Volumetric part based 3D object classification

This paper proposes a volumetric part based 3D object classification approach. Superquadric-hased Geon (SBG) description is implemented for representing individual volumetric parts, the constituents of 3D object. The classification of 3D ohject is decomposed into the constrained search on interpretation tree and the similarity measure computation. A set of integrated features and corresponding constraints are presented, which not only reflect individual parts' shape, but model's topological information among volumetric parts. These constraints are used to direct an efficient tree search. Following the searching stage, a similarity measure computation algorithm is developed to evaluate the shape similarity of object data and the stored models. By this classification approach, both whole and partial matching results with similarity ranks can he obtained; especially, focus match can be achieved, in which different key parts can be labeled and all the matched models with corresponding key parts can be obtained Some experiments are given to show the validity and efficiency of the approach for 3D object classification.