Improving performance of deblocking techniques using image fusion

Abstract

Block based transform coding is the most popular technique for image and video compression. However, images compressed using block based algorithms exhibit blocking which is one of the most annoying artifacts in compressed images and video. Many deblocking algorithms have been proposed to improve the quality of the reconstructed image. Although the deblocking operation improves the image appearance by smoothing the block discontinuities, a loss of information also occurs during this process. As a consequence, there is a need to develop methods to reduce the blocking artifacts while minimizing the information loss. We propose a novel fusion based technique to minimize the loss of useful information which may result from the deblocking operation. The loss of key image information can be reduced by fusing a deblocking result and the compressed image.