Reduced-Reference Quality Assessment Based on the Entropy of DWT Coefficients of Locally Weighted Gradient Magnitudes

Seyedalireza Golestaneh, Lina Karam

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Perceptual image quality assessment (IQA) attempts to use computational models to estimate the image quality in accordance with subjective evaluations. Reduced-reference IQA (RRIQA) 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 accuracy of the estimated image quality is essential and important in IQA. In this paper, we propose a training-free low-cost RRIQA method that requires a very small number of RR features (six RR features). The proposed RRIQA algorithm is based on the discrete wavelet transform (DWT) of locally weighted gradient magnitudes. We apply human visual system's contrast sensitivity and neighborhood gradient information to weight the gradient magnitudes in a locally adaptive manner. The RR features are computed by measuring the entropy of each DWT subband, for each scale, and pooling the subband entropies along all orientations, resulting in $L$ RR features (one average entropy per scale) for an $L$-level DWT. Extensive experiments performed on seven large-scale benchmark databases demonstrate that the proposed RRIQA method delivers highly competitive performance as compared with the state-of-the-art RRIQA models as well as full reference ones for both natural and texture images.

Original languageEnglish (US)
Article number7548344
Pages (from-to)5293-5303
Number of pages11
JournalIEEE Transactions on Image Processing
Volume25
Issue number11
DOIs
StatePublished - Nov 1 2016

Fingerprint

Wavelet Analysis
Discrete wavelet transforms
Entropy
Image quality
Benchmarking
Contrast Sensitivity
Databases
Weights and Measures
Costs and Cost Analysis
Textures
Costs
Experiments

Keywords

  • contrast sensitivity
  • Discrete wavelet transform
  • entropy
  • gradient magnitude
  • locally adaptive weighting
  • Reduced reference quality assessment (RRIQA)

ASJC Scopus subject areas

  • Software
  • Medicine(all)
  • Computer Graphics and Computer-Aided Design

Cite this

Reduced-Reference Quality Assessment Based on the Entropy of DWT Coefficients of Locally Weighted Gradient Magnitudes. / Golestaneh, Seyedalireza; Karam, Lina.

In: IEEE Transactions on Image Processing, Vol. 25, No. 11, 7548344, 01.11.2016, p. 5293-5303.

Research output: Contribution to journalArticle

@article{3dab4311e95349939fbe25e8af02b1fd,
title = "Reduced-Reference Quality Assessment Based on the Entropy of DWT Coefficients of Locally Weighted Gradient Magnitudes",
abstract = "Perceptual image quality assessment (IQA) attempts to use computational models to estimate the image quality in accordance with subjective evaluations. Reduced-reference IQA (RRIQA) 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 accuracy of the estimated image quality is essential and important in IQA. In this paper, we propose a training-free low-cost RRIQA method that requires a very small number of RR features (six RR features). The proposed RRIQA algorithm is based on the discrete wavelet transform (DWT) of locally weighted gradient magnitudes. We apply human visual system's contrast sensitivity and neighborhood gradient information to weight the gradient magnitudes in a locally adaptive manner. The RR features are computed by measuring the entropy of each DWT subband, for each scale, and pooling the subband entropies along all orientations, resulting in $L$ RR features (one average entropy per scale) for an $L$-level DWT. Extensive experiments performed on seven large-scale benchmark databases demonstrate that the proposed RRIQA method delivers highly competitive performance as compared with the state-of-the-art RRIQA models as well as full reference ones for both natural and texture images.",
keywords = "contrast sensitivity, Discrete wavelet transform, entropy, gradient magnitude, locally adaptive weighting, Reduced reference quality assessment (RRIQA)",
author = "Seyedalireza Golestaneh and Lina Karam",
year = "2016",
month = "11",
day = "1",
doi = "10.1109/TIP.2016.2601821",
language = "English (US)",
volume = "25",
pages = "5293--5303",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - Reduced-Reference Quality Assessment Based on the Entropy of DWT Coefficients of Locally Weighted Gradient Magnitudes

AU - Golestaneh, Seyedalireza

AU - Karam, Lina

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Perceptual image quality assessment (IQA) attempts to use computational models to estimate the image quality in accordance with subjective evaluations. Reduced-reference IQA (RRIQA) 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 accuracy of the estimated image quality is essential and important in IQA. In this paper, we propose a training-free low-cost RRIQA method that requires a very small number of RR features (six RR features). The proposed RRIQA algorithm is based on the discrete wavelet transform (DWT) of locally weighted gradient magnitudes. We apply human visual system's contrast sensitivity and neighborhood gradient information to weight the gradient magnitudes in a locally adaptive manner. The RR features are computed by measuring the entropy of each DWT subband, for each scale, and pooling the subband entropies along all orientations, resulting in $L$ RR features (one average entropy per scale) for an $L$-level DWT. Extensive experiments performed on seven large-scale benchmark databases demonstrate that the proposed RRIQA method delivers highly competitive performance as compared with the state-of-the-art RRIQA models as well as full reference ones for both natural and texture images.

AB - Perceptual image quality assessment (IQA) attempts to use computational models to estimate the image quality in accordance with subjective evaluations. Reduced-reference IQA (RRIQA) 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 accuracy of the estimated image quality is essential and important in IQA. In this paper, we propose a training-free low-cost RRIQA method that requires a very small number of RR features (six RR features). The proposed RRIQA algorithm is based on the discrete wavelet transform (DWT) of locally weighted gradient magnitudes. We apply human visual system's contrast sensitivity and neighborhood gradient information to weight the gradient magnitudes in a locally adaptive manner. The RR features are computed by measuring the entropy of each DWT subband, for each scale, and pooling the subband entropies along all orientations, resulting in $L$ RR features (one average entropy per scale) for an $L$-level DWT. Extensive experiments performed on seven large-scale benchmark databases demonstrate that the proposed RRIQA method delivers highly competitive performance as compared with the state-of-the-art RRIQA models as well as full reference ones for both natural and texture images.

KW - contrast sensitivity

KW - Discrete wavelet transform

KW - entropy

KW - gradient magnitude

KW - locally adaptive weighting

KW - Reduced reference quality assessment (RRIQA)

UR - http://www.scopus.com/inward/record.url?scp=84991106828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991106828&partnerID=8YFLogxK

U2 - 10.1109/TIP.2016.2601821

DO - 10.1109/TIP.2016.2601821

M3 - Article

VL - 25

SP - 5293

EP - 5303

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 11

M1 - 7548344

ER -