Gradient magnitude similarity deviation on multiple scales for color image quality assessment

Bo Zhang, Pedro V. Sander, Amine Bermak

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

1 Citation (Scopus)

Abstract

Recently, various image quality assessment (IQA) metrics based on gradient similarity have been developed. In this paper, we extend the work of gradient magnitude similarity deviation (GMSD) and propose a more efficient metric. First, a novel similarity index is proposed, which gives the flexibility to tune the masking parameter to more closely match the human vision system (HVS). Then, we propose a multi-scale GMSD method by incorporating scores of luminance distortion at different scales. Furthermore, a method for measuring chromatic distortions in YIQ color space based on our metric is proposed. The final IQA index, MS-GMSDc, is obtained by combining luminance and chrominance scores. Experimental results on four comprehensive datasets clearly show that, compared with 14 state-of-the-art IQA methods, our method achieves the best performance for both grayscale and chromatic image assessment.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1253-1257
Number of pages5
ISBN (Electronic)9781509041176
DOIs
Publication statusPublished - 16 Jun 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: 5 Mar 20179 Mar 2017

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period5/3/179/3/17

Fingerprint

Image quality
Color
Luminance

Keywords

  • Chromatic Distortion
  • Gradient Magnitude Similarity
  • Image Quality Assessment (IQA)
  • Multi-scale

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Zhang, B., Sander, P. V., & Bermak, A. (2017). Gradient magnitude similarity deviation on multiple scales for color image quality assessment. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 1253-1257). [7952357] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952357

Gradient magnitude similarity deviation on multiple scales for color image quality assessment. / Zhang, Bo; Sander, Pedro V.; Bermak, Amine.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1253-1257 7952357.

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

Zhang, B, Sander, PV & Bermak, A 2017, Gradient magnitude similarity deviation on multiple scales for color image quality assessment. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952357, Institute of Electrical and Electronics Engineers Inc., pp. 1253-1257, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 5/3/17. https://doi.org/10.1109/ICASSP.2017.7952357
Zhang B, Sander PV, Bermak A. Gradient magnitude similarity deviation on multiple scales for color image quality assessment. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1253-1257. 7952357 https://doi.org/10.1109/ICASSP.2017.7952357
Zhang, Bo ; Sander, Pedro V. ; Bermak, Amine. / Gradient magnitude similarity deviation on multiple scales for color image quality assessment. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1253-1257
@inproceedings{9bc4497cbc774ae0b7358454042245a1,
title = "Gradient magnitude similarity deviation on multiple scales for color image quality assessment",
abstract = "Recently, various image quality assessment (IQA) metrics based on gradient similarity have been developed. In this paper, we extend the work of gradient magnitude similarity deviation (GMSD) and propose a more efficient metric. First, a novel similarity index is proposed, which gives the flexibility to tune the masking parameter to more closely match the human vision system (HVS). Then, we propose a multi-scale GMSD method by incorporating scores of luminance distortion at different scales. Furthermore, a method for measuring chromatic distortions in YIQ color space based on our metric is proposed. The final IQA index, MS-GMSDc, is obtained by combining luminance and chrominance scores. Experimental results on four comprehensive datasets clearly show that, compared with 14 state-of-the-art IQA methods, our method achieves the best performance for both grayscale and chromatic image assessment.",
keywords = "Chromatic Distortion, Gradient Magnitude Similarity, Image Quality Assessment (IQA), Multi-scale",
author = "Bo Zhang and Sander, {Pedro V.} and Amine Bermak",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/ICASSP.2017.7952357",
language = "English",
pages = "1253--1257",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Gradient magnitude similarity deviation on multiple scales for color image quality assessment

AU - Zhang, Bo

AU - Sander, Pedro V.

AU - Bermak, Amine

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Recently, various image quality assessment (IQA) metrics based on gradient similarity have been developed. In this paper, we extend the work of gradient magnitude similarity deviation (GMSD) and propose a more efficient metric. First, a novel similarity index is proposed, which gives the flexibility to tune the masking parameter to more closely match the human vision system (HVS). Then, we propose a multi-scale GMSD method by incorporating scores of luminance distortion at different scales. Furthermore, a method for measuring chromatic distortions in YIQ color space based on our metric is proposed. The final IQA index, MS-GMSDc, is obtained by combining luminance and chrominance scores. Experimental results on four comprehensive datasets clearly show that, compared with 14 state-of-the-art IQA methods, our method achieves the best performance for both grayscale and chromatic image assessment.

AB - Recently, various image quality assessment (IQA) metrics based on gradient similarity have been developed. In this paper, we extend the work of gradient magnitude similarity deviation (GMSD) and propose a more efficient metric. First, a novel similarity index is proposed, which gives the flexibility to tune the masking parameter to more closely match the human vision system (HVS). Then, we propose a multi-scale GMSD method by incorporating scores of luminance distortion at different scales. Furthermore, a method for measuring chromatic distortions in YIQ color space based on our metric is proposed. The final IQA index, MS-GMSDc, is obtained by combining luminance and chrominance scores. Experimental results on four comprehensive datasets clearly show that, compared with 14 state-of-the-art IQA methods, our method achieves the best performance for both grayscale and chromatic image assessment.

KW - Chromatic Distortion

KW - Gradient Magnitude Similarity

KW - Image Quality Assessment (IQA)

KW - Multi-scale

UR - http://www.scopus.com/inward/record.url?scp=85023776221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023776221&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952357

DO - 10.1109/ICASSP.2017.7952357

M3 - Conference contribution

AN - SCOPUS:85023776221

SP - 1253

EP - 1257

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -