Image denoising algorithm using doubly local Wiener filtering with block-adaptive windows in wavelet domain

In this paper, we propose the block-adaptive windows that are used to upgrade the image denoising performance of the doubly local Wiener filtering method and the corresponding algorithm is also used to reduce spatially non-stationary additive white Gaussian noise (SNS-AWGN) in images. Based on the fact that the energy clusters in the detail subimages of an image exhibit direction features varying with spatial locations and oriented subbands, a noisy detail subimage is divided into non-overlapping small-size blocks and the spatial energy correlation function of each block is calculated to determine the principal direction of energy clusters within each block and the corresponding block-adaptive window. The block-adaptive windows are used to improve the estimations of the image's energy distribution in the detail subimages. For noisy images corrupted by SNS-AWGNs, non-uniform noise variances in the pixel domain must be estimated. To do that, we propose the joint neighborhood median absolute deviation (JNMAD) estimator, which makes the denoising algorithm able to be used in the cases of SNS-AWGNs. The experimental results show that the doubly local Wiener filtering method with block-adaptive windows is superior to other wavelet-based methods using two-dimensional separable wavelet transforms in the case of stationary noise and provides satisfactory performance in the cases of SNS-AWGNs. (c) 2007 Elsevier B.V. All rights reserved.