Accurate reconstruction of noisy medical images using orthogonal moments

Abstract

Accurate reconstruction of noisy medical images is presented in this work. Speckle, additive white Gaussian and Rician noises are the most popular kinds of noise raised in medical imaging systems. Medical images contaminated with these noises were reconstructed herein by using Pseudo Zernike, Legendre, Gaussian-Hermite, and Krawtchouk moments. Numerical experiments were conducted and the moments' performance in reconstructing the noisy medical images was evaluated. The experiments have shown that the performance of Legendre moments is superior to all other moments in the case of speckle and Rician noises, while in the case of additive Gaussian noise, Legendre, Gaussian-Hermite and Krawtchouk moments presenting very similar performances.