Ontology Based Object Learning and Recognition : Application to Image Retrieval

LES AUTEURS Nicolas MAILLOT, Monique THONNAT et Céline HUDELOT

RESUME:

This paper presents a new object categorization method and shows how it can be used for image retrieval.
Our approach involves machine learning and knowledge representation techniques.
A major element of our approach is a visual concept ontology composed of several types
of concepts (spatial concepts and relations, color concepts and texture concepts).
Visual concepts contained in this ontology can be seen as an intermediate layer between domain
knowledge and image processing procedures. Our approach is composed of three phases: (1) a knowledge acquisition phase, (2)
a learning phase and (3) a categorization phase. This paper is mainly focused on phases (2) and (3).
A major issue is the symbol grounding problem which consists of linking meaningfully symbols to sensory information. We propose a solution to this difficult issue by showing how learning techniques can map numerical features to visual concepts.

Mots clé: Intelligent Information Retrieval, Vision and Image Processing, Machine Learning, Knowledge Representation and Ontology, AI in Multimedia Systems

Pour télécharger cet article, cliquez ici

BibTeX reference:

@INPROCEEDINGS{maillot04a,

 author = {Maillot, Nicolas and Thonnat, Monique and Hudelot, Celine},

 title = {Ontology Based Object Learning and Recognition : Application 
to Image Retrieval},

 booktitle = {Proceedings of 16th IEEE International Conference on 
Tools For Artificial Intelligence},

 year = {2004},

 address = {Boca Raton, USA},

 publisher = {IEEE Computer Society Press}

}

Dernière mise à jour : 8/11/04
Catherine.Martin@sophia.inria.fr