Research Article
Dictionary-Based Image Denoising by Fused-Lasso Atom Selection
Input: A set of overlapping patches from noisy image ; | Output: The recovered image ; | (1) For : do | (2) Compute the weights vector for by Algorithm 1; | (3) Cluster the patches into ( by -Means with | norm measurement between and the cluster center; | (4) For : do | (5) Learn the dictionary for cluster by Algorithm 2; | (6) Recover all the patches in by Algorithm 3; | (7) End | (8) Compute the by averaging the recovered patches according to | their indexes. Then, update by the recovered image . | (9) End |
|