Skip to Main content Skip to Navigation
Journal articles

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.
Complete list of metadata
Contributor : Monique Thonnat Connect in order to contact the contributor
Submitted on : Tuesday, July 13, 2010 - 6:45:05 PM
Last modification on : Friday, February 4, 2022 - 3:24:48 AM
Long-term archiving on: : Thursday, October 14, 2010 - 3:45:48 PM


Files produced by the author(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⟩



Record views


Files downloads