No-reference image quality assessment using fusion metric

  • Jayashri V. BagadeEmail author
  • Kulbir Singh
  • Y. H. Dandawate


This paper presents a fusion featured metric for no-reference image quality assessment of natural images. Natural images exhibit strong statistical properties across the visual contents such as leading edge, high dimensional singularity, scale invariance, etc. The leading edge represents the strong presence of continuous points, whereas high singularity conveys about non-continuous points along the curves. Both edges and curves are equally important in perceiving the natural images. Distortions to the image affect the intensities of these points. The change in the intensities of these key points can be measured using SIFT. However, SIFT tends to ignore certain points such as the points in the low contrast region which can be identified by curvelet transform. Therefore, we propose a fusion of SIFT key points and the points identified by curvelet transform to model these changes. The proposed fused feature metric is computationally efficient and light on resources. The neruofuzzy classifier is employed to evaluate the proposed feature metric. Experimental results show a good correlation between subjective and objective scores for public datasets LIVE, TID2008, and TID2013.


Image quality assessment No-reference image quality assessment Scale invariant feature transform (SIFT) Curvelet Neurofuzzy classifier 



  1. 1.
    Benitz J, Castro J, Requena I (1997) Are artificial neural networks black boxes? IEEE Trans Neural Netw 8:1156–1164CrossRefGoogle Scholar
  2. 2.
    Bianco S, Celona L, Napoletano P, Schettini R (2017) On the use of deep learning for blind image quality assessment. SIViP 12:355–362. CrossRefGoogle Scholar
  3. 3.
    Chen MJ, Bovik AC (2009) No. reference image blur assessment using multiscale gradient. In: Proceeding of IEEE quality of multimedia experience, pp 70–74Google Scholar
  4. 4.
    Djimeli A, Tchiotsop D, Tichinda R (2013) Analysis of interest points of curvelet coefficients contributions of microscopic images and improvement of edges. Signal and Image Processing: An International Journal (SIPIJ) 4Google Scholar
  5. 5.
    Fan C, Zhang Y, Feng L, Jiang A (2018) No reference image quality assessment based on multi-expert convolution neural network. IEEE Access 6:8934–8943CrossRefGoogle Scholar
  6. 6.
    Fang Y, Ma K, Wang Z, Lin W, Fang Z, Zhai G (2015) No reference quality assessment of contrast distorted images based on natural scene statistics. IEEE Signal Processing Letters 22:838–842Google Scholar
  7. 7.
    Feng T, Deng D, Yan J, Zhang W, Shi W, Zou L (2016) Sparse representation of salient regions for no reference image quality assessment. Int J Adv Robot Syst. CrossRefGoogle Scholar
  8. 8.
    Gu K, Zhai G, Yang X, Zhang W (2015) Using free energy principle for blind image quality assessment. IEEE Transactions on Multimedia 17:50–63CrossRefGoogle Scholar
  9. 9.
    Hung Do Q, Chen J (2013) A neuro-fuzzy approach in the classification of students’ academic performance. Computational intelligence and neuroscience article ID 179097Google Scholar
  10. 10.
    Jhang Y, Damon M, Chandler D (2013) An algorithm for no-reference image quality assessment based on log-derivative statistics of natural scenes. SPIE Proceedings: Image Quality and System Performance 8653:86530J-10Google Scholar
  11. 11.
    Kamble V, Bhurchandi KM (2015) No reference image quality assessment algorithm: a survey. Optik International Journal for Light & Electron Optics 126:1090–1097CrossRefGoogle Scholar
  12. 12.
    Keelan BW Handbook of image quality, characterization and prediction. Marcel Dekker Inc. ISBN 0-8247-0770-2Google Scholar
  13. 13.
    Li L, Wu D, Wu J, Qian J, Chen B (2016) No reference image quality assessment with a gradient-induced dictionary. KSII Transactions on Internet and Information 10:288–306Google Scholar
  14. 14.
    Liu J, Yu X (2008) Research on SAR image matching technology based on SIFT. In: The international archives of the photogrammetry, remote sensing and spatial information sciences XXXVII part B1Google Scholar
  15. 15.
    Liu L, Dong H, Huang H, Bovik A (2014) No reference image quality assessment in curvelet domain. Signal Process Image Commun 29:494–505CrossRefGoogle Scholar
  16. 16.
    Liu W, Li C, Chi Y, Sun X (2014) Image quality assessment based on SIFT and SSIM. In: Advances in image and graphics technologies, IGTA 2014, Communications in Computer and Information Science 437. Springer, Berlin HeidelbergGoogle Scholar
  17. 17.
    Lu W, Zeng K, Tao D, Yuan Y, Gao X (2010) No-reference image quality assessment in contourlet. Neurocomputing 73:784–794CrossRefGoogle Scholar
  18. 18.
    Lv X, Qin M, Chen X, Wei G (2018) No reference image quality assessment based on statistics of convolution of feature maps. In: AIP conference proceeding 1995: 040034-1-040034-5.
  19. 19.
    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 27:1202_1213MathSciNetzbMATHGoogle Scholar
  20. 20.
    Mittal A, Moorthy A, Bovik AC (2011) Blind/referenceless image spatial quality evaluator. In: IEEE conference on signals, system and, computers, pp 723–727Google Scholar
  21. 21.
    Mittal A, Moorthy AK, Bovik AC (2012) No reference image quality assessment in the spatial domain. IEEE Trans Image Process 21:4695–4707MathSciNetCrossRefGoogle Scholar
  22. 22.
    Mittal A, Soundararajan R, Bovik A (2013) Making a completely blind image quality analyzer. IEEE Signal processing letters 20:209–213CrossRefGoogle Scholar
  23. 23.
    Moorthy AK, Bovik AC (2010) A two-step framework for constructing blind image quality indices. IEEE Signal Processing Letters 17:513–516CrossRefGoogle Scholar
  24. 24.
    Moorthy A, Bovik A (2011) Blind image quality assessment: from natural scene statistics to perceptual quality. IEEE Trans Image Process 20:3350–3364MathSciNetCrossRefGoogle Scholar
  25. 25.
    Nizami I, Masid M, Khursid K (2018) Feature selection for no-reference image quality assessment using natural scene statistics. Turk J Electr Eng Comput Sci 26:2163–2177CrossRefGoogle Scholar
  26. 26.
    Ponomarenko N, Lukin V, Zelensky A, Egiazarian K, Carli M, Battisti F (2009) TID2008 - a database for evaluation of full-reference visual quality assessment metrics. Advances of Modern Radio electronics 10:30–45Google Scholar
  27. 27.
    Ponomarenko N, Battisti F, Egiazarian K, Astola J, Lukin V (2009) Metrics performance comparison for colour image database. In: Fourth international workshop on video processing and quality metrics for consumer electronics, vol 27, pp 1–6Google Scholar
  28. 28.
    Ponomarenko N, Ieremeiev O, Lukin V, Egiazarian K, Jin L, Astola J, Vozel B, Chehdi K, Carli M, Battisti F, Kuo J (2013) Color image database TID2013: peculiarities and preliminary results. In: 4th European workshop on visual information processing EUVIP 106–111Google Scholar
  29. 29.
    Ponomarenko N, Jin L, Ieremeiev O, Lukin V, Egiazarian K, Astola J, Vozel B, Chehdi K, Carli M, Battisti F, Kuo J (2015) Image database TID2013: peculiarities, results and perspectives. Signal Process Image Commun 30:57–77CrossRefGoogle Scholar
  30. 30.
    Qin M, Lv X, Chen X, Wang W (2017) Hybrid NSS features for no-reference image quality assessment. IET Image Process 11:443–449CrossRefGoogle Scholar
  31. 31.
    Qiu F (2008) Nero-fuzzy based analysis of hyperspectral imagery. Photogramm Eng Remote Sens 74:1235–1247CrossRefGoogle Scholar
  32. 32.
    Saad MA, Bovik AC, Charrier C (2012) Blind image quality assessment: a natural scene statistics approach in the DCT domain. IEEE Trans Image Process 21:3339–3351MathSciNetCrossRefGoogle Scholar
  33. 33.
    Sheikh HR, Bovik AC, Cormack LK (2005) No-reference quality assessment using natural scene statistics: JPEG2000. IEEE Trans Image Process 14:1918–1927CrossRefGoogle Scholar
  34. 34.
    Sheikh HR, Wang Z, Cormack L, Bovik AC LIVE image quality assessment database release 2.
  35. 35.
    Telabi H, Milanfar (2018) NIMA: Neural image assessment. IEEE Trans Image Process 27:3998–4011MathSciNetCrossRefGoogle Scholar
  36. 36.
    Wang Z, Bovik A (2002) Why is image quality assessment so difficult. IEEE Signal Processing Letters 4:3313–3316Google Scholar
  37. 37.
    Wang Z, Bovik A (2006) A lecture book on modern image quality assessment. Morgan and Claypool edition publisherGoogle Scholar
  38. 38.
    Wang G, Wu Z, Yan H, Cui M (2016) No reference image quality assessment based on non-subsample shearlet transform and natural scene statistics. Optoelectron Lett 12CrossRefGoogle Scholar
  39. 39.
    Wei D, Lie Y (2016) No reference image quality assessment based on SIFT feature points. International Journal of Simulation: Systems, Science and Technology 17:17Google Scholar
  40. 40.
    Zhang D, Ding Y, Zheng N (2012) Nature scene statistics approach based on ICA for no reference image quality assessment. In: Proceedings of international workshop on information and electronics engineering (IWIEE), vol 29, pp 3589–3593CrossRefGoogle Scholar
  41. 41.
    Zhang Y, Moorthy A, Chandler D, Bovik A (2014) C-DIIVINE: no reference image quality assessment based on local magnitude and phase statistics of natural scenes. Signal Process Image Commun 29:725–747CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Jayashri V. Bagade
    • 1
    Email author
  • Kulbir Singh
    • 2
  • Y. H. Dandawate
    • 3
  1. 1.Department of Information TechnologyVishwakarma Institute of Information TechnologyPuneIndia
  2. 2.Department of Electronics and Communication EngineeringThapar Institute of Engineering and TechnologyPatialaIndia
  3. 3.Department of Electronics and TelecommunicationVishwakarma Institute of Information TechnologyPuneIndia

Personalised recommendations