Removal of Blocking Artifacts Using a Hierarchical Bayesian Approach

Abstract

Blocking artifacts are exhibited by block-compressed still images and sequences of images, primarily at high compression ratios. These artifacts are due to the independent processing (quantization) of the block transformed values of the intensity or the displaced frame difference. In this chapter, we provide a survey of the literature on the removal of such artifacts. We also apply the hierarchical Bayesian paradigm to the reconstruction of block discrete cosine transform compressed images and the estimation of the required hyperparameters. The evidence analysis within the hierarchical Bayesian paradigm is used to derive expressions for the iterative evaluation of these parameters. The proposed method allows for the combination of parameters estimated at the coder and decoder. The performance of the proposed algorithms is demonstrated experimentally.