A Mixed Denoising Algorithm Based on Weighted Joint Sparse Representation

Abstract

Joint sparse representation is not ideal for the processing of outliers in image, so a weighted joint sparse representation model for image denoising is proposed. This model introduces a weighted matrix of common information shared by data samples and reduces the influence of outliers. The greedy algorithm based on weighted simultaneous orthogonal matching pursuit is used to approximate the global optimal solution of the model effectively. The weighted noisy image block is used to remove the mixed noise of the image by jointly coding the nonlocal similar image blocks. By combining global priori knowledge and sparse errors into one unified framework, the denoising performance is further improved. Experimental results show that the denoising performance of this method is better than the existing hybrid denoising methods.