VOLUME DECOMPOSITION AND FEATURE RECOGNITION .2. CURVED OBJECTS

A method has been developed that decomposes a curved object into volum es, called maximal volumes, with the half-spaces of the object. A maxi mal volume has as few concave edges as possible without introducing ad ditional halfspaces. The object is first decomposed into minimal cells by extending the surfaces of the object. Combinations of these minima l cells are then composed to form maximal volumes. The combinations of such minimal cells that result in maximal volumes are found by traver sing a search tree which is pruned by examining the relationships amon g these minimal cells. One application of this decomposition method is recognition of machining features. With this decomposition method, a delta volume is decomposed into maximal volumes. Many maximal volumes are readily recognizable as features with graph matching. Compound fea tures can be recognized by combining maximal volumes. By subtracting m aximal volumes from each other in different orders and applying graph matching to the resulting volumes, multiple interpretations of feature s can be generated. Copyright (C) 1996 Elsevier Science Ltd