Abstract | ||
---|---|---|
In this paper, we propose a temporal error concealment method based on edge connectivity to neighboring regions through a damaged region. In the method, four regions around the damaged block, top, bottom, left, and right, are defined and the edge features of the regions are extracted by applying an edge operator for each direction. The mask for the boundary matching is determined by the edge information for each boundary region, which can be considered as a criterion to measure the activity of the boundary region. In other words, it is determined such that the mask size is proportional to the edge strength of each region in order to yield the higher reliability on boundary matching. This process is equivalent to applying weights depending on the edge features, which produces better motion vector for concealment. In experiments, it is verified that the proposed method outperforms the conventional methods in terms of image quality. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11949534_85 | PSIVT |
Keywords | Field | DocType |
edge operator,damaged region,edge strength,boundary region,conventional method,edge information,temporal error concealment method,neighboring region,edge connectivity,edge feature,boundary matching,edge adaptive boundary matching,image quality | Error concealment,Computer vision,Pattern recognition,Adaptive method,Computer science,Edge detection,Image processing,Image quality,Artificial intelligence,Operator (computer programming),Edge strength,Motion vector | Conference |
Volume | ISSN | ISBN |
4319 | 0302-9743 | 3-540-68297-X |
Citations | PageRank | References |
2 | 0.36 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hyun-Soo Kang | 1 | 13 | 6.22 |
Yong-Woo Kim | 2 | 33 | 3.79 |
Tae-Yong Kim | 3 | 3 | 1.46 |