Rehaussement de la classification textuelle d ’ images par leur contenu visuel Enhancement of textual images classification using their visual content

This paper deals with the existence of a dependance between the textual indexation (a set of keywords) of an image and its visual indexation (color and shape attributes). This experience has been realized on a corpus of news photos manually indexed by keywords extracted from a hierarchically structured thesaurus. First, a reference classification of these photos has been constructed from their textual indexation (regarded as relevant), then textual and visual features characterizing these classes have been constructed. Finally, they have been used to evaluate performances of a content-based image retrieval combining textual and visual description. Results of the visual-textual classification show an improvement of 54% against classification of textual information. Finally, we discuss on an application to an image search engine.

[1]  Hervé Glotin,et al.  Enhancement of Textual Images Classification Using Segmented Visual Contents for Image Search Engine , 2005, Multimedia Tools and Applications.

[2]  C.-C. Jay Kuo,et al.  Introduction to Content‐Based Image Retrieval—Overview of Key Techniques , 2002 .

[3]  Philippe Mulhem,et al.  Un modèle vectoriel étendu de recherche d'information adapté aux images , 2002, INFORSID.

[4]  Thierry Pun,et al.  The Truth about Corel - Evaluation in Image Retrieval , 2002, CIVR.

[5]  Jacques Le Maitre,et al.  Indexation et interrogation de photos de presse décrites en MPEG-7 et stockées dans une base de données XML , 2002, Ingénierie des Systèmes d Inf..

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

[7]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[8]  G. N. Lance,et al.  A general theory of classificatory sorting strategies: II. Clustering systems , 1967, Comput. J..

[9]  Ali Khenchaf,et al.  Traitement de l'information multimédia : recherche du média image , 2002, Ingénierie des Systèmes d Inf..

[10]  Michael E. Lesk,et al.  Computer Evaluation of Indexing and Text Processing , 1968, JACM.

[11]  Gerard Salton,et al.  Term-Weighting Approaches in Automatic Text Retrieval , 1988, Inf. Process. Manag..

[12]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  David A. Forsyth,et al.  Matching Words and Pictures , 2003, J. Mach. Learn. Res..