Reduced-reference quality assessment based on the entropy of DNT coefficients of locally weighted gradients

S. Alireza Golestaneh, Lina Karam

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

7 Citations (Scopus)

Abstract

Reduced-reference (RR) image quality assessment (IQA) methods make use of partial information or features extracted from the reference image for estimating the quality of distorted images. Finding a balance between the number of RR features and image quality estimation accuracy is a difficult task. This paper presents a training-free low cost RRIQA method which requires a very small number of RR features (6 RR features). The proposed RRIQA algorithm is based on the divisive normalization transform (DNT) of locally weighted gradient magnitudes. The weighting of the gradient magnitudes is performed in a locally adaptive manner based on the human visual system's contrast sensitivity and neighborhood gradient information. The RR features are obtained by computing the entropy of each DNT subband and, for each scale, averaging the subband entropies along all orientations, resulting in L RR features (one average entropy per scale) for an L-level DNT. Performance evaluations on four large-scale benchmark databases demonstrates that the proposed RRIQA method delivers highly competitive performance as compared to the state-of-the-art RRIQA models as well as full reference ones.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Processing, ICIP
PublisherIEEE Computer Society
Pages4117-4120
Number of pages4
Volume2015-December
ISBN (Print)9781479983391
DOIs
StatePublished - Dec 9 2015
EventIEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada
Duration: Sep 27 2015Sep 30 2015

Other

OtherIEEE International Conference on Image Processing, ICIP 2015
CountryCanada
CityQuebec City
Period9/27/159/30/15

Fingerprint

Entropy
Image quality
Costs

Keywords

  • contrast sensitivity function (CSF)
  • divisive normalization transform
  • entropy
  • Gaussian filtering
  • Reduced reference quality assessment (RRIQA)

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Golestaneh, S. A., & Karam, L. (2015). Reduced-reference quality assessment based on the entropy of DNT coefficients of locally weighted gradients. In Proceedings - International Conference on Image Processing, ICIP (Vol. 2015-December, pp. 4117-4120). [7351580] IEEE Computer Society. https://doi.org/10.1109/ICIP.2015.7351580

Reduced-reference quality assessment based on the entropy of DNT coefficients of locally weighted gradients. / Golestaneh, S. Alireza; Karam, Lina.

Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE Computer Society, 2015. p. 4117-4120 7351580.

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

Golestaneh, SA & Karam, L 2015, Reduced-reference quality assessment based on the entropy of DNT coefficients of locally weighted gradients. in Proceedings - International Conference on Image Processing, ICIP. vol. 2015-December, 7351580, IEEE Computer Society, pp. 4117-4120, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 9/27/15. https://doi.org/10.1109/ICIP.2015.7351580
Golestaneh SA, Karam L. Reduced-reference quality assessment based on the entropy of DNT coefficients of locally weighted gradients. In Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December. IEEE Computer Society. 2015. p. 4117-4120. 7351580 https://doi.org/10.1109/ICIP.2015.7351580
Golestaneh, S. Alireza ; Karam, Lina. / Reduced-reference quality assessment based on the entropy of DNT coefficients of locally weighted gradients. Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE Computer Society, 2015. pp. 4117-4120
@inproceedings{dbe15dbabfcb4c63ab8958083cb49e6c,
title = "Reduced-reference quality assessment based on the entropy of DNT coefficients of locally weighted gradients",
abstract = "Reduced-reference (RR) image quality assessment (IQA) methods make use of partial information or features extracted from the reference image for estimating the quality of distorted images. Finding a balance between the number of RR features and image quality estimation accuracy is a difficult task. This paper presents a training-free low cost RRIQA method which requires a very small number of RR features (6 RR features). The proposed RRIQA algorithm is based on the divisive normalization transform (DNT) of locally weighted gradient magnitudes. The weighting of the gradient magnitudes is performed in a locally adaptive manner based on the human visual system's contrast sensitivity and neighborhood gradient information. The RR features are obtained by computing the entropy of each DNT subband and, for each scale, averaging the subband entropies along all orientations, resulting in L RR features (one average entropy per scale) for an L-level DNT. Performance evaluations on four large-scale benchmark databases demonstrates that the proposed RRIQA method delivers highly competitive performance as compared to the state-of-the-art RRIQA models as well as full reference ones.",
keywords = "contrast sensitivity function (CSF), divisive normalization transform, entropy, Gaussian filtering, Reduced reference quality assessment (RRIQA)",
author = "Golestaneh, {S. Alireza} and Lina Karam",
year = "2015",
month = "12",
day = "9",
doi = "10.1109/ICIP.2015.7351580",
language = "English (US)",
isbn = "9781479983391",
volume = "2015-December",
pages = "4117--4120",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Reduced-reference quality assessment based on the entropy of DNT coefficients of locally weighted gradients

AU - Golestaneh, S. Alireza

AU - Karam, Lina

PY - 2015/12/9

Y1 - 2015/12/9

N2 - Reduced-reference (RR) image quality assessment (IQA) methods make use of partial information or features extracted from the reference image for estimating the quality of distorted images. Finding a balance between the number of RR features and image quality estimation accuracy is a difficult task. This paper presents a training-free low cost RRIQA method which requires a very small number of RR features (6 RR features). The proposed RRIQA algorithm is based on the divisive normalization transform (DNT) of locally weighted gradient magnitudes. The weighting of the gradient magnitudes is performed in a locally adaptive manner based on the human visual system's contrast sensitivity and neighborhood gradient information. The RR features are obtained by computing the entropy of each DNT subband and, for each scale, averaging the subband entropies along all orientations, resulting in L RR features (one average entropy per scale) for an L-level DNT. Performance evaluations on four large-scale benchmark databases demonstrates that the proposed RRIQA method delivers highly competitive performance as compared to the state-of-the-art RRIQA models as well as full reference ones.

AB - Reduced-reference (RR) image quality assessment (IQA) methods make use of partial information or features extracted from the reference image for estimating the quality of distorted images. Finding a balance between the number of RR features and image quality estimation accuracy is a difficult task. This paper presents a training-free low cost RRIQA method which requires a very small number of RR features (6 RR features). The proposed RRIQA algorithm is based on the divisive normalization transform (DNT) of locally weighted gradient magnitudes. The weighting of the gradient magnitudes is performed in a locally adaptive manner based on the human visual system's contrast sensitivity and neighborhood gradient information. The RR features are obtained by computing the entropy of each DNT subband and, for each scale, averaging the subband entropies along all orientations, resulting in L RR features (one average entropy per scale) for an L-level DNT. Performance evaluations on four large-scale benchmark databases demonstrates that the proposed RRIQA method delivers highly competitive performance as compared to the state-of-the-art RRIQA models as well as full reference ones.

KW - contrast sensitivity function (CSF)

KW - divisive normalization transform

KW - entropy

KW - Gaussian filtering

KW - Reduced reference quality assessment (RRIQA)

UR - http://www.scopus.com/inward/record.url?scp=84956624573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956624573&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351580

DO - 10.1109/ICIP.2015.7351580

M3 - Conference contribution

AN - SCOPUS:84956624573

SN - 9781479983391

VL - 2015-December

SP - 4117

EP - 4120

BT - Proceedings - International Conference on Image Processing, ICIP

PB - IEEE Computer Society

ER -