No reference image quality assessment based on subbands similarity and statistical analysis for JPEG2000

Ying Chun Guo, Ming Yu, Qiuming Zhu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

For undistorted images, the wavelet coefficients of between-scale coefficients in the same orientation are correlated, while compression coding reduce the correlation. Cosine similarity is used in this work to model the correlation of between-scale subbands, and statistical regression is applied to analyze the relationship between human subjective assessment Mean Opinion Scores (MOS) and subbands cosine similarity. The accurate quality model is obtained by regression analysis. Experimental results show that the proposed no-reference method has a high correlation with the MOS measurement, and a considerably lower computational complexity and less run time.

Original languageEnglish (US)
Pages (from-to)1496-1500
Number of pages5
JournalDianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology
Volume33
Issue number6
DOIs
StatePublished - Jun 1 2011

Fingerprint

Image quality
Statistical methods
Regression analysis
Computational complexity

Keywords

  • Cosine similarity
  • Image processing
  • JPEG2000
  • No-reference Image quality assessment
  • Statistical analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

No reference image quality assessment based on subbands similarity and statistical analysis for JPEG2000. / Guo, Ying Chun; Yu, Ming; Zhu, Qiuming.

In: Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, Vol. 33, No. 6, 01.06.2011, p. 1496-1500.

Research output: Contribution to journalArticle

@article{8234ce9e11d1493da3e478a57ece38d1,
title = "No reference image quality assessment based on subbands similarity and statistical analysis for JPEG2000",
abstract = "For undistorted images, the wavelet coefficients of between-scale coefficients in the same orientation are correlated, while compression coding reduce the correlation. Cosine similarity is used in this work to model the correlation of between-scale subbands, and statistical regression is applied to analyze the relationship between human subjective assessment Mean Opinion Scores (MOS) and subbands cosine similarity. The accurate quality model is obtained by regression analysis. Experimental results show that the proposed no-reference method has a high correlation with the MOS measurement, and a considerably lower computational complexity and less run time.",
keywords = "Cosine similarity, Image processing, JPEG2000, No-reference Image quality assessment, Statistical analysis",
author = "Guo, {Ying Chun} and Ming Yu and Qiuming Zhu",
year = "2011",
month = "6",
day = "1",
doi = "10.3724/SP.J.1146.2010.00890",
language = "English (US)",
volume = "33",
pages = "1496--1500",
journal = "Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology",
issn = "1009-5896",
publisher = "Science Press",
number = "6",

}

TY - JOUR

T1 - No reference image quality assessment based on subbands similarity and statistical analysis for JPEG2000

AU - Guo, Ying Chun

AU - Yu, Ming

AU - Zhu, Qiuming

PY - 2011/6/1

Y1 - 2011/6/1

N2 - For undistorted images, the wavelet coefficients of between-scale coefficients in the same orientation are correlated, while compression coding reduce the correlation. Cosine similarity is used in this work to model the correlation of between-scale subbands, and statistical regression is applied to analyze the relationship between human subjective assessment Mean Opinion Scores (MOS) and subbands cosine similarity. The accurate quality model is obtained by regression analysis. Experimental results show that the proposed no-reference method has a high correlation with the MOS measurement, and a considerably lower computational complexity and less run time.

AB - For undistorted images, the wavelet coefficients of between-scale coefficients in the same orientation are correlated, while compression coding reduce the correlation. Cosine similarity is used in this work to model the correlation of between-scale subbands, and statistical regression is applied to analyze the relationship between human subjective assessment Mean Opinion Scores (MOS) and subbands cosine similarity. The accurate quality model is obtained by regression analysis. Experimental results show that the proposed no-reference method has a high correlation with the MOS measurement, and a considerably lower computational complexity and less run time.

KW - Cosine similarity

KW - Image processing

KW - JPEG2000

KW - No-reference Image quality assessment

KW - Statistical analysis

UR - http://www.scopus.com/inward/record.url?scp=79959862657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959862657&partnerID=8YFLogxK

U2 - 10.3724/SP.J.1146.2010.00890

DO - 10.3724/SP.J.1146.2010.00890

M3 - Article

VL - 33

SP - 1496

EP - 1500

JO - Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology

JF - Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology

SN - 1009-5896

IS - 6

ER -