An Image Quality Metric Based on a Colour Appearance Model

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

5 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 and human
visual perception, both computer scientists and psychologists have
contributed to the development of image quality metrics. In this paper,
a novel image quality metric using a colour appearance model is proposed.
After the physical colour stimuli of the images being compared
are transformed into perceptual colour appearance attributes, the distortion
measures between the corresponding attributes are used to predict
the subjective scores of image quality, by use of data-driven models:
Multiple Linear Regression (MLR), General Regression Neural Network
(GRNN) and Back-Propagation Neural Network (BPNN). Based on the
data-driven model used, we have developed three image quality metrics,
CAM MLR, CAM GRNN and CAM BPNN. The experiments have
shown that the performance of CAM BPNN is better than the wellknown
image quality metric SSIM.
Original languageEnglish
Title of host publicationAdvanced Concepts for Intelligent Vision Systems
Subtitle of host publication10th International Conference, ACIVS 2008, Juan-les-Pins, France, October 20-24, 2008. Proceedings
EditorsS Bourenanne, W Philips, D Popescu, P Scheunders
PublisherSpringer-Verlag
Pages696-707
Number of pages12
Volume5259
ISBN (Print)978-3-540-88457-6
Publication statusPublished - 2008

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume5259

Fingerprint

Image quality
Computer aided manufacturing
Color
Neural networks
Backpropagation
Linear regression
Imaging techniques
Experiments

Cite this

Cui, L., & Allen, A. (2008). An Image Quality Metric Based on a Colour Appearance Model. In S. Bourenanne, W. Philips, D. Popescu, & P. Scheunders (Eds.), Advanced Concepts for Intelligent Vision Systems: 10th International Conference, ACIVS 2008, Juan-les-Pins, France, October 20-24, 2008. Proceedings (Vol. 5259, pp. 696-707). (Lecture Notes in Computer Science; Vol. 5259). Springer-Verlag.

An Image Quality Metric Based on a Colour Appearance Model. / Cui, Li; Allen, Alistair.

Advanced Concepts for Intelligent Vision Systems: 10th International Conference, ACIVS 2008, Juan-les-Pins, France, October 20-24, 2008. Proceedings. ed. / S Bourenanne; W Philips; D Popescu; P Scheunders. Vol. 5259 Springer-Verlag, 2008. p. 696-707 (Lecture Notes in Computer Science; Vol. 5259).

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

Cui, L & Allen, A 2008, An Image Quality Metric Based on a Colour Appearance Model. in S Bourenanne, W Philips, D Popescu & P Scheunders (eds), Advanced Concepts for Intelligent Vision Systems: 10th International Conference, ACIVS 2008, Juan-les-Pins, France, October 20-24, 2008. Proceedings. vol. 5259, Lecture Notes in Computer Science, vol. 5259, Springer-Verlag, pp. 696-707.
Cui L, Allen A. An Image Quality Metric Based on a Colour Appearance Model. In Bourenanne S, Philips W, Popescu D, Scheunders P, editors, Advanced Concepts for Intelligent Vision Systems: 10th International Conference, ACIVS 2008, Juan-les-Pins, France, October 20-24, 2008. Proceedings. Vol. 5259. Springer-Verlag. 2008. p. 696-707. (Lecture Notes in Computer Science).
Cui, Li ; Allen, Alistair. / An Image Quality Metric Based on a Colour Appearance Model. Advanced Concepts for Intelligent Vision Systems: 10th International Conference, ACIVS 2008, Juan-les-Pins, France, October 20-24, 2008. Proceedings. editor / S Bourenanne ; W Philips ; D Popescu ; P Scheunders. Vol. 5259 Springer-Verlag, 2008. pp. 696-707 (Lecture Notes in Computer Science).
@inproceedings{0c1a55c0a78d4040a25159799cf543ec,
title = "An Image Quality Metric Based on a Colour Appearance Model",
abstract = "Image quality metrics have been widely used in imaging systemsto maintain and improve the quality of images being processed andtransmitted. Due to the close relationship between image quality and humanvisual perception, both computer scientists and psychologists havecontributed to the development of image quality metrics. In this paper,a novel image quality metric using a colour appearance model is proposed.After the physical colour stimuli of the images being comparedare transformed into perceptual colour appearance attributes, the distortionmeasures between the corresponding attributes are used to predictthe subjective scores of image quality, by use of data-driven models:Multiple Linear Regression (MLR), General Regression Neural Network(GRNN) and Back-Propagation Neural Network (BPNN). Based on thedata-driven model used, we have developed three image quality metrics,CAM MLR, CAM GRNN and CAM BPNN. The experiments haveshown that the performance of CAM BPNN is better than the wellknownimage quality metric SSIM.",
author = "Li Cui and Alistair Allen",
year = "2008",
language = "English",
isbn = "978-3-540-88457-6",
volume = "5259",
series = "Lecture Notes in Computer Science",
publisher = "Springer-Verlag",
pages = "696--707",
editor = "S Bourenanne and W Philips and D Popescu and P Scheunders",
booktitle = "Advanced Concepts for Intelligent Vision Systems",

}

TY - GEN

T1 - An Image Quality Metric Based on a Colour Appearance Model

AU - Cui, Li

AU - Allen, Alistair

PY - 2008

Y1 - 2008

N2 - Image quality metrics have been widely used in imaging systemsto maintain and improve the quality of images being processed andtransmitted. Due to the close relationship between image quality and humanvisual perception, both computer scientists and psychologists havecontributed to the development of image quality metrics. In this paper,a novel image quality metric using a colour appearance model is proposed.After the physical colour stimuli of the images being comparedare transformed into perceptual colour appearance attributes, the distortionmeasures between the corresponding attributes are used to predictthe subjective scores of image quality, by use of data-driven models:Multiple Linear Regression (MLR), General Regression Neural Network(GRNN) and Back-Propagation Neural Network (BPNN). Based on thedata-driven model used, we have developed three image quality metrics,CAM MLR, CAM GRNN and CAM BPNN. The experiments haveshown that the performance of CAM BPNN is better than the wellknownimage quality metric SSIM.

AB - Image quality metrics have been widely used in imaging systemsto maintain and improve the quality of images being processed andtransmitted. Due to the close relationship between image quality and humanvisual perception, both computer scientists and psychologists havecontributed to the development of image quality metrics. In this paper,a novel image quality metric using a colour appearance model is proposed.After the physical colour stimuli of the images being comparedare transformed into perceptual colour appearance attributes, the distortionmeasures between the corresponding attributes are used to predictthe subjective scores of image quality, by use of data-driven models:Multiple Linear Regression (MLR), General Regression Neural Network(GRNN) and Back-Propagation Neural Network (BPNN). Based on thedata-driven model used, we have developed three image quality metrics,CAM MLR, CAM GRNN and CAM BPNN. The experiments haveshown that the performance of CAM BPNN is better than the wellknownimage quality metric SSIM.

M3 - Conference contribution

SN - 978-3-540-88457-6

VL - 5259

T3 - Lecture Notes in Computer Science

SP - 696

EP - 707

BT - Advanced Concepts for Intelligent Vision Systems

A2 - Bourenanne, S

A2 - Philips, W

A2 - Popescu, D

A2 - Scheunders, P

PB - Springer-Verlag

ER -