Image analysis using separable discrete moments of Charlier-Hahn

In this paper, we present a new set of bivariate discrete orthogonal polynomials defined from the product of Charlier and Hahn discrete orthogonal polynomials with one variable. This bivriate polynomial is used to define other set of separable two-dimensional discrete orthogonal moments called Charlier-Hahn’s moments. We also propose the use of the image slice representation methodology for fast computation of Charlier-Hahn’s moments. In this approach the image is decomposed into series of non-overlapped binary slices and each slice is described by a number of homogenous rectangular blocks. Thus, the moments of Charlier-Hahn can be computed fast and easily from the blocks of each slice. A novel set of Charlier-Hahn invariant moments is also presented. These invariant moments are derived algebraically from the geometric invariant moments and their computation is accelerated using an image representation scheme. The presented approaches are tested in several well known computer vision datasets including computational time, image reconstruction, the moment’s invariability and the classification of objects. The performance of these invariant moments used as pattern features for a pattern classification is compared with Charlier, Hahn, Tchebichef-Krawtchouk, Tchebichef-Hahn and Krawtchouk-Hahn invariant moments.