No-reference image quality assessment in contourlet domain

Wen Lu, Kai Zeng, Dacheng Tao*, Yuan Yuan, Xinbo Gao

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

The target of no-reference (NR) image quality assessment (IQA) is to establish a computational model to predict the visual quality of an image. The existing prominent method is based on natural scene statistics (NSS). It uses the joint and marginal distributions of wavelet coefficients for IQA. However, this method is only applicable to JPEG2000 compressed images. Since the wavelet transform fails to capture the directional information of images, an improved NSS model is established by contourlets. In this paper, the contourlet transform is utilized to NSS of images, and then the relationship of contourlet coefficients is represented by the joint distribution. The statistics of contourlet coefficients are applicable to indicate variation of image quality. In addition, an image-dependent threshold is adopted to reduce the effect of content to the statistical model. Finally, image quality can be evaluated by combining the extracted features in each subband nonlinearly. Our algorithm is trained and tested on the LIVE database II. Experimental results demonstrate that the proposed algorithm is superior to the conventional NSS model and can be applied to different distortions.

Original languageEnglish
Pages (from-to)784-794
Number of pages11
JournalNeurocomputing
Volume73
Issue number4-6
Early online date20 Nov 2009
DOIs
Publication statusPublished - Jan 2010

Fingerprint

Image quality
Statistics
Wavelet Analysis
Statistical Models
Wavelet transforms
Joints
Databases

Bibliographical note

Bayesian Networks / Design and Application of Neural Networks and Intelligent Learning Systems (KES 2008 / Bio-inspired Computing: Theories and Applications (BIC-TA 2007)

Keywords

  • Contourlets
  • Image modeling
  • Image quality assessment
  • No reference

Cite this

Lu, Wen ; Zeng, Kai ; Tao, Dacheng ; Yuan, Yuan ; Gao, Xinbo. / No-reference image quality assessment in contourlet domain. In: Neurocomputing. 2010 ; Vol. 73, No. 4-6. pp. 784-794.
@article{f4f5e013fbf04331be33718dc0a33a35,
title = "No-reference image quality assessment in contourlet domain",
abstract = "The target of no-reference (NR) image quality assessment (IQA) is to establish a computational model to predict the visual quality of an image. The existing prominent method is based on natural scene statistics (NSS). It uses the joint and marginal distributions of wavelet coefficients for IQA. However, this method is only applicable to JPEG2000 compressed images. Since the wavelet transform fails to capture the directional information of images, an improved NSS model is established by contourlets. In this paper, the contourlet transform is utilized to NSS of images, and then the relationship of contourlet coefficients is represented by the joint distribution. The statistics of contourlet coefficients are applicable to indicate variation of image quality. In addition, an image-dependent threshold is adopted to reduce the effect of content to the statistical model. Finally, image quality can be evaluated by combining the extracted features in each subband nonlinearly. Our algorithm is trained and tested on the LIVE database II. Experimental results demonstrate that the proposed algorithm is superior to the conventional NSS model and can be applied to different distortions.",
keywords = "Contourlets, Image modeling, Image quality assessment, No reference",
author = "Wen Lu and Kai Zeng and Dacheng Tao and Yuan Yuan and Xinbo Gao",
note = "Bayesian Networks / Design and Application of Neural Networks and Intelligent Learning Systems (KES 2008 / Bio-inspired Computing: Theories and Applications (BIC-TA 2007)",
year = "2010",
month = "1",
doi = "10.1016/j.neucom.2009.10.012",
language = "English",
volume = "73",
pages = "784--794",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "4-6",

}

Lu, W, Zeng, K, Tao, D, Yuan, Y & Gao, X 2010, 'No-reference image quality assessment in contourlet domain', Neurocomputing, vol. 73, no. 4-6, pp. 784-794. https://doi.org/10.1016/j.neucom.2009.10.012

No-reference image quality assessment in contourlet domain. / Lu, Wen; Zeng, Kai; Tao, Dacheng; Yuan, Yuan; Gao, Xinbo.

In: Neurocomputing, Vol. 73, No. 4-6, 01.2010, p. 784-794.

Research output: Contribution to journalArticle

TY - JOUR

T1 - No-reference image quality assessment in contourlet domain

AU - Lu, Wen

AU - Zeng, Kai

AU - Tao, Dacheng

AU - Yuan, Yuan

AU - Gao, Xinbo

N1 - Bayesian Networks / Design and Application of Neural Networks and Intelligent Learning Systems (KES 2008 / Bio-inspired Computing: Theories and Applications (BIC-TA 2007)

PY - 2010/1

Y1 - 2010/1

N2 - The target of no-reference (NR) image quality assessment (IQA) is to establish a computational model to predict the visual quality of an image. The existing prominent method is based on natural scene statistics (NSS). It uses the joint and marginal distributions of wavelet coefficients for IQA. However, this method is only applicable to JPEG2000 compressed images. Since the wavelet transform fails to capture the directional information of images, an improved NSS model is established by contourlets. In this paper, the contourlet transform is utilized to NSS of images, and then the relationship of contourlet coefficients is represented by the joint distribution. The statistics of contourlet coefficients are applicable to indicate variation of image quality. In addition, an image-dependent threshold is adopted to reduce the effect of content to the statistical model. Finally, image quality can be evaluated by combining the extracted features in each subband nonlinearly. Our algorithm is trained and tested on the LIVE database II. Experimental results demonstrate that the proposed algorithm is superior to the conventional NSS model and can be applied to different distortions.

AB - The target of no-reference (NR) image quality assessment (IQA) is to establish a computational model to predict the visual quality of an image. The existing prominent method is based on natural scene statistics (NSS). It uses the joint and marginal distributions of wavelet coefficients for IQA. However, this method is only applicable to JPEG2000 compressed images. Since the wavelet transform fails to capture the directional information of images, an improved NSS model is established by contourlets. In this paper, the contourlet transform is utilized to NSS of images, and then the relationship of contourlet coefficients is represented by the joint distribution. The statistics of contourlet coefficients are applicable to indicate variation of image quality. In addition, an image-dependent threshold is adopted to reduce the effect of content to the statistical model. Finally, image quality can be evaluated by combining the extracted features in each subband nonlinearly. Our algorithm is trained and tested on the LIVE database II. Experimental results demonstrate that the proposed algorithm is superior to the conventional NSS model and can be applied to different distortions.

KW - Contourlets

KW - Image modeling

KW - Image quality assessment

KW - No reference

UR - http://www.scopus.com/inward/record.url?scp=75749156539&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2009.10.012

DO - 10.1016/j.neucom.2009.10.012

M3 - Article

AN - SCOPUS:75749156539

VL - 73

SP - 784

EP - 794

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 4-6

ER -