Fast and accurate algorithm for 3D local object reconstruction using Krawtchouk moments

Abstract

Discrete Krawtchouk moments are powerful tools in the field of image processing application and pattern recognition. In this paper, we propose a fast and accurate algorithm based on matrix multiplication to extract local features of 3D Krawtchouk moments. The center of interest region in an object can be shifted by varying three parameters. We also computed local Tchebichef moments from 3D object by using the weight function of Krawtchouk polynomials. Experiment results have shown the superiority of the proposed method in terms of object reconstruction comparing with Tchebichef moments.