A CAD MODEL-BASED SYSTEM FOR OBJECT RECOGNITION

3D object recognition is a difficult and yet an important problem in c omputer vision. A 3D object recognition system has two major component s, namely: an object modeller and a system that performs the matching of stored representations to those derived from the sensed image. The performance of systems wherein the construction of object models is do ne by training from one or more images of the objects, has not been ve ry satisfactory. Although objects used in a robotic workcell or in ass embly processes have been designed using a CAD system, the vision syst ems used for recognition of these objects are independent of the CAD d atabase. This paper proposes a scheme for interfacing the CAD database of objects and the computer vision processes used for recognising the se objects. CAD models of objects are processed to generate vision ori ented features that appear in the different views of the object and th e same features are extracted from images of the object to identify th e object and its pose.