TY - JOUR
T1 - Repairing imperfect video enhancement algorithms using classification-based trained filters
AU - Shao, Ling
AU - Zhang, Hui
AU - Wang, Liang
AU - Wang, Lijun
PY - 2011/1/13
Y1 - 2011/1/13
N2 - There are numerous video processing algorithms and modules available. When the algorithms are not optimally tuned, undesired results may happen in the processed video signals, e.g. blurring, overshoots/downshoots, loss of details and aliasing. When the video processing modules are fixed, e.g. when the modules are implemented in hardware/chips, it is highly desirable to repair those unpleasant effects caused by certain imperfect algorithms. In this paper, we propose a solution based on classification and least squares trained filters to repair/patch low-quality video processing modules at the back end of a video chain. Extensive experiments show that the repairing method can significantly improve the video quality without modifying the original processing modules.
AB - There are numerous video processing algorithms and modules available. When the algorithms are not optimally tuned, undesired results may happen in the processed video signals, e.g. blurring, overshoots/downshoots, loss of details and aliasing. When the video processing modules are fixed, e.g. when the modules are implemented in hardware/chips, it is highly desirable to repair those unpleasant effects caused by certain imperfect algorithms. In this paper, we propose a solution based on classification and least squares trained filters to repair/patch low-quality video processing modules at the back end of a video chain. Extensive experiments show that the repairing method can significantly improve the video quality without modifying the original processing modules.
KW - Trained filters
KW - Video enhancement
KW - Compression artefacts removal
KW - De-blurring
KW - Resolution up-conversion
KW - Classification
KW - Least squares optimisation
U2 - 10.1007/s11760-010-0202-8
DO - 10.1007/s11760-010-0202-8
M3 - Article
VL - 5
SP - 307
EP - 313
JO - Signal, Image and Video Processing
JF - Signal, Image and Video Processing
SN - 1863-1703
IS - 3
ER -