Bivariate Double Density Discrete Wavelet for Enhanced Image Denoising

Abstract

Image denoising is of paramount importance in image processing. In this paper, we propose a new design technique for the design of Double density Discrete Wavelet Transform (DD DWT) AND DD CWT filter bank structure. These filter banks satisfy the perfect reconstruction as well as alias free properties of the DWT. Next, we utilized this filter bank structure in image denoising. Our denoising scheme is based on utilizing the interscale correlation/interscale dependence between wavelet coefficients of a DD DWT of the noisy image. This is known as the Bivariate Shrinkage scheme. More precisely, we update DD DWT of the noisy image at a certain scale, according to their correlations with the next coarser scale. The Maximum Likelihood Estimation are used for this update. Comparisons have been made with classical denoising schemes that threshold the DD DWT coefficient as well as denoising schemes employing Complex Wavelet Transform (CWT) filter banks. Illustrative examples are given to show the superiority of the proposed Bivariate DD DWT technique over current literature techniques.