Knowledge construction and interpretation of the objects based on 2D representation image in a machine perception

The image represents an information structure of an extreme complexity. We present a method for symbolic and structured description with several levels of abstraction. The application area concerns the construction and interpretation knowledge on 3D objects in a machine perception. The knowledge representation and scenes interpretation tasks based on 2D image used "Perceived Aspects Tables" and "Quality Tables" proposed by our vision system. The necessary knowledge to this task are formalised. Then, we resolve the main interpretation problem, the control and the identification of objects, thanks to the approach called: "Prediction-Checking of Hypotheses". The representation, which is suggested, is based on the "Frames" Model. With this end in view, an organisation system of perception and scenes interpretation tasks in order to maintain a coherent representation of a structured and evolutive environment is designed. The released concepts and the proposed system are realised in a LE-LISP Object Oriented environment based on the SHIRKA knowledge representation system.