WSEAS Transactions on Signal Processing
Print ISSN: 1790-5052, E-ISSN: 2224-3488
Volume 11, 2015
Edge Enhanced and Nonlocal Sparse Representation for Image Denoising
Authors: , ,
Abstract: Sparse representation and nonlocal self-similarity play an important role and show better results in image denoising. However, the methods based on sparse representation or nonlocal self-similarity tend to smooth the image edge structures or generate some artifacts. To improve the performance of image denoising, in this paper we propose an edge enhanced and nonlocal sparse representation (ENSR) model which combines Sobel edge detection results, local sparsity and nonlocal self-similarity. We use the iterative shrinkage algorithm to solve the l1-regularized ENSR minimization problem. The experimental results show that ENSR can better preserve the edge structure and achieve a competitive PSNR performance compared with some existing methods.