A Method of Image Denoising in the Complex
Wavelet Domain · 2008
In this paper, a new shrink theory and denoising algorithm for image with Gaussian noise based on complex wavelet transform is presented and investigated. We calculate threshold value by a moving window, we can obtain different threshold values for different coefficients using our method. We modify the noisy wavelet coefficients using bivariate shrinkage method, the shrinkage functions do not assume the independence of decompositional coefficients. In this paper, we propose the use of near-optimal thresholds and more suitable image denoising by using extensive numerical simulations. I. INTRODUCTION Image denoising is a lively research field. Classical nonlin- ear filters used for image denoising, such as median filter (1), are based on local analysis of pixels within a moving window. Recently, the research in the field of image denoising has been focused on the wavelet domain. Compared to the classical nonlinear filters, denoising in the wavelet domain is based on global multiscale analysis of images. Denoising of natural images corrupted with Gaussian noise is a classic problem in signal processing. Wavelet transform has become an important tool for this problem due to its energy compaction property. Simple denoising algorithms that use wavelet transform consist of three steps. • Calculate the wavelet transform of the noisy image. • Modify the noisy wavelet coefficients according to some rules. • Compute the inverse transform using the modified coef- ficients. First, the controllable redundancy of the mapping stage offers a balance between the degree of shift sensitivity and transform redundancy. Second, the flexibility to use any DWT in the transform implementation. In this paper, a new shrink theory and denoising algorithm for image with Gaussian noise based on complex wavelet transform is presented and investigated. We calculate threshold value by a moving window, we can obtain different threshold values for different coefficients using our method. We mod- ify the noisy wavelet coefficients using bivariate shrinkage method, the shrinkage functions do not assume the inde- pendence of decompositional coefficients. In this paper, we propose the use of near-optimal thresholds and more suitable image denoising by using extensive numerical simulations. The rest of the paper is organized as follows. Section II discusses the proposed method. In Section III, experiments on noisy images with both conventional methods and the proposed method are described, Simulation results and dis- cussions are presented in this section. Conclusions and future work are given in Section IV. II. THE PROPOSED METHOD