A Block-Grouping Method for Image Denoising by Block Matching and 3-D Transform Filtering

Image denoising by block matching and threedimensionaltransform filtering (BM3D) is a two steps state-ofthe-art algorithm that uses the redundancy of similar blocks innoisy image for removing noise. Similar blocks which can havesome overlap are found by a block matching method and groupedto make 3-D blocks for 3-D transform filtering. In this paper wepropose a new block grouping algorithm in the first step ofBM3D that improves the performance of denoising algorithmespecially in heavy noise conditions. In heavy noise conditions,BM3D causes some artifacts in the filtered image. These artifactsare reduced by the proposed block grouping algorithm. In theproposed block grouping method, beside of a similarity measureused for block matching, the amount of overlap between blocks isconsidered. Experimental results show that the proposed blockgrouping method can improve the performance of BM3D interms of both peak signal-to-noise ratio (PSNR) and visualquality.