Automatic Dictionary Learning Sparse Representation for Image Denoising

摘要

Sparse representation is a hot issue in image processing domain while the dictionary learning is the key part of sparse representation. In order to improve the performance of sparse representation and solve the dictionary atoms selecting problem in the dictionary learning process for further image denoising, in this paper, a kind of robust and adaptive automatic dictionary learning sparse representation algorithm is proposed. Firstly, we select image patches according to the structure similarity between image patches, and then we calculate the grey relation between neighbor potential image patches to cluster and select dictionary atoms accordingly. Finally, we select efficient dictionary atoms which can adapt to the noise and build an automatic dictionary for image denoising. The proposed algorithm is tested on large-scale benchmark databases. Experiment results demonstrate the validity of the proposed algorithm and the feasibility of grey theory used to automatic dictionary learning sparse representation for image denoising. The performance of the proposed algorithm is equivalent and sometimes surpasses the leading denoising algorithms published recently.