Publication detail

A Matlab-based Tool for Video Quality Evaluation without Reference

ZACH, O. SLANINA, M.

Original Title

A Matlab-based Tool for Video Quality Evaluation without Reference

English Title

A Matlab-based Tool for Video Quality Evaluation without Reference

Type

journal article in Web of Science

Language

en

Original Abstract

This paper deals with the design of a Matlab based tool for measuring video quality with no use of a reference sequence. The main goals are described and thetool and its features are shown. The paper begins with a description of the existing pixel-based no-reference quality metrics. Then, a novel algorithm for simple PSNR estimation of H.264/AVC coded videos is presented as an alternative. The algorithm was designed and tested using publicly available video database of H.264/AVC coded videos. Cross-validation was used to confirm the consistency of results.

English abstract

This paper deals with the design of a Matlab based tool for measuring video quality with no use of a reference sequence. The main goals are described and thetool and its features are shown. The paper begins with a description of the existing pixel-based no-reference quality metrics. Then, a novel algorithm for simple PSNR estimation of H.264/AVC coded videos is presented as an alternative. The algorithm was designed and tested using publicly available video database of H.264/AVC coded videos. Cross-validation was used to confirm the consistency of results.

Keywords

Quality assessment, GBIM, PSNR, MOS, image quality, H.264/AVC, quality metric

RIV year

2014

Released

11.04.2014

Pages from

405

Pages to

411

Pages count

7

BibTex


@article{BUT107062,
  author="Ondřej {Zach} and Martin {Slanina}",
  title="A Matlab-based Tool for Video Quality Evaluation without Reference",
  annote="This paper deals with the design of a Matlab based tool for measuring video quality with no use of a reference sequence. The main goals are described and thetool
and its features are shown. The paper begins with a description of the existing pixel-based no-reference quality metrics. Then, a novel algorithm for simple PSNR estimation of H.264/AVC
coded videos is presented as an alternative. The algorithm was designed and tested using publicly available video database of H.264/AVC coded videos.
Cross-validation was used to confirm the consistency of results.",
  chapter="107062",
  number="1",
  volume="23",
  year="2014",
  month="april",
  pages="405--411",
  type="journal article in Web of Science"
}