Multi-scale structural similarity for image quality assessment

Zhou Wang, Eero Simoncelli, Alan C. Bovik

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

Abstract

The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multi-scale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.

Original languageEnglish (US)
Title of host publicationConference Record of the Asilomar Conference on Signals, Systems and Computers
EditorsM.B. Matthews
Pages1398-1402
Number of pages5
Volume2
StatePublished - 2003
EventConference Record of the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States
Duration: Nov 9 2003Nov 12 2003

Other

OtherConference Record of the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers
CountryUnited States
CityPacific Grove, CA
Period11/9/0311/12/03

Fingerprint

Image quality

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Hardware and Architecture

Cite this

Wang, Z., Simoncelli, E., & Bovik, A. C. (2003). Multi-scale structural similarity for image quality assessment. In M. B. Matthews (Ed.), Conference Record of the Asilomar Conference on Signals, Systems and Computers (Vol. 2, pp. 1398-1402)

Multi-scale structural similarity for image quality assessment. / Wang, Zhou; Simoncelli, Eero; Bovik, Alan C.

Conference Record of the Asilomar Conference on Signals, Systems and Computers. ed. / M.B. Matthews. Vol. 2 2003. p. 1398-1402.

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

Wang, Z, Simoncelli, E & Bovik, AC 2003, Multi-scale structural similarity for image quality assessment. in MB Matthews (ed.), Conference Record of the Asilomar Conference on Signals, Systems and Computers. vol. 2, pp. 1398-1402, Conference Record of the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, United States, 11/9/03.
Wang Z, Simoncelli E, Bovik AC. Multi-scale structural similarity for image quality assessment. In Matthews MB, editor, Conference Record of the Asilomar Conference on Signals, Systems and Computers. Vol. 2. 2003. p. 1398-1402
Wang, Zhou ; Simoncelli, Eero ; Bovik, Alan C. / Multi-scale structural similarity for image quality assessment. Conference Record of the Asilomar Conference on Signals, Systems and Computers. editor / M.B. Matthews. Vol. 2 2003. pp. 1398-1402
@inproceedings{583d8b59c51a4f3e9bd0b90731111848,
title = "Multi-scale structural similarity for image quality assessment",
abstract = "The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multi-scale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.",
author = "Zhou Wang and Eero Simoncelli and Bovik, {Alan C.}",
year = "2003",
language = "English (US)",
volume = "2",
pages = "1398--1402",
editor = "M.B. Matthews",
booktitle = "Conference Record of the Asilomar Conference on Signals, Systems and Computers",

}

TY - GEN

T1 - Multi-scale structural similarity for image quality assessment

AU - Wang, Zhou

AU - Simoncelli, Eero

AU - Bovik, Alan C.

PY - 2003

Y1 - 2003

N2 - The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multi-scale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.

AB - The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multi-scale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=4143089652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4143089652&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1398

EP - 1402

BT - Conference Record of the Asilomar Conference on Signals, Systems and Computers

A2 - Matthews, M.B.

ER -