Weighted Encoding with Sparse Nonlocal Regularization for Mixed Noise Removal Approach

Mixed noise expulsion from characteristic images is a testing errand since the noise dispersion normally does not have a parametric model and has an overwhelming tail. One sort of the mixed noise is Additive White Gaussian Noise (AWGN) coupled with Impulse Noise (IN).However, first catch the region of IN pixels and afterward evacuate the mixed noise. On the other hand, such techniques have a tendency to create numerous curios when the mixed noise is strong. In this paper, propose a straightforward yet effective system, specifically namely Weighted Encoding with Sparse Nonlocal Regularization (WESNR), for mixed noise removal. In WESNR, soft impulse detection through weighted encoding is utilized to manage IN and AWGN at the same time. The image nonlocal self-similarity prior and sparsity prior are coordinated into a regularization term and brought into the variational encoding system. Exploratory results demonstrate that the proposed WESNR system accomplishes driving mixed noise evacuation execution regarding both visual quality and quantitative measures.