Local adaptive dictionary based image denoising

In this paper, the problem of balancing the noise removing and the image details preserving is considered. To remove noise adaptively, local dictionaries and sparse coding techniques are used. For a noised image patch, the local dictionary corresponding to it and the sparse coding technique are used to generate the sparse coding vector of the given patch. Then the noise of the given patch can be removed without any information on noise level by setting all components be zero but preserving largest component of the sparse coding vector. Because too much information on image details are removed with noise by the above process, a local weighted regression is adopted to refine the denoising image with the help of the information on the local geometry structure of noised image. Various experiments have been accomplished and prove our method to be effective in balancing the noise removing and the image details preserving.