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

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 parame ters. The general purpose of our approach is to achieve simplicity, speed a nd efficiency by using global invariants. For this, two new global paramete rs are introduced, which are invariant to rotation, translation and scaling : canonical length (CL), which provides an indirect measurement of object s urface and weighted principal directions (WPDs) corresponding to the meanin gful normal directions of the object surface. Abundant experimentation has been conducted with a real world system in order to validate the method. (C ) 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.