A model based vision system for recognition of machine parts

This paper describes a vision system based on the photometric stereo system and a model generator called GEOMAP. The photometric stereo system obtains a needle map from shading information of an observed image. An extended Gaussian image of the needle map reduces possible attitudes of an object relative to the viewer. A model-generator called GEOMAP generates a needle map which would be observed from the viewer direction determined from EGI. Comparing the needle map by the GEOMAP with the needle map by the photometric stereo System makes final recognition of the object. attitude. Comparison be map and the generated tween the observed needle needle map gives a final I