In this paper, a denoising approach, which exploits patchredundancy for removing Gaussian noise from RGB color images is described. Both geometrical and photometrical similarity of image patches have to be considered for learning the parameters of this Patch-based Locally Optimal Weiner(PLOW) filer. K-means clustering,with LARK(Locally Adaptive Regression Kernel) features, is used to identify the geometrically similar patches. As opposed to traditional color image denoising approaches, that perform denoising in each color channel independently, this method performs denoising in the luminance-chrominance color space and thus exploits correlation across color components. Since the luminance component, Y, contains most valuable image features such as objects, shades, textures, edges and patterns etc. , the information from the luminance component is only needed for clustering. Experimental results show that the denoising performance of the proposed method is better in terms of both peak signal-to-noise ratio and subjective visual quality.

Image denoising Color Image restoration Gaussian noise.