Making a “Completely Blind” Image Quality Analyzer
The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
An important aim of research on the blind image quality assessment (IQA) problem is to devise perceptual models that can predict the quality of distorted images with as little prior knowledge of the images or their distortions as possible. Current state-of-the-art “general purpose” no reference (NR) IQA algorithms require knowledge about anticipated distortions in the form of training examples and corresponding human opinion scores. However we have recently derived a blind IQA model that only makes use of measurable deviations from statistical regularities observed in natural images, without training on human-rated distorted images, and, indeed without any exposure to distorted images. Thus, it is “completely blind.” The new IQA model, which we call the Natural Image Quality Evaluator (NIQE) is based on the construction of a “quality aware” collection of statistical features based on a simple and successful space domain natural scene statistic (NSS) model. These features are derived from a corpus of natural, undistorted images. Experimental results show that the new index delivers performance comparable to top performing NR IQA models that require training on large databases of human opinions of distorted images. A software release is available at http://live.ece.utexas.edu/research/quality/niqe_release.zip.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
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 · cited 4×
“We compared NIQE with three FR indices: PSNR, SSIM [9] and multiscale SSIM (MS-SSIM) [18], five general purpose OA-DA algorithms - CBIQ [6], LBIQ [7], BLIINDS-II [5], DIIVINE [4], BRISQUE [3] and the DA-OU approach TMIQ [8].”
BackgroundMethodSelf-citationBook Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 1×
“, xk) are the NSS features computed in (5)(8), and ν and Σ denote the mean and covariance matrix of the MVG model, which are estimated using a standard maximum likelihood estimation procedure [16].”
MethodPattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937655 · Cited by 8,216 · cited 1×
“Images were selected from copyright free Flickr data and from the Berkeley image segmentation database [17] making sure that no overlap occurs with the test image content.”
MethodMultiscale structural similarity for image quality assessment
Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2004) · The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 · doi:10.1109/acssc.2003.1292216 · Cited by 6,253 · cited 1×
“We compared NIQE with three FR indices: PSNR, SSIM [9] and multiscale SSIM (MS-SSIM) [18], five general purpose OA-DA algorithms - CBIQ [6], LBIQ [7], BLIINDS-II [5], DIIVINE [4], BRISQUE [3] and the DA-OU approach TMIQ [8].”
MethodSelf-citationNo-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 · cited 6×
“above, their statistics are characterized by ‘quality aware’ NSS features computed from each selected patch [3].”
BackgroundMethodSelf-citationA Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms
Sheikh, H. R., Sabir, M. F., & Bovik, A. C. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881959 · Cited by 2,966 · cited 3×
“The NIQE scores are passed through a logistic non-linearity [2] before computing LCC for mapping to DMOS space.”
BackgroundMethodSelf-citationPattern recognition and machine learning
(2007) · Choice Reviews Online · doi:10.5860/choice.44-5091 · Cited by 2,650
Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality
Moorthy, A. K., & Bovik, A. C. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2147325 · Cited by 1,763 · cited 3×
“Existing general purpose NR IQA algorithms are based on models that can learn to predict human judgments of image quality from databases of human-rated distorted images [3], [4], [5], [6], [7].”
BackgroundMethodSelf-citationBlind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain
Saad, M. A., Bovik, A. C., & Charrier, C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2191563 · Cited by 1,751 · cited 3×
“Existing general purpose NR IQA algorithms are based on models that can learn to predict human judgments of image quality from databases of human-rated distorted images [3], [4], [5], [6], [7].”
BackgroundMethodSelf-citationThe statistics of natural images
Ruderman, D. (1994) · Network: Computation in Neural Systems · doi:10.1088/0954-898x/5/4/006 · Cited by 941 · cited 2×
“The coefficients (1) have been observed to reliably follow a Gaussian distribution when computed from natural images that have suffered little or no apparent distortion [10].”
BackgroundMethodSharifi, K., & Leon-Garcia, A. (1995) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/76.350779 · Cited by 540 · cited 1×
“The parameters of the GGD (α, β), can be reliably estimated using the moment-matching based approach proposed in [14].”
MethodNo-Reference Image Quality Assessment Using Visual Codebooks
Ye, P., & Doermann, D. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2190086 · Cited by 270
Learning a blind measure of perceptual image quality
Tang, H., Joshi, N., & Kapoor, A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995446 · Cited by 251 · cited 3×
“Existing general purpose NR IQA algorithms are based on models that can learn to predict human judgments of image quality from databases of human-rated distorted images [3], [4], [5], [6], [7].”
BackgroundMethodBlind Image Quality Assessment Without Human Training Using Latent Quality Factors
Mittal, A., Muralidhar, G. S., Ghosh, J., & Bovik, A. C. (2012) · IEEE Signal Processing Letters · doi:10.1109/lsp.2011.2179293 · Cited by 139 · cited 2×
“One such effort was made in this direction by the authors of [8].”
BackgroundMethodSelf-citationMultiscale skewed heavy tailed model for texture analysis
Lasmar, N.-E., Stitou, Y., & Berthoumieu, Y. (2009) · 2009 16th IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2009.5414404 · Cited by 128 · cited 3×
“The products of neighboring coefficients are well-modeled as following a zero mode asymmetric generalized Gaussian distribution (AGGD) [15]: f(x; γ, βl, βr) = γ (βl+βr)Γ( 1γ ) exp ( − ( −x βl )γ) ∀x ≤ 0 γ (βl+βr)Γ( 1γ ) exp ( − ( x βr )γ) ∀x ≥ 0.”
BackgroundMethodInfluentialNo-reference image sharpness assessment based on local phase coherence measurement
Hassen, R., Wang, Z., & Salama, M. M. A. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5496297 · Cited by 114 · cited 1×
“Since humans appear to more heavily weight their judgments of image quality from the sharp image regions [12], more salient quality measurements can be made from sharp patches.”
BackgroundStatistics of natural image distortions
Moorthy, A. K., & Bovik, A. C. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5495298 · Cited by 58 · cited 1×
“Prior studies of NSS based image quality have shown that the generalized Gaussian distribution effectively captures the behavior of the coefficients (1) of natural and distorted versions of them [13].”
BackgroundSelf-citationNo-reference image quality assessment based on visual codebook
Ye, P., & Doermann, D. (2011) · 2011 18th IEEE International Conference on Image Processing · doi:10.1109/icip.2011.6116318 · Cited by 56
Perceptual Video Processing: Seeing the Future [Point of View]
Bovik, A. C. (2010) · Proceedings of the IEEE · doi:10.1109/jproc.2010.2068371 · Cited by 19
Self-citation
Research works printed but not linked: 1
- 2012, Image obsessed, National Geographic, 221, 35
Cited by
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., & Loy, C. C. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-11021-5_5 · Cited by 4,731
EnlightenGAN: Deep Light Enhancement Without Paired Supervision
Jiang, Y., Gong, X., Liu, D., Cheng, Y., Fang, C., Shen, X., Yang, J., Zhou, P., & Wang, Z. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3051462 · Cited by 2,715
“t and LIME are not well scored, because of causing many over-exposures and sometimes amplifying the noise. 4.3.3 No-Referenced Image Quality Assessment We adopt Natural Image Quality Evaluator (NIQE) [48], a well-known no-reference image quality assessment for evaluating real image restoration without ground-truth, to…”
InfluentialZero-Reference Deep Curve Estimation for Low-Light Image Enhancement
Guo, C., Li, C., Guo, J., Loy, C. C., Hou, J., Kwong, S., & Cong, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00185 · Cited by 2,459
Kindling the Darkness: A Practical Low-light Image Enhancer
Zhang, Y., Zhang, J., & Guo, X. (2019) · Proceedings of the 27th ACM International Conference on Multimedia · doi:10.1145/3343031.3350926 · Cited by 2,102
“Four metrics are adopted for quantitative comparison, which are PSNR, SSIM, LOE [9], and NIQE [31].”
MethodDeep Learning for Image Super-Resolution: A Survey
Wang, Z., Chen, J., & Hoi, S. C. H. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2982166 · Cited by 1,969
Metadata
- Authors
- Mittal, A., Soundararajan, R., & Bovik, A. C.
- Affiliations
- The University of Texas at Austin (US)
- Venue
- IEEE Signal Processing Letters
- Published
- 2013-03
- Volume
- 20
- Issue
- 3
- Pages
- 209-212
- ISSN
- 1070-9908 (ISSN-L)
- 1558-2361
- OpenAlex
- W2102166818
- Cited by
- 6,766
- References
- 19
- Citations by year
- 2026: 856 · 2025: 1104 · 2024: 1023 · 2023: 860 · 2022: 757 · 2021: 598 · 2020: 463 · 2019: 329 · 2018: 241 · 2017: 182 · 2016: 129 · 2015: 98 · 2014: 92 · 2013: 31
- FWCI
- 73.09
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Signal Processing Letters (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
- no-reference image quality assessment, natural scene statistics, statistical features, natural image statistics, quality-aware features, image distortion
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.