Translation and scale invariants of Krawtchouk moments

Krawtchouk moments are discrete orthogonal moments which are effective for image representation. The translation and scale invariants of Krawtchouk moments are achieved either by normalizing the image or by using a combination of the corresponding invariants of geometric moments. However, the derivation of these functions is not based on Krawtchouk polynomials. In this paper, we propose a new method to derive the translation and scale invariants of Krawtchouk moments directly from the Krawtchouk polynomials. The performance of the proposed method is verified using binary characters. Experimental results show that the values of the Krawtchouk moments are invariant under image translation and scale. Furthermore, the speed of the proposed method is faster than conventional methods. (C) 2017 Published by Elsevier B.V.