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.