Object recognition using the Connection Machine

The authors report on a model-based object recognition system and its parallel implementation on the Connection Machine system. The goal is to recognize two-dimensional objects in a scene, given a reasonably large database of known objects. The system uses massively parallel hypotheses generation and parameter space clustering in place of serial constraint propagation. Local boundary features that constrain an object's position and orientation provide a basis for hypothesis generation. Parameter space clustering of hypotheses is used to rank hypotheses according to preliminary evidence prior to verification. This greatly reduces the time for recognition and number of hypotheses that must be tested. Experiments show that the time required by this approach scales at a much slower range than either the number of objects in the database or objects in the scene. >