Global shape invariants: a solution for 3D free-form object discrimination/identification problem

摘要

A method for solving the 3D object recognition problem is described in this paper. The method uses a new set of global features as discriminant parameters. The general purpose of our approach is to achieve simplicity, speed and efficiency by using global invariants. For this, two new global parameters are introduced, which are invariant to rotation, translation and scaling: canonical length (CL), which provides an indirect measurement of object surface and weighted principal directions (WPDs) corresponding to the meaningful normal directions of the object surface. Abundant experimentation has been conducted with a real world system in order to validate the method.