Ontology based complex object recognition

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. (c) 2006 Elsevier B.V. All rights reserved.