Denoising by Anisotropic Diffusion of Independent Component Coefficients

In this paper, we propose an image denoising method that incorporates anisotropic diffusion and independent component analysis (ICA) techniques. An image is decomposed into independent component coefficients, and anisotropic diffusion is applied to filtering the IC coefficients. The proposed method achieved much better noise suppression with minimum edge blurring compared with other denoising methods, such as original anisotropic diffusion filter and wavelet shrinkage. The effectiveness of the proposed method is demonstrated by simulation experiments on medical image denoising.