Ontology Based Complex Object Recognition

Abstract : This paper presents a new approach for object categorization involving the following aspects of cognitive vision: learning, recognition and knowledge representation.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. Machine learning techniques are used to solve the symbol grounding problem (i.e. linking meaningfully symbols to sensory information). This paper shows how a new object categorization system is set up by a knowledge acquisition and learning phase and then used by an object categorization phase.
Type de document :
Article dans une revue
Image and Vision Computing, Elsevier, 2008, 26 (1), pp 102-113
Liste complète des métadonnées

Contributeur : Monique Thonnat <>
Soumis le : mardi 13 juillet 2010 - 18:45:05
Dernière modification le : samedi 27 janvier 2018 - 01:30:41
Document(s) archivé(s) le : jeudi 14 octobre 2010 - 15:45:48


Fichiers produits par l'(les) auteur(s)


  • HAL Id : inria-00502361, version 1



Nicolas Maillot, Monique Thonnat. Ontology Based Complex Object Recognition. Image and Vision Computing, Elsevier, 2008, 26 (1), pp 102-113. 〈inria-00502361〉



Consultations de la notice


Téléchargements de fichiers