Image Denoising based on Sparse Representation and Non-Negative Matrix Factorization

Image denoising problem can be addressed as an inverse problem. One of the most recent approaches to solve this problem is sparse decomposition over redundant dictionaries. In sparse representation we represent signals as a linear combination of a redundant dictionary atoms. In this paper we propose an algorithm for image denoising based on Non Negative Matrix Factorization (NMF) and sparse representation over redundant dictionary. It trains the initialized dictionary based on training samples constructed from noised image, then it search for the best representation for the source by using the approximate matching pursuit (AMP) which uses the nearest neighbor search to get the best atom to represent that source. During that it alternates between the dictionary update and the sparse coding. We use this algorithm to reconstruct image from denoised one. We will call our algorithm N-NMF. {[}R. M. Farouk and H.A.Khalil. Image Denoising based on Sparse Representation and Non-Negative Matrix Factorization. Life Science Journal 2012; 9(1):337-341]. (ISSN: 1097-8135). http://www.lifesciencesite.com. 48