Image Denoising Using Block Thresholding

Abstract

This paper proposes a new image denoising method BlockShrink. BlockShrink is a completely data-driven block thresholding approach and is also easy to implement. It utilizes the pertinence of the neighbor wavelet coefficients by using the block thresholding scheme. It can decide the optimal block size and threshold for every wavelet subband by minimizing Stein's unbiased risk estimate (SURE). BlockShrink enjoys a number of advantages over the other conventional image denoising methods. Experimental results show that BlockShrink outperforms significantly classic SureShrink method and NeighShrink method proposed by Chen et al.