ON GEOMETRIC HASHING AND THE GENERALIZED HOUGH TRANSFORM

The generalized Hough transform and geometric hashing are two contempo rary paradigms for model-based object recognition. Both schemes simult aneously find instances of objects in a scene and determine the locati on and orientation of these instances. The methods encode the models f or the objects in a similar fashion and object recognition is achieved by image features ''voting'' for object models. For both schemes, the object recognition time is largely independent of the number of objec ts that are encoded in the object-model database. This paper puts the two schemes in perspective and examines differences and similarities. We also study the object representation techniques and discuss how the object representations are used for object recognition and position e stimation.