Reduction of JPEG compression artifacts by kernel regression and probabilistic self-organizing maps
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part II
| Hi-index | 0.43 |
A blocking artifact is one of major drawbacks of a block-based compression image. This appears at the block boundaries as visible discontinuities because of rough quantization. In this paper, we propose an adaptive deblocking algorithm that reduces block discontinuities in DCT domain. Our algorithm applies a deblocking procedure to each line of adjacent 3 blocks, so the block is divided into several line vectors. There are three low pass filters that are applied differently to 1times24 DCT values according to each condition of adjacent 3 vectors for conserving image details, and we use a transform table of different dimension DCTs (1times8 and 1times24 DCT) for reducing a computational cost. The experimental results show that the proposed method performs distinguished effects on an improvement of subjective image quality and a computational efficiency.