A Training-Based Method for Reducing Ringing Artifact in BDCT-Encoded Images

Wang, Guangyu; Wong, Tien-Tsin; Heng, Pheng-Ann

A Training-Based Method for Reducing Ringing Artifact in BDCT-Encoded Images

Files

105-113.pdf (552.21 KB)

Date

2004

Authors

Wang, Guangyu
Wong, Tien-Tsin
Heng, Pheng-Ann

Publisher

The Eurographics Association

Abstract

The quantization procedure of block-based discrete cosine transform (BDCT) compression (such as JPEG) introduces annoying visual artifact. In this paper, we propose a novel training-based method to reduce the ringing artifact in BDCT-encoded high-contrast images (images with large smooth color areas and strong edges/outlines). Our main focus is on the removal of ringing artifact that is seldom addressed by existing methods. In the proposed method, the contaminated image is modeled as a Markov random field (MRF). We learn the behavior of contamination by extracting massive number of artifact patterns from a training set. To organize the extracted artifact patterns, we use the tree-structured vector quantization (TSVQ). Instead of post-filtering the input contaminated image, we synthesize an artifact-reduced image. We show that substantial improvement (both statistical and visual) is achieved using the proposed method. Moreover, since our method is non-iterative, it can remove artifact within a very short period of time.

        @inproceedings{:10.2312/EGMM/MM04/105-113
,
booktitle = {Eurographics Multimedia Workshop
},
editor = {N. Correia and J. Jorge and T. Chambel and Z. Pan
},
title = {{A Training-Based Method for Reducing Ringing Artifact in BDCT-Encoded Images
}},
author = {Wang, Guangyu and 
Wong, Tien-Tsin and 
Heng, Pheng-Ann
},
year = {2004
},
publisher = {The Eurographics Association
},
ISSN = {1812-7118
},
ISBN = {3-905673-17-7
},
DOI = {/10.2312/EGMM/MM04/105-113
}
}