Ontology based complex object recognition

This paper presents an object categorization method. Our approach involves the following aspects of cognitive vision : machine learning 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. This paper details this approach which is composed of three phases: a knowledge acquisition phase, a learning phase and a categorization phase. A major issue is the symbol grounding problem (symbol grounding consists in 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.