This paper introduces a new set of orthogonal moment functions based on the
discrete Tchebichef polynomials. The Tchebichef moments can be effectively
used as pattern features in the analysis of two-dimensional images. The im
plementation of moments proposed in this paper does not involve any numeric
al approximation, since the basis set is orthogonal in the discrete domain
of the image coordinate space. This property makes Tchebichef moments super
ior to the conventional orthogonal moments such as Legendre moments and Zer
nike moments, in terms of preserving the analytical properties needed to en
sure information redundancy in a moment set. The paper also details the var
ious computational aspects of Tchebichef moments and demonstrates their fea
ture representation capability using the method of image reconstruction.