Full-reference metrics multidistortional analysis

Oleg Ieremeiev; Vladimir Lukin; Nikolay Ponomarenko; Karen Egiazarian

doi:10.2352/ISSN.2470-1173.2017.13.IPAS-202

Full-reference metrics multidistortional analysis

Oleg Ieremeiev, Vladimir Lukin, Nikolay Ponomarenko, Karen Egiazarian

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

Abstract

This paper is devoted to analysis and further improvement of full-reference metrics of image visual quality. The effectiveness of a metric is characterized by the rank correlation factors between the obtained array of mean opinion scores (MOS) and the corresponding array of given metric values. This allows to determine the correspondence of a considered metric to a human visual system (HVS). Results obtained on the database TID2013 show that Spearman correlation for the best existing metrics (PSNRHMA, FSIM, SFF, etc.) does not exceed 0.85. In this paper, extended verification tools that allow to detect the shortcomings of the metrics taking into account combined distortions is proposed. An example for further improvement of the PSNRHMA metric is presented.

Original language	English
Title of host publication	Image Processing: Algorithms and Systems XV
Pages	27-35
Number of pages	9
DOIs	https://doi.org/10.2352/ISSN.2470-1173.2017.13.IPAS-202
Publication status	Published - 2017
Publication type	A4 Article in conference proceedings
Event	IS&T International Symposium on Electronic Imaging - Duration: 1 Jan 2000 → …

Publication series

Name	Electronic Imaging
ISSN (Print)	2470-1173

Conference

Conference	IS&T International Symposium on Electronic Imaging
Period	1/01/00 → …

Keywords

Full-reference metrics
Image visual quality assessment
Metrics analysis
Metrics verification
Multiple distortions

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Science Applications
Human-Computer Interaction
Software
Electrical and Electronic Engineering
Atomic and Molecular Physics, and Optics

Access to Document

10.2352/ISSN.2470-1173.2017.13.IPAS-202

Cite this

@inproceedings{280e2c75d6ae4a54aacc37bb281fff91,

title = "Full-reference metrics multidistortional analysis",

abstract = "This paper is devoted to analysis and further improvement of full-reference metrics of image visual quality. The effectiveness of a metric is characterized by the rank correlation factors between the obtained array of mean opinion scores (MOS) and the corresponding array of given metric values. This allows to determine the correspondence of a considered metric to a human visual system (HVS). Results obtained on the database TID2013 show that Spearman correlation for the best existing metrics (PSNRHMA, FSIM, SFF, etc.) does not exceed 0.85. In this paper, extended verification tools that allow to detect the shortcomings of the metrics taking into account combined distortions is proposed. An example for further improvement of the PSNRHMA metric is presented.",

keywords = "Full-reference metrics, Image visual quality assessment, Metrics analysis, Metrics verification, Multiple distortions",

author = "Oleg Ieremeiev and Vladimir Lukin and Nikolay Ponomarenko and Karen Egiazarian",

note = "jufoid=84313 EXT={"}Ponomarenko, Nikolay{"} EXT={"}Lukin, Vladimir{"}; IS&T International Symposium on Electronic Imaging ; Conference date: 01-01-2000",

year = "2017",

doi = "10.2352/ISSN.2470-1173.2017.13.IPAS-202",

language = "English",

series = "Electronic Imaging",

pages = "27--35",

booktitle = "Image Processing: Algorithms and Systems XV",

}

TY - GEN

T1 - Full-reference metrics multidistortional analysis

AU - Ieremeiev, Oleg

AU - Lukin, Vladimir

AU - Ponomarenko, Nikolay

AU - Egiazarian, Karen

N1 - jufoid=84313 EXT="Ponomarenko, Nikolay" EXT="Lukin, Vladimir"

PY - 2017

Y1 - 2017

N2 - This paper is devoted to analysis and further improvement of full-reference metrics of image visual quality. The effectiveness of a metric is characterized by the rank correlation factors between the obtained array of mean opinion scores (MOS) and the corresponding array of given metric values. This allows to determine the correspondence of a considered metric to a human visual system (HVS). Results obtained on the database TID2013 show that Spearman correlation for the best existing metrics (PSNRHMA, FSIM, SFF, etc.) does not exceed 0.85. In this paper, extended verification tools that allow to detect the shortcomings of the metrics taking into account combined distortions is proposed. An example for further improvement of the PSNRHMA metric is presented.

AB - This paper is devoted to analysis and further improvement of full-reference metrics of image visual quality. The effectiveness of a metric is characterized by the rank correlation factors between the obtained array of mean opinion scores (MOS) and the corresponding array of given metric values. This allows to determine the correspondence of a considered metric to a human visual system (HVS). Results obtained on the database TID2013 show that Spearman correlation for the best existing metrics (PSNRHMA, FSIM, SFF, etc.) does not exceed 0.85. In this paper, extended verification tools that allow to detect the shortcomings of the metrics taking into account combined distortions is proposed. An example for further improvement of the PSNRHMA metric is presented.

KW - Full-reference metrics

KW - Image visual quality assessment

KW - Metrics analysis

KW - Metrics verification

KW - Multiple distortions

U2 - 10.2352/ISSN.2470-1173.2017.13.IPAS-202

DO - 10.2352/ISSN.2470-1173.2017.13.IPAS-202

M3 - Conference contribution

AN - SCOPUS:85040625876

T3 - Electronic Imaging

SP - 27

EP - 35

BT - Image Processing: Algorithms and Systems XV

T2 - IS&T International Symposium on Electronic Imaging

Y2 - 1 January 2000

ER -