Un modèle de représentation d'images fixes ? base de graphes et instanciation automatique de sa configuration squelettique

In this article, we propose a new model of images representation. This work contributes to the subject of the general framework for image indexing and retrieval on the WEB .We describe a method to construct and quantify images from a semantic model, based on graphs, using a set of descriptors. This quantification of the skeleton graph is used for indexing images. In the case of images, the retrieval is mostly done by using text information (image’s name, surrounding text, annotations...) but the information related to content images (color , pattern, texture, structure...) are not considered. It is within this context that the proposed approach allows automatically to calculate for each object of the image (represented by a region) a local descriptor that allows to definite its visual and semantic characteristics. This approach therefore presents an extension of the classical model of visual graph used in information retrieval. MOTS-CLÉS : Représentation de graphes, Graphes sémantiques, Attributs d’images, Descripteurs bas niveau, Concepts sémantiques, segmentation d’images.