Méthodes d'apprentissage pour la recherche d'images par le contenu
Speaker(s) : Matthieu CORD (ENSEA - Université de Cergy-Pontoise)
The recent domain of image retrieval in large databases has induced a revision of the topics of image processing and pattern recognition. Image retrieval and extraction of visual information from image databases are useful in many applications. The processing of visual content has emerged as a key area for the application of Machine Learning (ML) techniques. In this talk, we focus on content-based retrieval strategies for large image databases. After introducing statistical approaches for data representation and classification, some aspects of interactive learning strategies and relevance feedback are explained. We present different ML techniques as active learning and concept learning that have been applied to the processing of visual information extraction and CBIR applications. As an example, the RETIN system strategy developed in the ETIS lab. is presented.
Javier.Diaz (at) nulllip6.fr