  Gianluigi CIOCCA.  COLOR IN DATABASES: INDEXATION AND SIMILARITY , 2000 .

[12]  Thomas S. Huang,et al.  Image retrieval with relevance feedback: from heuristic weight adjustment to optimal learning methods , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[13]  B. S. Manjunath,et al.  Image indexing using a texture dictionary , 1995, Other Conferences.

[14]  Raimondo Schettini,et al.  Color-based image retrieval using spatial-chromatic histograms , 2001, Image Vis. Comput..

[15]  Nuno Vasconcelos,et al.  Bayesian models for visual information retrieval , 2000 .

[16]  Michael J. Swain,et al.  The capacity of color histogram indexing , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Gerard Salton,et al.  The SMART Retrieval System—Experiments in Automatic Document Processing , 1971 .

[18]  Donald Geman,et al.  A Stochastic Feedback Model for Image Retrieval , 1999 .

[19]  Jean-Michel Jolion,et al.  Image indexation and content based search using pre-attentive similarities , 2000, RIAO.

[20]  Chahab Nastar,et al.  Relevance feedback and category search in image databases , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[21]  Shih-Fu Chang,et al.  VisualSEEk: a fully automated content-based image query system , 1997, MULTIMEDIA '96.

[22]  Bernard Chalmond.  Eléments de modélisation pour l'analyse d'images , 2000 .

[23]  Bruce E. Hajek,et al.  Cooling Schedules for Optimal Annealing , 1988, Math. Oper. Res..

[24]  Joshua R. Smith,et al.  Image retrieval evaluation , 1998, Proceedings. IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173).

[25]  Leonidas J. Guibas,et al.  A metric for distributions with applications to image databases , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).