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 language | English (US) |
---|---|
Title of host publication | Proceedings - International Conference on Image Processing, ICIP |
Publisher | IEEE Computer Society |
Pages | 4117-4120 |
Number of pages | 4 |
Volume | 2015-December |
ISBN (Print) | 9781479983391 |
DOIs | |
State | Published - Dec 9 2015 |
Event | IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada Duration: Sep 27 2015 → Sep 30 2015 |
Other
Other | IEEE International Conference on Image Processing, ICIP 2015 |
---|---|
Country | Canada |
City | Quebec City |
Period | 9/27/15 → 9/30/15 |
Fingerprint
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
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 proceeding › Conference contribution
}
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 -