Blind image quality assessment using a combination of statistical features and CNN


Blind Image Quality Assessment (BIQA) has been an enticing research problem in image processing, during the last few decades. In spite of the introduction of several BIQA algorithms, quantifying image quality without the help of a reference image still remains an unsolved problem. We propose a method for BIQA, combining Natural Scene Statistics (NSS) feature and Probabilistic Quality representation by a CNN. A certain number of features are considered for each image. We also propose to increase the NSS feature set alongside with the same CNN architecture and compare its results accordingly. Support Vector Machine (SVM) regression is applied on these features to get a quality score for that particular image. The results obtained by applying the proposed quality score on benchmark datasets, show the effectiveness of the proposed quality metric compared to the state-of-the-art metrics.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6


  1. 1.

    Bandawi HA, Deng G (2018) Blind image quality assessment based on Benford’s law. IET Image Process 12(11):1983–1993

    Article  Google Scholar 

  2. 2.

    Fan DP, Cheng MM, Liu Y, Li T, Borji A (2019) Structure-measure: A new way to evaluate foreground maps, ICCV

  3. 3.

    Fan DP, Gong C, Cao Y, Ren B, Cheng MM, Borji A (2018) Enhanced-alignment measure for binary foreground map evaluation, IJCAI

  4. 4.

    Fan DP, Zhang SC, Wu YH, Liu Y, Cheng MM, Ren B, Rosin PL, Ji R (2019) Scoot: A perceptual metric for facial sketches, ICCV

  5. 5.

    Field DJ (1987) Relations between the statistics of natural images and the response properties of cortical cells. J Opt Soc Am A 4(12):2379–2394

    Article  Google Scholar 

  6. 6.

    Ghadiyaram D, Bovik AC (2015) LIVE in the wild image quality challenge database. Online:

  7. 7.

    Ghadiyaram D, Bovik AC (2016) Massive online crowdsourced study of subjective and objective picture quality. IEEE Trans Image Process 25(1):372–387

    MathSciNet  Article  Google Scholar 

  8. 8.

    He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition, arXiv:1512.03385

  9. 9.

    Hou W, Gao X, Tao D, Li X (2015) Blind image quality assessment via deep learning. IEEE Trans Neural Netw Learn Syst 26(6):1275–1286

    MathSciNet  Article  Google Scholar 

  10. 10.

    Kamble V, Bhurchandi KM (2015) No-reference image quality assessment algorithms: a survey. Optik, Elsevier 126(11-12):1090–1097

    Google Scholar 

  11. 11.

    Kundu D, Choi LK, Bovik AC, Evans BL (2018) Perceptual quality evaluation of synthetic pictures distorted by compression and transmission. Signal Process Image Commun 61:54–72

    Article  Google Scholar 

  12. 12.

    Larson EC, Chandler DM (2010) Most apparent distortion: full-reference image quality assessment and the role of strategy. Journal of Electronic Imaging 19:1

    Google Scholar 

  13. 13.

    Li Y, Po LM, Xu X, Feng L, Yuan F, Cheung CH, Cheung KW (2015) No-reference image quality assessment with Shearlet transform and deep neural networks. Neurocomputing 154:94–109

    Article  Google Scholar 

  14. 14.

    Liu L, Liu B, Huang H, Bovik AC (2014) No-reference image quality assessment based on spatial and spectral entropies. Signal Processing: Image Communication, Elsevier 29(8):856–863

    Google Scholar 

  15. 15.

    Liu X, van de Weijer J, Bagdanov AD (2017) RankIQA: Learning from rankings for no-reference image quality assessment, ICCV

  16. 16.

    Lu X, Ma C, Ni B, Yang X (2019) Adaptive region proposal with channel regularization for robust object tracking.

  17. 17.

    Lu X, Ma C, Ni B, Yang X, Reid I, Yang MH (2018) Deep Regression tracking with shrinkage loss, ECCV

  18. 18.

    Lu X, Ni B, Ma C, Yang X (2019) Learning transform-aware attentive network for object tracking. Neurocomputing 349:133–144

    Article  Google Scholar 

  19. 19.

    Lu X, Wang W, Ma C, Shen J, Shao L, Porikli F (2019) See more, know more: Unsupervised video object segmentation with Co-Attention siamese networks, CVPR

  20. 20.

    Ma K, Liu W, Zhang K, Duanmu Z, Wang Z, Zuo W (2018) End-to-end blind image quality assessment using deep neural networks. IEEE Trans Image Process 27(3):1202–1213

    MathSciNet  Article  Google Scholar 

  21. 21.

    Margolin R, Zelnik-Manor L, Tal A (2014) How To evaluate foreground maps?, CVPR

  22. 22.

    Mittal A, Krishna Moorthy A, Bovik AC (2012) No-Reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708

    MathSciNet  Article  Google Scholar 

  23. 23.

    Moorthy AK, Bovik AC (2011) Blind image quality assessment: From natural scene statistics to perceptual quality. IEEE Trans Image Process 20(12):3350–3364

    MathSciNet  Article  Google Scholar 

  24. 24.

    Oszust M (2019) Local feature descriptor and derivative filters for blind image quality assessment. IEEE Signal Processing Letters 26(2):322–326

    Article  Google Scholar 

  25. 25.

    Reddy SV, Dev DC, Kothari N, Channappayya SS (2019) Generating image distortion maps using convolutional autoencoders with application to no reference image quality assessment. IEEE Signal Processing Letters 26(1):89–93

    Article  Google Scholar 

  26. 26.

    Ruderman DL (1994) The statistics of natural images. Netw Comput Neural Syst 5(4):517–548

    Article  Google Scholar 

  27. 27.

    Ruderman DL, Cronin TW, Chiao C (1998) Statistics of cone response to natural images: Implications for visual coding. J Opt Soc Am A 15(8):2036–2045

    Article  Google Scholar 

  28. 28.

    Saad MA, Bovik AC, Charrier C (2012) Blind image quality assessment: a natural scene statistics approach in the DCT domain. IEEE Trans Image Process 21 (8):3339–3352

    MathSciNet  Article  Google Scholar 

  29. 29.

    Sheikh HR, Sabir MF, Bovik AC (2006) A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans Image Process 15 (11):3440–3451

    Article  Google Scholar 

  30. 30.

    Sheikh HR, Sabir MF, Bovik AC (2006) A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans Image Process 15 (11):3440–3451

    Article  Google Scholar 

  31. 31.

    Sheikh HR, Wang Z, Cormack L, Bovik AC (2005) LIVE image quality assessment database release 2.

  32. 32.

    Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition, ICLR

  33. 33.

    Sun T, Ding S, Xu X (2018) An image response framework for no-reference image quality assessment. Comput Electr Eng 70:764–776

    Article  Google Scholar 

  34. 34.

    Temel D, Prabhushankar M, Regib GA (2016) UNIQUE: Unsupervised image quality estimation. IEEE Signal Processing Letters 23(10):1414–1418

    Article  Google Scholar 

  35. 35.

    Wang W, Lu X, Shen J, Crandall D, Shao L (2019) Zero-Shot video object segmentation via attentive graph neural networks, ICCV

  36. 36.

    Wang X, Liang X, Yang B, Li FWB (2019) No-reference synthetic image quality assessment with convolutional neural network and local image saliency. Computational Visual Media 5:193–208

    Article  Google Scholar 

  37. 37.

    Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13 (4):600–612

    Article  Google Scholar 

  38. 38.

    Wu J, Lin W, Shi G, Liu A (2013) Reduced-reference image quality assessment with visual information fidelity. IEEE Trans Multimed 15(7):1700–1705

    Article  Google Scholar 

  39. 39.

    Wu Q, Li HL, Ngan KN, Ma K (2018) Blind image quality assessment using local consistency aware retriever and uncertainty aware evaluator. IEEE Trans Circuits Syst Video Technol 28(9):2078–2089

    Article  Google Scholar 

  40. 40.

    Yan W, Na L, Zongying L, Zhaorui G, Haiyong Z, Bing Z, Mengnan S (2018) An imaging-inspired no-reference underwater color image quality assessment metric. Comput Electr Eng 70:904–913

    Article  Google Scholar 

  41. 41.

    Yang J, Sim K, Jiang B, Lu W (2018) Blind image quality assessment utilising local mean eigenvalues. IET Image Process 54(12):754–756

    Google Scholar 

  42. 42.

    Yang X, Sun Q, Wang T (2018) Image quality assessment via spatial structural analysis. Comput Electr Eng 70:349–365

    Article  Google Scholar 

  43. 43.

    Zeng H, Zhang L, Bovik AC (2017) A probabilistic quality representation approach to deep blind image quality prediction, arXiv:1708.08190

  44. 44.

    Zhang L, Bovik AC (2015) A Feature-Enriched completely blind image quality evaluator. IEEE Trans Image Process 24(8):2579–2591

    MathSciNet  Article  Google Scholar 

  45. 45.

    Zhang Y, Wu J, Xie X, Li L, Shi G (2016) Blind image quality assessment with improved natural scene statistics model. Digital Signal Processing, Elsevier 57:56–65

    MathSciNet  Article  Google Scholar 

Download references


The authors wish to thank NVIDIA for their research grant in form of a TITANX GPU as faculty GPU grant.

Author information



Corresponding author

Correspondence to Snehasis Mukherjee.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Jeripothula, A.B., Velamala, S.K., Banoth, S.K. et al. Blind image quality assessment using a combination of statistical features and CNN. Multimed Tools Appl (2020).

Download citation


  • Blind image quality assessment
  • NSS
  • CNN