RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment
Abstract
We study the problem of automatic "reduced-reference" image quality assessment (QA) algorithms from the point of view of image information change. Such changes are measured between the reference- and natural-image approximations of the distorted image. Algorithms that measure differences between the entropies of wavelet coefficients of reference and distorted images, as perceived by humans, are designed. The algorithms differ in the data on which the entropy difference is calculated and on the amount of information from the reference that is required for quality computation, ranging from almost full information to almost no information from the reference. A special case of these is algorithms that require just a single number from the reference for QA. The algorithms are shown to correlate very well with subjective quality scores, as demonstrated on the Laboratory for Image and Video Engineering Image Quality Assessment Database and the Tampere Image Database. Performance degradation, as the amount of information is reduced, is also studied.
AI snapshot
Written from the paper’s full text.
TL;DR
The paper introduces RRED indices, reduced-reference image quality assessment algorithms that measure average absolute differences between scaled wavelet-domain entropies of a reference image and a Gaussian-scale-mixture natural-image approximation of the distorted image. Across LIVE and TID2008, the indices correlate well with subjective scores and degrade gracefully as reference information is reduced, with some variants approaching full-reference performance.
Key findings
- On LIVE, RRED M16/16 achieved overall SROCC 0.9429 and LCC 0.9385 using L/36 scalars, compared with PSNR SROCC 0.8754 and VIF (FR) SROCC 0.9636; RRED M10/10 achieved overall SROCC 0.9343 using L/144 scalars.
- Filtering and subsampling reduced reference information but degraded overall SROCC from 0.9429 at L/36 to 0.8543 at L/9296.
- Single-number algorithms had overall SROCC 0.7682 for σ²W = 0, 0.7978 for σ²W = 0.1, and 0.8877 for σ²W = 1; RRED* using 4 numbers achieved overall SROCC 0.8606, outperforming WNISM (0.7651) but below Curvelet (0.9104) and HWD2 (0.9418).
- On TID2008, RRED M16/16 achieved overall SROCC 0.824, above VIF (0.750), VSNR (0.705), PSNR (0.553), and WNISM (0.512), but below MSSIM (0.853); RRED 1/22 achieved 0.521.
Methods
- The RRED family computes the average absolute difference between scaled entropies of wavelet coefficients after an additive Gaussian neural noise channel, modeling both reference and distorted wavelet coefficients as Gaussian scale mixtures; algorithms vary by subband and by the amount of reference information via filtering/subsampling.
- Experiments used LIVE (779 distorted images, five distortion categories) and TID2008 (17 distortion types, 1700 distorted images), with a steerable pyramid decomposition using 6 orientations at 4 scales (25 subbands), 3×3 blocks (N = 9), and σ²W = 0.1 except in the single-number noise study; parameters were estimated by maximum likelihood without database training.
- Performance was assessed with Spearman rank-order correlation (SROCC) and linear correlation coefficient (LCC) after logistic nonlinearity against subjective DMOS/MOS, compared with PSNR, VIF, MSSIM, VSNR, WNISM, Curvelet, and HWD2.
Limitations
- The paper states that overall performance of single-number algorithms may be improved by better aligning scores across distortion categories, that multiscale decomposition increases complexity and needs efficient implementations, and that dependence on viewing distance requires better understanding; future work includes video.
- The paper reports that performance degrades with subsampling and that single-number algorithms are sensitive to neural noise variance; Gaussian blur performance decreases as σ²W increases (0.9698 at 0, 0.9038 at 0.1, 0.6108 at 1).
- Evident from reported tables, though not framed as limitations by the authors: RRED* overall SROCC 0.8606 is lower than Curvelet 0.9104 and HWD2 0.9418 on LIVE, and TID2008 RRED M16/16 is below MSSIM overall (0.824 vs 0.853) with low SROCC for mean shift (0.538) and contrast change (0.542).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
0 of 16 cited sources checked · 0 supported · 0 flagged
- Findingown data§ C. RR Quality Index · p. 9
Filtering and subsampling scaled entropy terms over patches results in loss of performance with subsampling.
“This procedure results in loss of performance with subsampling as illustrated in Section V.”
Quote in the paperNot a substantial claim- The authors state this as an assumption: Non-overlapping blocks of wavelet coefficients are independent and identically distributed.
- Findingown data§ V. RESULTS AND DISCUSSION · p. 17
The RRED indices that require only a single number from the reference are more sensitive to the choice of the neural noise variance.
“It turns out that these algorithms are more sensitive to the choice of the neural noise variance.”
Quote in the paperSubstantial claim - Findingown data§ V. RESULTS AND DISCUSSION · p. 13
Choosing vertical subbands yields marginally better performance than choosing horizontal subbands.
“Further, we observe that the performance obtained by choosing the vertical subbands is marginally better than the horizontal subbands.”
Quote in the paperNot a substantial claim - Findingown data§ V. RESULTS AND DISCUSSION · p. 15
As the RRED indices are evaluated in finer scales, they provide a better separation of quality scores.
“As we move from (a) to (d), the RRED indices are now evaluated in finer scales, which provide a better separation of quality scores.”
Quote in the paperSubstantial claim - Findingnone given§ VI. CONCLUSION · p. 20
Even when only a single scalar is obtained from the reference image, the algorithm achieves close to state of the art performance within each distortion category without knowing anything about the type of distortions.
“Even when only a single scalar is obtained from the reference image, the algorithm achieves close to state of the art performance within each distortion category without knowing anything about the type of distortions that the image might have been subjected to.”
Quote in the paperSubstantial claim
- Findingnone given§ VI. CONCLUSION · p. 20
The algorithms perform much better than mean squared error, which is a full-reference algorithm.
“Moreover, the algorithms perform much better than mean squared error, which is an FR algorithm.”
Quote in the paperSubstantial claim - Findingreasoning§ V. RESULTS AND DISCUSSION · p. 16
Certain distortions such as JPEG and JPEG2000 lead to different locations in the same subband having an increase and decrease in entropy simultaneously.
“Certain distortions such as JPEG and JPEG2000 lead to different locations in the same subband having an increase and decrease in entropy simultaneously.”
Quote in the paperSubstantial claim - Findingnone given§ V. RESULTS AND DISCUSSION · p. 15
The only drawback of the algorithm evaluated in subband 10 is reduced performance in the category of images corrupted by fast fading errors.
“The only drawback of the algorithm is the reduced performance in the category of images corrupted by fast fading errors.”
Quote in the paperNot a substantial claim - Findingown data§ V. RESULTS AND DISCUSSION · p. 13
Some RRED indices perform nearly as well as the best performing full-reference QA algorithms such as VIF.
“One important observation is that some of the RRED indices perform nearly as well as the best performing FR QA algorithms such as VIF.”
Quote in the paperSubstantial claim - Findingown data§ V. RESULTS AND DISCUSSION · p. 16
The performance of the RR algorithms degrades with subsampling.
“Table III clearly demonstrates the degradation in the performance of the RR algorithms with subsampling.”
Quote in the paperSubstantial claim - Findingreasoning§ V. RESULTS AND DISCUSSION · p. 18
The overall computational complexity of the RRED algorithms is O(N(log N + M^2)).
“Thus the overall computational complexity of the RRED algorithms is O ( N (log N + M 2 )) .”
Quote in the paperNot a substantial claim - Findingown data§ V. RESULTS AND DISCUSSION · p. 14
Subbands at certain scales are more sensitive to particular distortions or artifacts.
“The correlation analysis reveals that subbands at certain scales are more sensitive to particular distortions or artifacts.”
Quote in the paperSubstantial claim - Findingown data§ V. RESULTS AND DISCUSSION · p. 17
By using 4 numbers from the four vertical subbands at different scales of the reference and weighting the bands from coarser to finer scales in the ratio 8:4:2:1, the overall SROCC for σ_W^2 = 0.1 can be improved to 0.8606.
“For example, by using 4 numbers from the four vertical subbands at different scales of the reference, we can improve the overall SROCC for σ 2 W = 0 . 1 to 0.8606 by weighting the bands from coarser scales to the finer scales in the ratio 8:4:2:1.”
Quote in the paperNot a substantial claim - Findingown data§ V. RESULTS AND DISCUSSION · p. 20
One of the bottlenecks in the computation of the RRED indices is the time required to perform a multiscale multiorientation decomposition using steerable pyramids, which requires 1.5-1.6 seconds.
“One of the bottle necks in the computation of the RRED indices is the time required to perform a multiscale multiorientation decomposition using steerable pyramids, which requires 1.5-1.6 seconds.”
Quote in the paperNot a substantial claim - Findingnone given§ V. RESULTS AND DISCUSSION · p. 17
The RRED* algorithm still achieves excellent performance within each distortion category.
“This algorithm still achieves excellent performance within each distortion category.”
Quote in the paperSubstantial claim - Findingnone given§ V. RESULTS AND DISCUSSION · p. 15
The performance of the subband at the second finest scale (subband 16) is uniformly very good for all distortion types and on the overall database.
“Also, we observe that the performance of the subband at the second finest scale (subband 16) is uniformly very good for all distortion types and on the overall database.”
Quote in the paperNot a substantial claim - Findingown data§ V. RESULTS AND DISCUSSION · p. 13
For images distorted by Gaussian noise, the performance of the RRED indices is comparable with that of PSNR, a full-reference algorithm.
“Even for images distorted by Gaussian noise, the performance of the RRED indices is comparable with that of PSNR, which is an FR algorithm.”
Quote in the paperSubstantial claim - Findingnone given§ VI. CONCLUSION · p. 20
When the number of scalars required is around 1/40 of the image size, the algorithm achieves a performance nearly as good as the best performing full-reference QA algorithms.
“When the number of scalars required is around 1/40 of the image size, the algorithm achieves a performance which is nearly as good as the best performing full reference QA algorithms.”
Quote in the paperSubstantial claim - Findingnone given§ V. RESULTS AND DISCUSSION · p. 13
The performance of the algorithms in the RRED framework is robust to the choice of the neural noise variance, especially when there is high information from the reference.
“The performance of the algorithms in the RRED framework has proved to be robust to the choice of the neural noise variance, especially in the regime of high information from the reference.”
Quote in the paperNot a substantial claim - Findingreasoning§ V. RESULTS AND DISCUSSION · p. 15
The outliers in (a), (b) and (c) correspond to images containing a large area of high frequency textured regions.
“The outliers in (a), (b) and (c) correspond to images containing a large area of high frequency textured regions.”
Quote in the paperNot a substantial claim - Premisecitation§ I. INTRODUCTION · p. 2
Mean squared error has a very poor correlation with human perception.
“The mean squared error (MSE) has been used as a quality metric for a very long time, owing to its simplicity, despite having a very poor correlation with human perception [1].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [1] [1] Z. Wang and A. C. Bovik, 'Mean squared error: Love it or leave it? - A new look at signal fidelity measures,' IEEE Signal Processing Magazine , vol. 26, no. 1, pp. 98-117, Jan. 2009. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Interpretationreasoning§ I. INTRODUCTION · p. 3
The proposed quality index, based on the absolute difference, does not indicate which of the two images is the reference image.
“Of course, since the quality index is based on the absolute difference, it does not indicate which of the two images is the reference image.”
Quote in the paperNot a substantial claim - Premisecitation§ I. INTRODUCTION · p. 3
The performances of multiscale geometric analysis algorithms degrade severely with reduction in the data rate required from the reference.
“Moreover, their performances degrade severely with the reduction in the data rate required from the reference.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [15] [15] X. Gao, W. Lu, D. Tao, and X. Li, 'Image quality assessment based on multiscale geometric analysis,' IEEE Transactions on Image Processing , vol. 18, no. 7, pp. 1409-1423, 2009. - source
Not checked in the free run.
- Premisecitation§ I. INTRODUCTION · p. 2
The blind image quality assessment index based on Renyi entropy anisotropy has not been thoroughly evaluated on a large and comprehensive dataset.
“In [11], blind image quality assessment indices that measure the anisotropy in the distorted image through the Renyi entropy are introduced. However, performance of this index has not been thoroughly evaluated on a large and comprehensive dataset.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [11] [11] S. Gabarda and G. Cristobal, 'Blind image quality assessment through anisotropy,' J. Opt. Soc. Amer. A , vol. 24, pp. B42-B51, 2007. - source
Not checked in the free run.
- Interpretationnone given§ I. INTRODUCTION · p. 3
The proposed RRED algorithms are not dependent on any parameters that need to be trained on databases.
“Another interesting feature of these algorithms is that they are not dependent on any parameters that need to be trained on databases.”
Quote in the paperSubstantial claim - Interpretationcitation§ I. INTRODUCTION · p. 3
The proposed algorithms are applicable in scalable image and video QA because the reference information scales with the size of the images.
“Since, the reference information scales with the size of the images, the algorithms are also applicable in scalable image and video QA [21].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [21] [21] K. Seshadrinathan and A. C. Bovik, 'Multi-scale and scalable video quality assessment,' in Proc. IEEE Int Conf on Consumer Electronics , Las Vegas, NV, 2008. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Interpretationreasoning§ C. RR Quality Index · p. 8
The RRED indices are always positive.
“This also implies that the RRED indices are always positive.”
Quote in the paperNot a substantial claim - Premisecitation§ I. INTRODUCTION · p. 3
Multiscale geometric analysis algorithms depend on parameters that need to be tuned delicately on different databases.
“These algorithms depend on parameters that need to be tuned delicately on different databases.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [15] [15] X. Gao, W. Lu, D. Tao, and X. Li, 'Image quality assessment based on multiscale geometric analysis,' IEEE Transactions on Image Processing , vol. 18, no. 7, pp. 1409-1423, 2009. - source
Not checked in the free run.
- Interpretationnone given§ C. RR Quality Index · p. 8
Either image can compute the RRED index using the entropy information from the other image.
“Either image can compute the index using the entropy information from the other image.”
Quote in the paperSubstantial claim - Interpretationreasoning§ B. Contrast Masking · p. 11
Conditioning on the realizations of the premultiplier random variables is analogous to divisive normalization processes in the primary visual cortex (area V1).
“Our approach to entropic RR QA algorithm design uses conditioning on the realizations of the premultiplier random variables, which is analogous to divisive normalization processes in the primary visual cortex (area V1) of the human visual system.”
Quote in the paperSubstantial claim- The authors state this as an assumption: The perceived reference and distorted images pass through an additive neural noise channel, where the noise is a zero mean Gaussian random vector for each block of coefficients.
- Interpretationreasoning§ C. Suprathreshold Effects · p. 12
The ratio of variances raised to powers is the underlying distortion measure on which a nonlinear logarithmic function is applied.
“Thus the ratio of variances raised to powers is the underlying distortion measure on which a nonlinear logarithmic function is applied.”
Quote in the paperSubstantial claim - Study design and conductown data§ V. RESULTS AND DISCUSSION · p. 18
The results on TID2008 demonstrate that the parameters of the algorithm do not require any training on databases.
“The results presented below demonstrate that the parameters of the algorithm do not require any training on databases.”
Quote in the paperSubstantial claim - Interpretationown data§ V. RESULTS AND DISCUSSION · p. 17
It is possible to trade off overall performance and Gaussian blur performance and achieve a desirable operating point by choosing the corresponding value of σ_W^2.
“Thus it is possible to trade off these performances and achieve a desirable operating point by choosing the corresponding value of σ 2 W .”
Quote in the paperSubstantial claim - Interpretationreasoning§ V. RESULTS AND DISCUSSION · p. 16
The reduced performance on the overall database can be attributed to the different ranges of quality scores that occur for different distortion types.
“The reduced performance on the overall database can be attributed to the different ranges of quality scores that occur for different distortion types.”
Quote in the paperSubstantial claim - Interpretationreasoning§ B. Contrast Masking · p. 11
The difference of weighted entropies ensures numerical stability of the distortions at locations where the energy of the coefficients is extremely small, especially when the neural noise variance is also small.
“The difference of weighted entropies also ensures numerical stability of the distortions at locations where the energy of the coefficients is extremely small, especially when the neural noise variance is also small.”
Quote in the paperSubstantial claim- The authors state this as an assumption: The perceived reference and distorted images pass through an additive neural noise channel, where the noise is a zero mean Gaussian random vector for each block of coefficients.
- Interpretationown data§ V. RESULTS AND DISCUSSION · p. 13
Transmitting the right information is crucial to obtain high performance QA algorithms.
“This suggests that transmitting the right information is crucial to obtain high performance QA algorithms.”
Quote in the paperNot a substantial claim - Interpretationreasoning§ V. RESULTS AND DISCUSSION · p. 14
Edge-like artifacts introduced by compressed and noisy distortions are reflected better in the coarser subbands.
“This is because edge like artifacts introduced by these distortions are reflected better in the coarser subbands.”
Quote in the paperSubstantial claim - Interpretationreasoning§ V. RESULTS AND DISCUSSION · p. 15
Because (a), (b) and (c) are evaluations at coarser scales, they do not accurately capture the degradation in quality in high frequency regions, leading to deviations in the logistic fit.
“Since (a), (b) and (c) are evaluations of the RRED indices at coarser scales, they do not accurately capture the degradation in quality in these high frequency regions leading to deviations in the logistic fit.”
Quote in the paperSubstantial claim - Interpretationreasoning§ C. Suprathreshold Effects · p. 12
The logarithm operation in the algorithm accomplishes the suprathreshold effect.
“The logarithm operation in the algorithm essentially accomplishes this desirable property.”
Quote in the paperSubstantial claim - Interpretationown data§ V. RESULTS AND DISCUSSION · p. 15
The flattening of the logistic curves from (a) to (d) indicates that RRED indices at coarser scales tend to cluster the quality indices of most images close to zero.
“The flattening of the curves from (a) to (d) indicates that the RRED indices at coarser scales tend to cluster the quality indices of most images close to zero.”
Quote in the paperNot a substantial claim - Interpretationreasoning§ V. RESULTS AND DISCUSSION · p. 16
When weighted entropies are summed up, the gain and loss of entropies tend to cancel each other, leading to lower quality ranges.
“As a result, when weighted entropies are summed up, the gain and loss of entropies tend to cancel each other leading to lower quality ranges.”
Quote in the paperSubstantial claim - Study design and conductnone given§ VI. CONCLUSION · p. 20
The RRED indices do not depend on any parameters that need to be trained on databases.
“A distinguishing feature of the RRED indices is that these algorithms do not depend on any parameters that need to be trained on databases.”
Quote in the paperSubstantial claim
- May combine two claims. 20
- Classified as probably not a substantial claim. 24
May combine two claims.
Findingown data§ Abstract · p. 1The proposed RRED algorithms correlate very well with subjective quality scores and attain highly competitive performance on the LIVE Image Quality Assessment Database, the Tampere Image Database, and a large comprehensive database of distorted images and subjective scores.
“The algorithms are shown to correlate very well with subjective quality scores as demonstrated on the LIVE Image Quality Assessment Database and Tampere Image Database.”
- Also stated in: § I. INTRODUCTION · p. 4 · boosted
“It is found that the performance attained is highly competitive on a large and comprehensive database of distorted images and subjective scores.”
Quote in the paperSubstantial claim- The authors state this as an assumption: The wavelet coefficients of the distorted image can be modeled as a Gaussian scale mixture distribution.
- The authors state this as an assumption: The perceived reference and distorted images pass through an additive neural noise channel, where the noise is a zero mean Gaussian random vector for each block of coefficients.
- Also stated in: § I. INTRODUCTION · p. 4 · boosted
May combine two claims.
Findingown data§ V. RESULTS AND DISCUSSION · p. 18RRED M_16^16 performs better than some of the best full-reference algorithms, while RRED_1^22 is competitive with PSNR and outperforms [12].
“RRED M 16 16 performs better than some of the best full reference algorithms while RRED 1 22 is competitive with PSNR and outperforms [12].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [12] [12] Z. Wang, G. Wu, H. R. Sheikh, E. P. Simoncelli, E. H. Yang, and A. C. Bovik, 'Quality-aware images,' IEEE Trans. Image Process. , vol. 15, no. 5, pp. 1680-1689, 2006. - source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given§ V. RESULTS AND DISCUSSION · p. 18The steerable pyramid decomposition of the image has a computational complexity of O(N log N) arithmetic operations per scale, where N is the total number of pixels in the image.
“The steerable pyramid decomposition of the image has a computational complexity of O ( N log N ) arithmetic operations per scale, where N is the total number of pixels in the image.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given§ V. RESULTS AND DISCUSSION · p. 15The LCC results in Table II show the same trends as the SROCC results in Table I.
“We observe the same trends in Table II as in Table I for SROCC.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ V. RESULTS AND DISCUSSION · p. 20Overall the algorithm requires around 2.8 seconds to transmit the desired information from each reference or distorted image.
“Overall the algorithm requires around 2.8 seconds to transmit the desired information from each (reference or distorted) image.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ V. RESULTS AND DISCUSSION · p. 20Computation of the index from the numbers transmitted from the reference and distorted requires time of the order of milliseconds.
“Finally, computation of the index from the numbers transmitted from the reference and distorted requires time of the order of milliseconds.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingnone given§ V. RESULTS AND DISCUSSION · p. 18The estimation of K_U requires O(N) operations, while the singular value decomposition of K_U requires O(M^3) operations, where K_U is of size M × M.
“The estimation of K U requires O ( N ) operations, while the singular value decomposition of K U requires O ( M 3 ) operations, where K U is of size M × M .”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given§ V. RESULTS AND DISCUSSION · p. 15Similar trends are observed for the other subbands as well.
“Similar trends are observed for the other subbands as well.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ V. RESULTS AND DISCUSSION · p. 13Most RRED indices considerably outperform PSNR for all distortion types except Gaussian noise, as well as on the entire LIVE database.
“Further, most of the RRED indices considerably outperform PSNR for all distortion types (except images distorted by Gaussian noise) as well as on the entire database.”
Quote in the paperSubstantial claimMay combine two claims.
Findingnone given§ V. RESULTS AND DISCUSSION · p. 15The overall performance decays in the subband at the finest scale while the performance in the individual categories is still very good.
“The overall performance decays in the subband at the finest scale while the performance in the individual categories is still very good.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingreasoning§ V. RESULTS AND DISCUSSION · p. 14The performance of fast fading errors goes down with the fineness of the scale even though the overall performance on the database is still very good.
“The performance of fast fading errors goes down with the fineness of the scale even though the overall performance on the database is still very good.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given§ V. RESULTS AND DISCUSSION · p. 13The algorithms are robust to the exact choice of the size of neighborhoods, yielding approximately the same performance for different sizes.
“However, the algorithms are robust to the exact choice of the size of neighborhoods and we get approximately the same performance for different sizes.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingnone given§ V. RESULTS AND DISCUSSION · p. 17While the overall performance increases as σ_W^2 increases, the performance within the category of images distorted by Gaussian blur decreases.
“While the overall performance increases as σ 2 W increases, the performance within the category of images distorted by Gaussian blur decreases.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown data§ V. RESULTS AND DISCUSSION · p. 16Even though overall correlations are reduced by increases in the degree of subsampling, the correlation score for each individual distortion category remains very competitive with state of the art full-reference algorithms.
“Observe that even though the overall correlations are reduced by increases in the degree of subsampling, the correlation score for each individual distortion category remains very competitive with state of the art FR algorithms.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown data§ V. RESULTS AND DISCUSSION · p. 15The algorithm evaluated in subband 10 yields excellent overall performance in terms of both SROCC and LCC, as well as for compression, noise and blur distortions.
“The algorithm evaluated in subband 10 yields excellent overall performance (in terms of both SROCC and LCC) as well as for compression, noise and blur distortions.”
Quote in the paperSubstantial claimMay combine two claims.
Findingnone given§ V. RESULTS AND DISCUSSION · p. 18The estimation of local variance parameters (premultipliers) requires O(NM^2) operations, while sending the desired information from the reference or distorted image can be upper bounded by a cost of O(N).
“Further, the estimation of local variance parameters (premultipliers) requires O ( NM 2 ) operations, while sending the desired information from the reference or distorted image can be upper bounded by a cost of O ( N ) .”
Quote in the paperNot a substantial claimMay combine two claims.
Findingreasoning§ V. RESULTS AND DISCUSSION · p. 14Blur and fast fading errors are better captured by subbands at finer scales, while coarser scales perform better for compressed and noisy images.
“While blur and fast fading errors are better captured by subbands at finer scales, the coarser scales perform better for compressed and noisy images.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ V. RESULTS AND DISCUSSION · p. 20Computing the scaled entropies for a subband, which is also the information required to be transmitted, takes 0.9-1 seconds for the largest subband.
“Computing the scaled entropies for a subband, which is also the information required to be transmitted takes 0.9-1 seconds for the largest subband.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Interpretationreasoning§ C. RR Quality Index · p. 9The almost reference free algorithm still requires the single number without which quality cannot be computed.
“The algorithm still requires the single number without which quality cannot be computed.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given§ C. RR Quality Index · p. 9The two methods reduce the amount of information gradually from an almost full reference scenario to an almost reference free scenario.
“The two methods described above illustrate how the amount of information can be reduced gradually from an almost full reference scenario to an almost reference free scenario.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Interpretationreasoning§ C. RR Quality Index · p. 9RRED 1_k requires only a single scalar from the reference for quality computation.
“RRED 1 k denotes the algorithm in which all the scaled entropy terms in the subband are added and only the sum, which is a single scalar, is required for quality computation.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning§ C. RR Quality Index · p. 8The reduced reference QA index corresponding to subband k is a reduced reference index because M_k is less than the size of the image.
“The above index is a reduced reference index since M k is less than the size of the image.”
Quote in the paperNot a substantial claim- The authors state this as an assumption: The covariance matrices K_U_k and K_V_k are full rank.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ I. INTRODUCTION · p. 3The algorithm based on Weibull statistics of wavelet coefficients achieves good performance at a given data rate.
“The algorithm by [20] based on Weibull statistics of wavelet coefficients achieves good performance at a given data rate.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [20] [20] W. Xue and X. Mou, 'Reduced reference image quality assessment based on Weibull statistics,' in Second International Workshop on Quality of Multimedia Experience , Trondheim, 2010. - source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ I. INTRODUCTION · p. 2SSIM, VIF, VSNR and JND are successful full reference algorithms that have been shown to perform well in predicting the quality scores of human subjects.
“The structural similarity index (SSIM) [2], visual information fidelity (VIF) [3], visual signal to noise ratio (VSNR) [4] and just noticeable difference (JND) metrix [5], are examples of successful full reference algorithms which have been shown to perform well in predicting the quality scores of human subjects.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites [2] [2] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, 'Image quality assessment: From error measurement to structural similarity,' IEEE Trans. Image Process. , vol. 13, no. 4, pp. 600-612, Apr. 2004. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites [3] [3] H. R. Sheikh and A. C. Bovik, 'Image information and visual quality,' IEEE Trans. Image Process. , vol. 15, no. 2, pp. 430-444, Feb. 2006. - source
Not checked in the free run.
- cites [4] [4] D. M. Chandler and S. S. Hemami, 'VSNR: A wavelet-based visual signal-to-noise ratio for natural images,' IEEE Trans. Image Process. , vol. 16, no. 9, pp. 2284-2298, Sep. 2007. - source
Not checked in the free run.
May combine two claims.
Interpretationown data§ II. INFORMATION THEORETIC APPROACHES TO QA · p. 5The proposed RRED algorithms possess desirable psychovisual properties leading to excellent performance.
“However, we show later on that this procedure still possesses desirable psychovisual properties leading to excellent performance of the algorithms.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Interpretationnone given§ A. Scale-Space-Orientation Decomposition · p. 10The first step in the RR algorithm is a wavelet decomposition of the image at multiple scales and orientations, which imitates the signal processing in the primary visual cortex (area V1).
“The first step in the RR algorithm, similar to IFC/VIF, is a wavelet decomposition of the image at multiple scales and orientations. This step imitates the signal processing that happens in the primary visual cortex (area V1) of the human visual system.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning§ I. INTRODUCTION · p. 3The proposed framework allows users to choose an algorithm from this class for general purpose or distortion specific quality assessment.
“The framework also allows users to choose an algorithm from this class for general purpose or distortion specific quality assessment.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ I. INTRODUCTION · p. 2Training-based no reference QA techniques perform at least as well as mean squared error.
“Training based NR QA techniques have resulted in algorithms that perform at least as well as mean squared error, which has the benefit of a reference image [9], [10].”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites [9] [9] A. K. Moorthy and A. C. Bovik, 'A two-step framework for constructing blind image quality indices,' IEEE Signal Processing Letters , vol. 17, no. 5, pp. 587-599, May 2010. - source
Not checked in the free run.
- cites [10] [10] M. A. Saad, A. C. Bovik, and C. Charrier, 'A DCT statistics based blind image quality index,' IEEE Signal Processing Letters , vol. 17, no. 6, pp. 583-586, Jun. 2010. - source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ I. INTRODUCTION · p. 2The DNT-extended KL divergence algorithm depends on a number of parameters that need to be trained on databases.
“However, this algorithm depends on a number of parameters that need to be trained on databases.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [13] [13] Q. Li and Z. Wang, 'Reduced-reference image quality assessment using divisive normalization-based image representation,' IEEE Journal of Selected Topics in Signal Processing: Special issue on Visual Media Quality Assessment , vol. 3, pp. 202211, 2009. - source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ I. INTRODUCTION · p. 2The quality aware images algorithm performs well only for certain individual distortion categories.
“The performance of this algorithm is good only for certain individual distortion categories.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [12] [12] Z. Wang, G. Wu, H. R. Sheikh, E. P. Simoncelli, E. H. Yang, and A. C. Bovik, 'Quality-aware images,' IEEE Trans. Image Process. , vol. 15, no. 5, pp. 1680-1689, 2006. - source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone given§ C. RR Quality Index · p. 8Any enhanced image would show a difference in entropies and the difference should be interpreted as an improvement in quality.
“Also, any enhanced image would show a difference in entropies and the difference should be interpreted as an improvement in quality.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Study design and conductcitation§ V. RESULTS AND DISCUSSION · p. 13The neural noise variance value σ_W^2 = 0.1 is the same as used in prior algorithms and does not involve training on the database.
“Note that this is the same value of neural noise variance that has been used in prior algorithms [3] and we do not imply any training on the database.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [3] [3] H. R. Sheikh and A. C. Bovik, 'Image information and visual quality,' IEEE Trans. Image Process. , vol. 15, no. 2, pp. 430-444, Feb. 2006. - source
Not checked in the free run.
Classified as probably not a substantial claim.
Premisecitation§ V. RESULTS AND DISCUSSION · p. 13Human subjects are more sensitive to horizontal and vertical orientations than to other orientations.
“The analysis in [22] suggests that human subjects are more sensitive to horizontal and vertical orientations than others.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [22] [22] H. R. Sheikh, A. C. Bovik, and G. de Veciana, 'An information fidelity criterion for image quality assessment using natural scene statistics,' IEEE Trans. Image Process. , vol. 14, no. 12, pp. 2117-2128, Dec. 2005. - source
Not checked in the free run.
May combine two claims.
Interpretationreasoning§ B. Contrast Masking · p. 11Divisive normalization approximates conditioning and vice versa.
“Therefore, divisive normalization approximates conditioning and vice versa.”
Quote in the paperSubstantial claim- The authors state this as an assumption: The perceived reference and distorted images pass through an additive neural noise channel, where the noise is a zero mean Gaussian random vector for each block of coefficients.
Probably not a substantial claim: may not pass S4 (based).
Study design and conductnone given§ V. RESULTS AND DISCUSSION · p. 13The reduced reference algorithm operates without knowledge of the distortion type.
“Note that the reduced reference algorithm operates without knowledge of the distortion type.”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationnone given§ V. RESULTS AND DISCUSSION · p. 16In JPEG, increases in entropy occur due to the introduction of discontinuous blocking artifacts, while decreases in entropy occur in smoother regions that are heavily quantized.
“For example, in JPEG, increases in entropy occur due to the introduction of discontinuous blocking artifacts, while decreases in entropy occur in smoother regions that are heavily quantized.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given§ VI. CONCLUSION · p. 20The use of a multiscale multiorientation decomposition before computing the index increases the complexity of the algorithm.
“The use of a multiscale multiorientation decomposition before computing the index increases the complexity of the algorithm.”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationreasoning§ V. RESULTS AND DISCUSSION · p. 16When the entropies are summed up after the absolute value of the difference is calculated for every block, the changes in the entropies are still preserved, leading to an algorithm that possesses better overall performance.
“When the entropies are summed up after the absolute value of the difference is calculated for every block, the changes in the entropies are still preserved leading to an algorithm that possesses better overall performance.”
Quote in the paperSubstantial claimMay combine two claims.
Interpretationown data§ V. RESULTS AND DISCUSSION · p. 17The neural noise variance of the model impacts the perception of blur apart from being able to better align scores belonging to different distortion categories.
“This suggests that the neural noise variance of our model does impact the perception of blur apart from being able to better align scores belonging to different distortion categories.”
Quote in the paperSubstantial claim
The authors state this as an assumption.
Modifications of natural image statistics are perceptually noticeable.
“It is also based on the assumption that such modifications of natural image statistics are perceptually noticeable.”
The authors state this as an assumption.
Non-overlapping blocks of wavelet coefficients are independent and identically distributed.
“Non-overlapping blocks are assumed independent and identically distributed (i.i.d.).”
The authors state this as an assumption.
The wavelet coefficients of the distorted image can be modeled as a Gaussian scale mixture distribution.
“This means that we model the wavelet coefficients of the distorted image as well as a Gaussian scale mixture distribution.”
The authors state this as an assumption.
The perceived reference and distorted images pass through an additive neural noise channel, where the noise is a zero mean Gaussian random vector for each block of coefficients.
“We additionally model the perceived reference and distorted images as passing through an additive neural noise channel, where the noise is assumed to be a zero mean Gaussian random vector for each block of coefficients.”
The authors state this as an assumption.
The covariance matrices K_U_k and K_V_k are full rank.
“In the following, assume that K U k and K V k are full rank matrices.”
The authors state this as an assumption.
The scalar premultiplier S_mk and the Gaussian vector U_mk are independent.
“Also, S mk and ¯ U mk are independent.”
The authors state this as an assumption.
The neural noise vectors W_mk and W'_mk are independent of each other, independent of C_mk and D_mk, and independent across indices m and k.
“where W mk ∼ N (0 , σ 2 W I N ) and W ′ mk ∼ N (0 , σ 2 W I N ) , W mk and W ′ mk are independent of each other, independent of ¯ C mk and ¯ D mk and independent across the indices m and k .”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Gaussian-blur SROCC differs for the same algorithm
MinorTables I and III report different Gaussian-blur SROCC values for the unsubsampled RRED M16 algorithm.
“| Gaussian Blur | 0.9221 | 0.9595 | 0.9678 | 0.9236 | 0.7812 | 0.9728 |”
“| Gaussian Blur | 0.9675 | 0.9429 | 0.9674 | 0.9679 | 0.9655 |”
Opposite claims about fast-fading performance across scales
MinorThe paper says finer-scale subbands capture fast-fading errors better, then says fast-fading performance goes down as the scale becomes finer.
“While blur and fast fading errors are better captured by subbands at finer scales, the coarser scales perform better for compressed and noisy images.”
“The performance of fast fading errors goes down with the fineness of the scale even though the overall performance on the database is still very good.”
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works
Self-citationImage information and visual quality
Sheikh, H. R., & Bovik, A. C. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.859378 · Cited by 4,104 · see citing works
Self-citationDaugman, J. G. (1985) · Journal of the Optical Society of America A · doi:10.1364/josaa.2.001160 · Cited by 3,219 · see citing works
Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures
Wang, Z., & Bovik, A. C. (2009) · IEEE Signal Processing Magazine · doi:10.1109/msp.2008.930649 · Cited by 3,175 · see citing works
Self-citationImage denoising using scale mixtures of gaussians in the wavelet domain
Portilla, J., Strela, V., Wainwright, M. J., & Simoncelli, E. P. (2003) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.818640 · Cited by 2,256 · see citing works
An information fidelity criterion for image quality assessment using natural scene statistics
Sheikh, H. R., Bovik, A. C., & de Veciana, G. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.859389 · Cited by 1,399 · see citing works
Self-citationLive image quality assessment database release 2
Sheikh, H. R. (2005) · Medical Entomology and Zoology · Cited by 1,276 · see citing works
A Two-Step Framework for Constructing Blind Image Quality Indices
Moorthy, A. K., & Bovik, A. C. (2010) · IEEE Signal Processing Letters · doi:10.1109/lsp.2010.2043888 · Cited by 1,196 · see citing works
Self-citationContrast masking in human vision
Legge, G. E., & Foley, J. M. (1980) · Journal of the Optical Society of America · doi:10.1364/josa.70.001458 · Cited by 1,188 · see citing works
VSNR: A Wavelet-Based Visual Signal-to-Noise Ratio for Natural Images
Chandler, D. M., & Hemami, S. S. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.901820 · Cited by 1,147 · see citing works
The steerable pyramid: a flexible architecture for multi-scale derivative computation
Simoncelli, E. P., & Freeman, W. T. (2002) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.1995.537667 · Cited by 1,077 · see citing works
TID2008 – A database for evaluation of full-reference visual quality assessment metrics
Ponomarenko, N. N., Лукин, В. В., & Zelensky, A. A. (2004) · Iris (Roma Tre University) · Cited by 1,000 · see citing works
Image Quality Assessment: From Error Measurement to Structural Similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · Cited by 880 · see citing works
Self-citationNo-reference perceptual quality assessment of JPEG compressed images
Wang, Z., Sheikh, H. R., & Bovik, A. C. (2003) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2002.1038064 · Cited by 839 · see citing works
Self-citationNatural signal statistics and sensory gain control
Schwartz, O., & Simoncelli, E. P. (2001) · Nature Neuroscience · doi:10.1038/90526 · Cited by 835 · see citing works
Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos
Seshadrinathan, K., & Bovik, A. C. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2034992 · Cited by 708 · cited 1× · see citing works
“Successful video QA algorithms such as the MOVIE index [28] employ Gabor filters to decompose video data prior to performing QA.”
MethodSelf-citationNo-reference quality assessment using natural scene statistics: JPEG2000
Sheikh, H. R., Bovik, A. C., & Cormack, L. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.854492 · Cited by 575 · see citing works
Self-citationHuman luminance pattern-vision mechanisms: masking experiments require a new model
Foley, J. M. (1994) · Journal of the Optical Society of America A · doi:10.1364/josaa.11.001710 · Cited by 573 · see citing works
Perceptual blur and ringing metrics: application to JPEG2000
Marziliano, P., Frederic Dufaux, A., WINKLER, S. S., & Ebrahimi, T. (2003) · Signal Processing Image Communication · doi:10.1016/j.image.2003.08.003 · Cited by 491 · see citing works
Model of visual contrast gain control and pattern masking
Watson, A. B., & Solomon, J. A. (1997) · Journal of the Optical Society of America A · doi:10.1364/josaa.14.002379 · Cited by 472 · see citing works
Teo, P. C., & Heeger, D. J. (2002) · Proceedings of 1st International Conference on Image Processing · doi:10.1109/icip.1994.413502 · Cited by 471 · see citing works
A DCT Statistics-Based Blind Image Quality Index
Saad, M. A., Bovik, A. C., & Charrier, C. (2010) · IEEE Signal Processing Letters · doi:10.1109/lsp.2010.2045550 · Cited by 372 · see citing works
Self-citationContrast gain control in the cat visual cortex
Ohzawa, I., Sclar, G., & Freeman, R. D. (1982) · Nature · doi:10.1038/298266a0 · Cited by 348 · see citing works
Reduced-Reference Image Quality Assessment Using Divisive Normalization-Based Image Representation
Li, Q., & Wang, Z. (2009) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2009.2014497 · Cited by 323 · see citing works
Blind image quality assessment through anisotropy
Gabarda, S., & Cristóbal, G. (2007) · Journal of the Optical Society of America A · doi:10.1364/josaa.24.000b42 · Cited by 301 · see citing works
Wang, Z., Wu, G., Sheikh, H. R., Simoncelli, E. P., Yang, E.-H., & Bovik, A. C. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.864165 · Cited by 293 · see citing works
Self-citationImage Quality Assessment Based on Multiscale Geometric Analysis
Gao, X., Lu, W., Tao, D., & Li, X. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2018014 · Cited by 252 · see citing works
Objective quality assessment of color images based on a generic perceptual reduced reference
Carnec, M., Le Callet, P., & Barba, D. (2008) · Signal Processing: Image Communication · doi:10.1016/j.image.2008.02.003 · Cited by 124 · see citing works
Reduced-reference metric design for objective perceptual quality assessment in wireless imaging
Engelke, U., Kusuma, T. M., Zepernick, H., & Caldera, M. (2009) · Signal Processing Image Communication · doi:10.1016/j.image.2009.06.005 · Cited by 95 · see citing works
A scalable wavelet-based video distortion metric and applications
Masry, M., Hemami, S. S., & Sermadevi, Y. (2006) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2005.861946 · Cited by 94 · see citing works
Unifying analysis of full reference image quality assessment
Seshadrinathan, K., & Bovik, A. C. (2008) · 2008 15th IEEE International Conference on Image Processing · doi:10.1109/icip.2008.4711976 · Cited by 85 · see citing works
Self-citationColor Distribution Information for the Reduced-Reference Assessment of Perceived Image Quality
Redi, J., Gastaldo, P., Heynderickx, I. E. J., & Zunino, R. (2010) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2010.2087456 · Cited by 76 · see citing works
Reduced reference image quality assessment based on Weibull statistics
Xue, W., & Mou, X. (2010) · 2010 Second International Workshop on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2010.5518131 · Cited by 47 · see citing works
Reduced-reference image quality assessment using distributed source coding
Chono, K., Lin, Y.-C., Varodayan, D., Miyamoto, Y., & Girod, B. (2008) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2008.4607508 · Cited by 39 · see citing works
Subjective Evaluation of Spatial Resolution and Quantization Noise Tradeoffs
Bae, S. H., Pappas, T. N., & Juang, B.-H. F. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2008.2009796 · Cited by 23 · see citing works
On the nearly scale-independent rank behavior of image quality metrics
Gaubatz, M. D., & Hemami, S. S. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4711851 · Cited by 6 · see citing works
Multi-scale and Scalable Video Quality Assessment
Seshadrinathan, K., & Bovik, A. C. (2008) · International Conference on Consumer Electronics · doi:10.1109/icce.2008.4588117 · Cited by 2 · see citing works
Self-citationMulti-scale and Scalable Video Quality Assessment
Seshadrinathan, K., & Bovik, A. C. (2008) · 2008 Second International Conference on Electrical Engineering · doi:10.1109/icee.2008.4585297 · Cited by 1 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 1
- 0, JNDmetrix Technology
Cited by
Sorted by citations
No-Reference Image Quality Assessment in the Spatial Domain
Mittal, A., Moorthy, A. K., & Bovik, A. C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2214050 · Cited by 6,064 · see citing works
Self-citationGradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index
Xue, W., Zhang, L., Mou, X., & Bovik, A. C. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2293423 · Cited by 1,697 · see citing works
Self-citationDeep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
Bosse, S., Maniry, D., Muller, K.-R., Wiegand, T., & Samek, W. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2760518 · Cited by 1,263 · see citing works
Waterloo Exploration Database: New Challenges for Image Quality Assessment Models
Ma, K., Duanmu, Z., Wu, Q., Wang, Z., Yong, H., Li, H., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2631888 · Cited by 789 · see citing works
Massive Online Crowdsourced Study of Subjective and Objective Picture Quality
Ghadiyaram, D., & Bovik, A. C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2500021 · Cited by 782 · see citing works
Self-citationKonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment
Hosu, V., Lin, H., Sziranyi, T., & Saupe, D. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2967829 · Cited by 759 · see citing works
Perceptual image quality assessment: a survey
Zhai, G., & Min, X. (2020) · Science China Information Sciences · doi:10.1007/s11432-019-2757-1 · Cited by 662 · see citing works
Javier Galbally, A., Marcel, S., & Fiérrez, J. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2292332 · Cited by 611 · see citing works
Aquino, A., Arias, M. E., & Marín, D. (2010) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2010.2053042 · Cited by 517 · see citing works
Blind Image Quality Assessment Based on High Order Statistics Aggregation
Xu, J., Ye, P., Li, Q., Du, H., Liu, Y., & Doermann, D. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2585880 · Cited by 490 · see citing works
Blind Prediction of Natural Video Quality
Saad, M. A., Bovik, A. C., & Charrier, C. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2299154 · Cited by 471 · see citing works
Self-citationLearning a No-Reference Quality Assessment Model of Enhanced Images With Big Data
Gu, K., Tao, D., Qiao, J., & Lin, W. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2649101 · Cited by 449 · see citing works
Seven Challenges in Image Quality Assessment: Past, Present, and Future Research
Chandler, D. M. (2013) · ISRN Signal Processing · doi:10.1155/2013/905685 · Cited by 427 · see citing works
The Analysis of Image Contrast: From Quality Assessment to Automatic Enhancement
Gu, K., Zhai, G., Lin, W., & Liu, M. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2401732 · Cited by 390 · see citing works
Video Quality Assessment by Reduced Reference Spatio-Temporal Entropic Differencing
Soundararajan, R., & Bovik, A. C. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2214933 · Cited by 368 · see citing works
Self-citationPerceptual video quality assessment: a survey
Min, X., Duan, H., Sun, W., Zhu, Y., & Zhai, G. (2024) · Science China Information Sciences · doi:10.1007/s11432-024-4133-3 · Cited by 218 · see citing works
Automatic Prediction of Perceptual Image and Video Quality
Bovik, A. C. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2013.2257632 · Cited by 212 · see citing works
Self-citationA survey of deep learning approaches to image restoration
Su, J., Xu, B., & Yin, H. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.02.046 · Cited by 194 · see citing works
A Fast Approach for No-Reference Image Sharpness Assessment Based on Maximum Local Variation
Bahrami, K., & Kot, A. C. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2314487 · Cited by 192 · see citing works
Two-Stream Convolutional Networks for Blind Image Quality Assessment
Yan, Q., Gong, D., & Zhang, Y. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2883741 · Cited by 182 · see citing works
Perceptual Image Quality Assessment with Transformers
Cheon, M., Yoon, S., Kang, B., & Lee, J. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00054 · Cited by 181 · see citing works
Reduced-Reference Image Quality Assessment With Visual Information Fidelity
Wu, J., Lin, W., Shi, G., & Liu, A. (2013) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2013.2266093 · Cited by 170 · see citing works
Blind Image Quality Assessment Based on Multichannel Feature Fusion and Label Transfer
Wu, Q., Li, H., Meng, F., Ngan, K. N., Luo, B., Huang, C., & Zeng, B. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2412773 · Cited by 163 · see citing works
Model-Based Referenceless Quality Metric of 3D Synthesized Images Using Local Image Description
Gu, K., Jakhetiya, V., Qiao, J., Li, X., Lin, W., & Thalmann, D. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2733164 · Cited by 154 · see citing works
Reduced-Reference Image Quality Assessment in Free-Energy Principle and Sparse Representation
Liu, Y., Zhai, G., Gu, K., Liu, X., Zhao, D., & Gao, W. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2729020 · Cited by 153 · see citing works
SpEED-QA: Spatial Efficient Entropic Differencing for Image and Video Quality
Bampis, C. G., Gupta, P., Soundararajan, R., & Bovik, A. C. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2726542 · Cited by 150 · see citing works
Self-citationA Gabor Feature-Based Quality Assessment Model for the Screen Content Images
Ni, Z., Zeng, H., Ma, L., Hou, J., Chen, J., & Ma, K.-K. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2839890 · Cited by 118 · see citing works
Quality Assessment for Comparing Image Enhancement Algorithms
Chen, Z., Jiang, T., & Tian, Y. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.384 · Cited by 111 · see citing works
Reduced-Reference Quality Assessment of Screen Content Images
Wang, S., Gu, K., Zhang, X., Lin, W., Ma, S., & Gao, W. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2602764 · Cited by 110 · see citing works
An Objective Deghosting Quality Metric for HDR Images
Tursun, O. T., Akyüz, A. O., Erdem, A., & Erdem, E. (2016) · Computer Graphics Forum · doi:10.1111/cgf.12818 · Cited by 103 · see citing works
Data-Efficient Image Quality Assessment with Attention-Panel Decoder
Qin, G., Hu, R., Liu, Y., Zheng, X., Liu, H., Li, X., & Zhang, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25302 · Cited by 102 · see citing works
Orientation selectivity based visual pattern for reduced-reference image quality assessment
Wu, J., Lin, W., Shi, G., Li, L., & Fang, Y. (2016) · Information Sciences · doi:10.1016/j.ins.2016.02.043 · Cited by 96 · see citing works
Gu, K., Qiao, J., Lee, S., Liu, H., Lin, W., & Callet, P. L. (2019) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2019.2906768 · Cited by 88 · see citing works
Gradient Direction for Screen Content Image Quality Assessment
Ni, Z., Ma, L., Zeng, H., Cai, C., & Ma, K. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2599294 · Cited by 87 · see citing works
No-Reference Image Quality Assessment by Wide-Perceptual-Domain Scorer Ensemble Method
Liu, T.-J., & Liu, K.-H. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2771422 · Cited by 86 · see citing works
Golestaneh, S. A., & Karam, L. J. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2601821 · Cited by 81 · see citing works
Yang, J., Zhao, Y. S., Liu, J., Jiang, B., Meng, Q., Lu, W. B., & Gao, X. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3024627 · Cited by 78 · see citing works
Saliency-induced reduced-reference quality index for natural scene and screen content images
Min, X., Gu, K., Zhai, G., Hu, M., & Yang, X. (2017) · Signal Processing · doi:10.1016/j.sigpro.2017.10.025 · Cited by 77 · see citing works
Blind Quality Assessment of Camera Images Based on Low-Level and High-Level Statistical Features
Liu, Y., Gu, K., Wang, S., Zhao, D., & Gao, W. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2849602 · Cited by 74 · see citing works
UIQI: A Comprehensive Quality Evaluation Index for Underwater Images
Liu, Y., Gu, K., Cao, J., Wang, S., Zhai, G., Dong, J., & Kwong, S. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3301226 · Cited by 73 · see citing works
Biologically Inspired Blind Quality Assessment of Tone-Mapped Images
Yue, G., Hou, C., Gu, K., Mao, S., & Zhang, W. (2017) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2739708 · Cited by 72 · see citing works
No-reference Stereoscopic Image Quality Assessment Using Natural Scene Statistics
Appina, B., Khan, S., & Channappayya, S. S. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.02.001 · Cited by 70 · see citing works
Blind Image Quality Assessment by Natural Scene Statistics and Perceptual Characteristics
Liu, Y., Gu, K., Li, X., & Zhang, Y. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3414837 · Cited by 64 · see citing works
Assessing Image Quality Issues for Real-World Problems
Chiu, T.-Y., Zhao, Y., & Gurari, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00370 · Cited by 63 · see citing works
Visual Orientation Selectivity Based Structure Description
Wu, J., Lin, W., Shi, G., Zhang, Y., Dong, W., & Chen, Z. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2460467 · Cited by 63 · see citing works
Semi-Reference Sonar Image Quality Assessment Based on Task and Visual Perception
Chen, W., Gu, K., Zhao, T., Jiang, G., & Callet, P. L. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2991546 · Cited by 58 · see citing works
Jakhetiya, V., Gu, K., Singhal, T., Guntuku, S. C., Xia, Z., & Lin, W. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2888861 · Cited by 55 · see citing works
Madhusudana, P. C., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3106801 · Cited by 54 · see citing works
Self-citationA shallow convolutional neural network for blind image sharpness assessment
Yu, S., Wu, S., Wang, L., Jiang, F., Xie, Y., & Li, L. (2017) · PLoS ONE · doi:10.1371/journal.pone.0176632 · Cited by 53 · see citing works
Objective image quality assessment: a survey
He, L., Gao, F., Hou, W., & Hao, L. (2013) · International Journal of Computer Mathematics · doi:10.1080/00207160.2013.816415 · Cited by 53 · see citing works
Niu, Y., Zhang, H., Guo, W., & Ji, R. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2634590 · Cited by 52 · see citing works
Effective and Efficient Blind Quality Evaluator for Contrast Distorted Images
Yue, G., Hou, C., Zhou, T., & Zhang, X. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2868555 · Cited by 52 · see citing works
Huang, W., Xu, W., Wan, R., Zhang, P., Zha, Y., & Pang, M. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3239780 · Cited by 51 · see citing works
Predicting the Quality of Images Compressed After Distortion in Two Steps
Yu, X., Bampis, C. G., Gupta, P., & Bovik, A. C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2922850 · Cited by 48 · see citing works
Self-citationMaking image quality assessment robust
Mittal, A., Moorthy, A. K., & Bovik, A. C. (2012) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2012.6489326 · Cited by 47 · see citing works
Self-citationImage Quality Ranking Method for Microscopy
Koho, S., Fazeli, E., Eriksson, J., & Hanninen, P. E. (2016) · Scientific Reports · doi:10.1038/srep28962 · Cited by 46 · see citing works
Zhu, W., Zhai, G., Min, X., Hu, M., Liu, J., Guo, G., & Yang, X. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2902484 · Cited by 46 · see citing works
Survey of information theory in visual quality assessment
Soundararajan, R., & Bovik, A. C. (2013) · Signal Image and Video Processing · doi:10.1007/s11760-013-0442-5 · Cited by 45 · see citing works
Self-citationQuality assessment for real out-of-focus blurred images
Liu, Y., Gu, K., Zhai, G., Liu, X., Zhao, D., & Gao, W. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.03.007 · Cited by 45 · see citing works
Blind quality assessment of night-time image
Hu, R., Liu, Y., Wang, Z., & Li, X. (2021) · Displays · doi:10.1016/j.displa.2021.102045 · Cited by 45 · see citing works
Wu, Q., Li, H., Meng, F., Ngan, K. N., & Zhu, S. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.08.009 · Cited by 44 · see citing works
Fractal Analysis for Reduced Reference Image Quality Assessment
Xu, Y., Liu, D., Quan, Y., & Callet, P. L. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2413298 · Cited by 44 · see citing works
A Prediction Backed Model for Quality Assessment of Screen Content and 3-D Synthesized Images
Jakhetiya, V., Gu, K., Lin, W., Li, Q., & Jaiswal, S. P. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2756666 · Cited by 43 · see citing works
Natural image statistics based 3D reduced reference image quality assessment in contourlet domain
Wang, X., Liu, Q., Wang, R., & Chen, Z. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.05.090 · Cited by 42 · see citing works
Comparison-Based Image Quality Assessment for Selecting Image Restoration Parameters
Liang, H.-Y., & Weller, D. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2601783 · Cited by 35 · see citing works
Predicting Stereoscopic Image Quality via Stacked Auto-Encoders Based on Stereopsis Formation
Yang, J., Sim, K., Lu, W. B., & Jiang, B. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2889562 · Cited by 40 · see citing works
Dual-Channel Multi-Task CNN for No-Reference Screen Content Image Quality Assessment
Zhang, C., Huang, Z., Liu, S., & Xiao, J. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3143321 · Cited by 39 · see citing works
Subjective and objective quality assessment for image restoration: A critical survey
Hu, B., Li, L., Wu, J., & Qian, J. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.115839 · Cited by 37 · see citing works
No-Reference Deep Quality Assessment of Compressed Light Field Images
Guo, Z., Gao, W., Wang, H., Wang, J., & Fan, S. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428383 · Cited by 32 · see citing works
Reduced reference image quality assessment using regularity of phase congruency
Liu, D., Xu, Y., Quan, Y., & Callet, P. L. (2014) · Signal Processing Image Communication · doi:10.1016/j.image.2014.06.007 · Cited by 32 · see citing works
No-training, no-reference image quality index using perceptual features
Li, C., Ju, Y., Bovik, A. C., Wu, X., & Sang, Q. (2013) · Optical Engineering · doi:10.1117/1.oe.52.5.057003 · Cited by 32 · see citing works
Self-citationToward a Blind Quality Predictor for Screen Content Images
Shao, F., Gao, Y., Li, F., & Jiang, G. (2017) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2017.2676180 · Cited by 32 · see citing works
Reduced-reference image quality assessment based on distortion families of local perceived sharpness
Zhang, Y., Phan, T. D., & Chandler, D. M. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.03.020 · Cited by 30 · see citing works
No-Reference Quality Assessment for Contrast-Distorted Images
Liu, Y., & Li, X. (2020) · IEEE Access · doi:10.1109/access.2020.2991842 · Cited by 30 · see citing works
Learning a Unified Blind Image Quality Metric via On-Line and Off-Line Big Training Instances
Gu, K., Xu, X., Qiao, J., Jiang, Q., Lin, W., & Thalmann, D. (2019) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2895605 · Cited by 29 · see citing works
Blind image quality assessment with hierarchy: Degradation from local structure to deep semantics
Wu, J., Zeng, J., Dong, W., Shi, G., & Lin, W. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.12.005 · Cited by 29 · see citing works
Reduced reference image and video quality assessments: review of methods
Dost, S., Saud, F., Shabbir, M., Khan, M. G., Shahid, M. U., & Lövström, B. (2022) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-021-00578-y · Cited by 28 · see citing works
BNB Method for No-Reference Image Quality Assessment
Fang, R., Al-Bayaty, R., & Wu, D. O. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2539658 · Cited by 28 · see citing works
Directionlet transform based sharpening and enhancement of mammographic X-ray images
Anand, S., Kumari, R. S. S., Jeeva, S., & Thivya, T. (2013) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2013.02.001 · Cited by 27 · see citing works
Visual Quality Assessment of Stereoscopic Image and Video: Challenges, Advances, and Future Trends
Su, C.-C., Moorthy, A. K., & Bovik, A. C. (2014) · Springer eBooks · doi:10.1007/978-3-319-10368-6_7 · Cited by 27 · see citing works
Self-citationQuantifying Visual Image Quality: A Bayesian View
Duanmu, Z., Liu, W., Wang, Z., & Wang, Z. (2021) · Annual Review of Vision Science · doi:10.1146/annurev-vision-100419-120301 · Cited by 27 · see citing works
No reference image quality assessment based on local binary pattern statistics
Zhang, M., Xie, J., Zhou, X., & Fujita, H. (2013) · Visual Communications and Image Processing · doi:10.1109/vcip.2013.6706418 · Cited by 26 · see citing works
Ma, J., An, P., Shen, L., & Li, K. (2017) · IEEE Access · doi:10.1109/access.2017.2785282 · Cited by 25 · see citing works
Fingermark quality assessment framework with classic and deep learning ensemble models
Oblak, T., Haraksim, R., Peer, P., & Beslay, L. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109148 · Cited by 24 · see citing works
Fang, Z., Cui, Y., Yu, M., Jiang, G., Lian, K., Wen, Y., & Xu, J. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3306527 · Cited by 24 · see citing works
A Study of Subjective and Objective Quality Assessment of HDR Videos
Shang, Z., Ebenezer, J. P., Venkataramanan, A. K., Wu, Y., Wei, H., Sethuraman, S., & Bovik, A. C. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3333217 · Cited by 24 · see citing works
Self-citationBlind Image Quality Assessment of Natural Scenes Based on Entropy Differences in the DCT Domain
Yang, X., Li, F., Zhang, W., & He, L. (2018) · Entropy · doi:10.3390/e20110885 · Cited by 24 · see citing works
CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP
Tang, Z., Wang, Z., Peng, B., & Dong, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78125-4_4 · Cited by 23 · see citing works
Bag-of-words feature representation for blind image quality assessment with local quantized pattern
Xie, X., Zhang, Y., Wu, J., Shi, G., & Dong, W. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.05.034 · Cited by 23 · see citing works
Detection of spoofing attacks for ear biometrics through image quality assessment and deep learning
Toprak, İ., & Toygar, Ö. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114600 · Cited by 23 · see citing works
Xiang, J., Chen, P., Dang, Y., Liang, R., & Jiang, G. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3273855 · Cited by 23 · see citing works
Predicting Detection Performance on Security X-Ray Images as a Function of Image Quality
Gupta, P., Sinno, Z., Glover, J. L., Paulter, N. G., & Bovik, A. C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2896488 · Cited by 23 · see citing works
Self-citationScreen Content Video Quality Assessment Model Using Hybrid Spatiotemporal Features
Zeng, H., Huang, H., Hou, J., Cao, J., Wang, Y., & Ma, K. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3206621 · Cited by 22 · see citing works
Generalized Gaussian scale mixtures: A model for wavelet coefficients of natural images
Gupta, P., Moorthy, A. K., Soundararajan, R., & Bovik, A. C. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.05.009 · Cited by 21 · see citing works
Self-citationNo-reference image quality assessment with visual pattern degradation
Wu, J., Zhang, M., Li, L., Dong, W., Shi, G., & Lin, W. (2019) · Information Sciences · doi:10.1016/j.ins.2019.07.061 · Cited by 21 · see citing works
Visual structural degradation based reduced-reference image quality assessment
Wu, J., Lin, W., Fang, Y., Li, L., Shi, G., & Issac Niwas, S. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.05.008 · Cited by 20 · see citing works
Jensen–Shannon divergence for visual quality assessment
Bruni, V., Rossi, E., & Vitulano, D. (2013) · Signal Image and Video Processing · doi:10.1007/s11760-013-0444-3 · Cited by 20 · see citing works
Perceptual image quality assessment combining free-energy principle and sparse representation
Liu, Y., Zhai, G., Liu, X., & Zhao, D. (2016) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2016.7538867 · Cited by 20 · see citing works
Ding, Y. S., Zhao, Y., & Zhao, X. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.03.001 · Cited by 19 · see citing works
Jakhetiya, V., Gu, K., Jaiswal, S. P., Singhal, T., & Xia, Z. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.2965469 · Cited by 19 · see citing works
- Authors
- Soundararajan, R., & Bovik, A. C.
- Affiliations
- The University of Texas at Austin (US)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2012-02
- Volume
- 21
- Issue
- 2
- Pages
- 517-526
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2037243393
- Semantic Scholar
- fa34db4aad1414c88392e0583f5f28c780c7e2e6
- Cited by
- 337
- References
- 38
- Citations by year
- 2026: 5 · 2025: 17 · 2024: 9 · 2023: 14 · 2022: 22 · 2021: 23 · 2020: 21 · 2019: 22 · 2018: 41 · 2017: 36 · 2016: 36 · 2015: 27 · 2014: 33 · 2013: 21 · 2012: 9
- FWCI
- 21.69
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- reduced-reference image quality assessment, entropy difference, wavelet coefficients, image distortion, visual perception, subjective quality correlation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
