Superquadrics parameter estimation from shading image using genetic algorithm

3-D shape modeling is very important for efficient shape description and recognition. Superquadrics that is a parametric 3-D shape modeling function can represent various shapes by using a single equation with some parameters. In this study, the superquadrics parameters of 3-D shape are estimated from a 2-D shading image by using a genetic algorithm (GA), which is an optimizing technique based on mechanisms of natural selection. Ten parameters, which are five parameters of the superquadrics shape, three eular angle parameters, and two shift parameters, are coded as a string in the GA. The string is evaluated by the difference between the given 2-D shading image and the calculated shading image from the 3-D shape represented by the parameters. By applying the GA to the optimization of the evaluation value, the string having the minimum difference is sought. The parameters are estimated from some shading images of various 3-D shapes by using the proposed method, and the results are presented