Qualitative and quantitative matching of solid models and images of 3D objects

A model-based vision system which recognizes 3D objects in an image is presented. The procedure is divided into two phases: qualitative and quantitative. First, component primitives of objects are qualitatively detected in the image, so as to invoke efficiently as few candidate object models as necessary from a number of models and to get corresponding points between models and data. Then, a candidate transformation is quantitatively hypothesized for each object by initially matching a few corresponding points in the primitive; the match is tested and adjusted for verification by matching all the points in the model