Repairing imperfect video enhancement algorithms using classification-based trained filters

Shao, Ling, Zhang, Hui, Wang, Liang and Wang, Lijun (2011) Repairing imperfect video enhancement algorithms using classification-based trained filters. Signal, Image and Video Processing, 5 (3). pp. 307-313. ISSN 1863-1703

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1007/s11760-010-0202-8

Abstract

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.

Item Type: Article
Uncontrolled Keywords: Trained filters, Video enhancement, Compression artefacts removal, De-blurring, Resolution up-conversion, Classification, Least squares optimisation
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer Science and Digital Technologies
Depositing User: Paul Burns
Date Deposited: 10 Jun 2015 15:54
Last Modified: 03 Nov 2016 12:02
URI: http://nrl.northumbria.ac.uk/id/eprint/22852

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics


Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence