Automatic recognition of 3-D objects via geographic encoding

An approach to computer recognition of 3-D objects is presented. The vision system acquires the useful knowledge about the objects by taking their pictures at several stable positions and with various viewing angles. The acquired knowledge is represented by four levels of geographic codes. At each stable position, the object is characterized by a set of geographic code clusters. During the training phase, a knowledge base for geographic encoding representation is created. In the recognition phase, the vision system extracts the geographic codes of unknown objects and performs pattern cluster matching for the identification of the objects