The Neck-based Parts Computation Method for Shape Decomposition

Abstract

In the task of forming high-level object-centered models from low-level image-based features, parts serve as an intermediate representation. A representation of parts for object recognition should be rich, stable, and invariant to changes in the viewing conditions. In addition, it should be capable of describing partially occluded shapes. This paper describes a method for decomposing a shape into its parts. The method is based on the negative curvature minima which have co-circular tangents, and directly compute necks from limb-based computation with a certain condition. Therefore, the method is efficient for partitioning a shape into the parts. Currently, we assume that the shape is a closed planar curve.