An image quality metric based on corner, edge and symmetry maps

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

Image quality metrics have been widely used in imaging systems to maintain
and improve the quality of images being processed and transmitted. Due
to the close relationship between image quality perception and human visual
system, the development of image quality metrics (IQMs) has been
contributed to by both psychologists and computer scientists. In this paper,
three novel image quality metrics have been proposed by improving
the well-known image quality metric structure similarity index (SSIM). In
this new approach, images are not compared directly, but their feature maps
are (preprocessing is incorporated to extract the corner, edge and symmetry
maps). The similarity measured (by SSIM) between corner, edge and symmetry
maps of images being compared is used as an indicator of image quality,
and named C SSIM, E SSIM and S SSIM respectively. The experiments
show that all the proposed image quality metrics have a better performance
than SSIM, and E SSIM has the best performance among them.
Original languageEnglish
Title of host publicationProceedings of British Machine Vision Conference (BMVC) 2008
EditorsMark Everingham, Chris Needham, Roberto Fraile
PublisherBMVA
Pages373-382
Number of pages10
ISBN (Electronic)978 1 901725 37 7
ISBN (Print)978 1 901725 36 0
Publication statusPublished - Sep 2008
EventBritish Machine Vision Conference 2008 - Leeds, United Kingdom
Duration: 1 Sep 20084 Sep 2008

Conference

ConferenceBritish Machine Vision Conference 2008
CountryUnited Kingdom
CityLeeds
Period1/09/084/09/08

Fingerprint

Image quality
Imaging systems

Cite this

Cui, L., & Allen, A. R. (2008). An image quality metric based on corner, edge and symmetry maps. In M. Everingham, C. Needham, & R. Fraile (Eds.), Proceedings of British Machine Vision Conference (BMVC) 2008 (pp. 373-382). BMVA.

An image quality metric based on corner, edge and symmetry maps. / Cui, L.; Allen, Alastair Robert.

Proceedings of British Machine Vision Conference (BMVC) 2008. ed. / Mark Everingham; Chris Needham; Roberto Fraile. BMVA, 2008. p. 373-382.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cui, L & Allen, AR 2008, An image quality metric based on corner, edge and symmetry maps. in M Everingham, C Needham & R Fraile (eds), Proceedings of British Machine Vision Conference (BMVC) 2008. BMVA, pp. 373-382, British Machine Vision Conference 2008, Leeds, United Kingdom, 1/09/08.
Cui L, Allen AR. An image quality metric based on corner, edge and symmetry maps. In Everingham M, Needham C, Fraile R, editors, Proceedings of British Machine Vision Conference (BMVC) 2008. BMVA. 2008. p. 373-382
Cui, L. ; Allen, Alastair Robert. / An image quality metric based on corner, edge and symmetry maps. Proceedings of British Machine Vision Conference (BMVC) 2008. editor / Mark Everingham ; Chris Needham ; Roberto Fraile. BMVA, 2008. pp. 373-382
@inproceedings{960307a332174e4d81f298b45e3bf522,
title = "An image quality metric based on corner, edge and symmetry maps",
abstract = "Image quality metrics have been widely used in imaging systems to maintainand improve the quality of images being processed and transmitted. Dueto the close relationship between image quality perception and human visualsystem, the development of image quality metrics (IQMs) has beencontributed to by both psychologists and computer scientists. In this paper,three novel image quality metrics have been proposed by improvingthe well-known image quality metric structure similarity index (SSIM). Inthis new approach, images are not compared directly, but their feature mapsare (preprocessing is incorporated to extract the corner, edge and symmetrymaps). The similarity measured (by SSIM) between corner, edge and symmetrymaps of images being compared is used as an indicator of image quality,and named C SSIM, E SSIM and S SSIM respectively. The experimentsshow that all the proposed image quality metrics have a better performancethan SSIM, and E SSIM has the best performance among them.",
author = "L. Cui and Allen, {Alastair Robert}",
year = "2008",
month = "9",
language = "English",
isbn = "978 1 901725 36 0",
pages = "373--382",
editor = "Mark Everingham and Chris Needham and Roberto Fraile",
booktitle = "Proceedings of British Machine Vision Conference (BMVC) 2008",
publisher = "BMVA",

}

TY - GEN

T1 - An image quality metric based on corner, edge and symmetry maps

AU - Cui, L.

AU - Allen, Alastair Robert

PY - 2008/9

Y1 - 2008/9

N2 - Image quality metrics have been widely used in imaging systems to maintainand improve the quality of images being processed and transmitted. Dueto the close relationship between image quality perception and human visualsystem, the development of image quality metrics (IQMs) has beencontributed to by both psychologists and computer scientists. In this paper,three novel image quality metrics have been proposed by improvingthe well-known image quality metric structure similarity index (SSIM). Inthis new approach, images are not compared directly, but their feature mapsare (preprocessing is incorporated to extract the corner, edge and symmetrymaps). The similarity measured (by SSIM) between corner, edge and symmetrymaps of images being compared is used as an indicator of image quality,and named C SSIM, E SSIM and S SSIM respectively. The experimentsshow that all the proposed image quality metrics have a better performancethan SSIM, and E SSIM has the best performance among them.

AB - Image quality metrics have been widely used in imaging systems to maintainand improve the quality of images being processed and transmitted. Dueto the close relationship between image quality perception and human visualsystem, the development of image quality metrics (IQMs) has beencontributed to by both psychologists and computer scientists. In this paper,three novel image quality metrics have been proposed by improvingthe well-known image quality metric structure similarity index (SSIM). Inthis new approach, images are not compared directly, but their feature mapsare (preprocessing is incorporated to extract the corner, edge and symmetrymaps). The similarity measured (by SSIM) between corner, edge and symmetrymaps of images being compared is used as an indicator of image quality,and named C SSIM, E SSIM and S SSIM respectively. The experimentsshow that all the proposed image quality metrics have a better performancethan SSIM, and E SSIM has the best performance among them.

M3 - Conference contribution

SN - 978 1 901725 36 0

SP - 373

EP - 382

BT - Proceedings of British Machine Vision Conference (BMVC) 2008

A2 - Everingham, Mark

A2 - Needham, Chris

A2 - Fraile, Roberto

PB - BMVA

ER -