Image classification using separable invariant moments of Krawtchouk-Tchebichef

In this paper, we propose a new set of separable two-dimensional discrete orthogonal moments called Krawtcouk-Tchebichef's moments. This set of moments is based on the bivariate discrete orthogonal polynomials defined from the product of Krawtchouk and Tchebichef discrete orthogonal polynomials with one variable. We also present a novel set of Krawtchouk-Tchebichef invariant moments. These invariant moments are derived algebraically from the geometric invariant moments and their computation is accelerated using an image representation scheme. The performance of these invariant moments used as pattern features for a pattern classification is compared with Tchebichef and Krawtchouk invariant moments.