No-reference quality metric for degraded and enhanced video

Jorge Caviedes, Franco Oberti

Research output: Contribution to journalConference article

26 Citations (Scopus)

Abstract

In this paper we present a no-reference objective quality metric (NROQM) that has resulted from extensive research on impairment metrics, image feature metrics, and subjective image quality in several projects in Philips Research, and participation in the ITU Video Quality Experts Group. The NROQM is aimed at requirements including video algorithm development, embedded monitoring and control of image quality, and evaluation of different types of display systems. NROQM is built from metrics for desirable and non-desirable image features (sharpness, contrast, noise, clipping, ringing, and blocking artifacts), and accounts for their individual and combined contributions to perceived image quality. We describe our heuristic, incremental approach to modeling quality and training the NROQM, and its advantages to deal with imperfect data and imperfect metrics. The results of training the NROQM using a large set of video sequences, which include degraded and enhanced video, show high correlation between objective and subjective scores, and the results of the first performance test show good objective-subjective correlations as well. We also discuss issues that require further research such as fully content-independent metrics, measuring over-enhanced video quality, and the role of temporal impairment metrics.

Original languageEnglish (US)
Pages (from-to)621-632
Number of pages12
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume5150 I
DOIs
StatePublished - Oct 1 2003
Externally publishedYes
EventVisual Communications and Image Processing 2003 - Lugano, Switzerland
Duration: Jul 8 2003Jul 11 2003

Fingerprint

Image quality
Metric
Image Quality
Display devices
Video Quality
impairment
Monitoring
Imperfect
education
Clipping
Performance Test
performance tests
sharpness
Sharpness
display devices
Large Set
artifacts
Display
Heuristics
requirements

Keywords

  • No-reference image quality
  • Objective image quality metric
  • Video impairment metric

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

No-reference quality metric for degraded and enhanced video. / Caviedes, Jorge; Oberti, Franco.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 5150 I, 01.10.2003, p. 621-632.

Research output: Contribution to journalConference article

@article{6da2de374439447fb8f7ef4b000ca523,
title = "No-reference quality metric for degraded and enhanced video",
abstract = "In this paper we present a no-reference objective quality metric (NROQM) that has resulted from extensive research on impairment metrics, image feature metrics, and subjective image quality in several projects in Philips Research, and participation in the ITU Video Quality Experts Group. The NROQM is aimed at requirements including video algorithm development, embedded monitoring and control of image quality, and evaluation of different types of display systems. NROQM is built from metrics for desirable and non-desirable image features (sharpness, contrast, noise, clipping, ringing, and blocking artifacts), and accounts for their individual and combined contributions to perceived image quality. We describe our heuristic, incremental approach to modeling quality and training the NROQM, and its advantages to deal with imperfect data and imperfect metrics. The results of training the NROQM using a large set of video sequences, which include degraded and enhanced video, show high correlation between objective and subjective scores, and the results of the first performance test show good objective-subjective correlations as well. We also discuss issues that require further research such as fully content-independent metrics, measuring over-enhanced video quality, and the role of temporal impairment metrics.",
keywords = "No-reference image quality, Objective image quality metric, Video impairment metric",
author = "Jorge Caviedes and Franco Oberti",
year = "2003",
month = "10",
day = "1",
doi = "10.1117/12.510112",
language = "English (US)",
volume = "5150 I",
pages = "621--632",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

TY - JOUR

T1 - No-reference quality metric for degraded and enhanced video

AU - Caviedes, Jorge

AU - Oberti, Franco

PY - 2003/10/1

Y1 - 2003/10/1

N2 - In this paper we present a no-reference objective quality metric (NROQM) that has resulted from extensive research on impairment metrics, image feature metrics, and subjective image quality in several projects in Philips Research, and participation in the ITU Video Quality Experts Group. The NROQM is aimed at requirements including video algorithm development, embedded monitoring and control of image quality, and evaluation of different types of display systems. NROQM is built from metrics for desirable and non-desirable image features (sharpness, contrast, noise, clipping, ringing, and blocking artifacts), and accounts for their individual and combined contributions to perceived image quality. We describe our heuristic, incremental approach to modeling quality and training the NROQM, and its advantages to deal with imperfect data and imperfect metrics. The results of training the NROQM using a large set of video sequences, which include degraded and enhanced video, show high correlation between objective and subjective scores, and the results of the first performance test show good objective-subjective correlations as well. We also discuss issues that require further research such as fully content-independent metrics, measuring over-enhanced video quality, and the role of temporal impairment metrics.

AB - In this paper we present a no-reference objective quality metric (NROQM) that has resulted from extensive research on impairment metrics, image feature metrics, and subjective image quality in several projects in Philips Research, and participation in the ITU Video Quality Experts Group. The NROQM is aimed at requirements including video algorithm development, embedded monitoring and control of image quality, and evaluation of different types of display systems. NROQM is built from metrics for desirable and non-desirable image features (sharpness, contrast, noise, clipping, ringing, and blocking artifacts), and accounts for their individual and combined contributions to perceived image quality. We describe our heuristic, incremental approach to modeling quality and training the NROQM, and its advantages to deal with imperfect data and imperfect metrics. The results of training the NROQM using a large set of video sequences, which include degraded and enhanced video, show high correlation between objective and subjective scores, and the results of the first performance test show good objective-subjective correlations as well. We also discuss issues that require further research such as fully content-independent metrics, measuring over-enhanced video quality, and the role of temporal impairment metrics.

KW - No-reference image quality

KW - Objective image quality metric

KW - Video impairment metric

UR - http://www.scopus.com/inward/record.url?scp=0141608043&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141608043&partnerID=8YFLogxK

U2 - 10.1117/12.510112

DO - 10.1117/12.510112

M3 - Conference article

AN - SCOPUS:0141608043

VL - 5150 I

SP - 621

EP - 632

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -