Image denoising using multi-stage sparse representations

This paper presents a novel image denoising method based on multiscale sparse representations. The denoising is performed in a multi-stage framework where sparse representations are obtained in different scales to capture multiscale image features. Based on the multi-stage structure, we introduce a new stopping criterion for sparse coding to capture image structures more accurately than previous methods. Furthermore we propose a thresholding technique to effectively avoid artifacts which are usually introduced due to the erroneous pursuit for noise-induced structures. Experimental results demonstrate that the proposed method achieves PSNR performance comparable to other state-of-the-art methods while producing denoised images with superior visual quality.