Skip to main content
SpringerLink
Log in

Blind Image Quality Assessment for Multiple Distortion Image

  • Published:
Circuits, Systems, and Signal Processing Aims and scope Submit manuscript

Abstract

In real world, images always do not have the ground truth that we can compare with. Therefore, we consider blind image quality assessment (BIQA) no-reference methods for the real-world images without ground truth. However, the existing BIQA can only consider an image with a single-distortion-type. For these reasons, a multitask hierarchical blind image quality assessment model is proposed to assess multiple distortion types of images. An integrated algorithm that incorporates an improved deep neural network by introducing a penalty term and a shared layer is proposed to improve its generalization performance. Experimental results show that the proposed algorithm is significantly better than algorithms such as DIIVINE and BRISQUE in the Pearson linear correlation coefficient and Spearman rank-order correlation coefficient; for each image, the three most significant distortion categories and probability results are obtained through the algorithm. It can effectively solve the problem of image quality assessment when multiple types of distortion are present.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

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

Similar content being viewed by others

Data Availability

The data that support the findings of this study are available from the author upon reasonable request.

References

  1. J. Ballé, V. Laparra, E P. Simoncelli, Density modeling of images using a generalized normalization transformation. arXiv preprint arXiv:1511.06281 (2015)

  2. J. Ballé, V. Laparra, E. P. Simoncelli, End-to-end optimized image compression. arXiv preprint arXiv:1611.01704 (2016)

  3. J. Beron, H.D. Benitez-Restrepo, A.C. Bovik, Blind image quality assessment for super resolution via optimal feature selection. IEEE Access 8, 143201–143218 (2020)

    Article  Google Scholar 

  4. S. Bianco, L. Celona, P. Napoletano et al., On the use of deep learning for blind image quality assessment. Signal Image Video Process. 12(2), 355–362 (2018)

    Article  Google Scholar 

  5. S. Bosse, D. Maniry, K.R. Müller et al., Deep neural networks for no-reference and full-reference image quality assessment. IEEE Trans. Image Process. 27(1), 206–219 (2017)

    Article  MathSciNet  Google Scholar 

  6. M. Carandini, D.J. Heeger, Normalization as a canonical neural computation. Nat. Rev. Neurosci. 13(1), 51 (2012)

    Article  Google Scholar 

  7. D. A. Clevert, T. Unterthiner, S. Hochreiter, Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289 (2015)

  8. D.I.H. Farías, R.G. Cabrera, T.C. Fraga et al., Modification of the marching cubes algorithm to obtain a 3D representation of a planar image. Program. Comput. Softw. 47(3), 215–223 (2021)

    Article  MathSciNet  Google Scholar 

  9. R. Fang, D. Wu, No-reference image quality assessment based on BNB measurement. In 2013 IEEE China Summit and International Conference on Signal and Information Processing. IEEE, 2013: 528–532

  10. Y. Fang, K. Ma, Z. Wang et al., No-reference quality assessment of contrast-distorted images based on natural scene statistics. IEEE Signal Process. Lett. 22(7), 838–842 (2014)

    Google Scholar 

  11. M. Gonzalez-Lee, H. Vazquez-Leal, J.F. Gomez-Aguilar et al., Exploring the cross-correlation as a means for detecting digital watermarks and its reformulation into the fractional calculus framework. IEEE Access 6, 71699–71718 (2018)

    Article  Google Scholar 

  12. T. Gu, X. Liu, Q. Sang, et al. No-reference image quality assessment algorithm for stereoscopic images via dual-tree complex wavelet transform. Comput. Eng. Appl. (2019)

  13. Y. Guo, X. Zhao, J. Li et al., Blind multiple-input multiple-output image phase retrieval. IEEE Trans. Ind. Electron. 67(3), 2220–2230 (2019)

    Article  Google Scholar 

  14. Y. Guo, J. Chen, X. Ren et al., Joint raindrop and haze removal from a single image. IEEE Trans. Image Process. 29, 9508–9519 (2020)

    Article  Google Scholar 

  15. K. He, X. Zhang, S. Ren, et al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1026–1034

  16. S. Khattak, I. Hussain, J. F. Gomez-Aguilar, et al. Analysis of PD-type iterative learning control for discrete-time singular system. Math. Methods Appl. Sci. (2021)

  17. J. Kim, S. Lee, Fully deep blind image quality predictor. IEEE J. Sel. Topics Signal Process. 11(1), 206–220 (2016)

    Article  Google Scholar 

  18. D. P. Kingma, J. Ba, Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  19. Q. Li, W. Lin, K. Gu et al., Blind image quality assessment based on joint log-contrast statistics. Neurocomputing 331, 189–198 (2019)

    Article  Google Scholar 

  20. D. Liang, X. Gao, W. Lu et al., Deep multi-label learning for image distortion identification. Signal Process. 172, 107536 (2020)

    Article  Google Scholar 

  21. Y.H. Liu, K.F. Yang, H.M. Yan, No-reference image quality assessment method based on visual parameters. J. Electron. Sci. Technol. 17(2), 171–184 (2019)

    Google Scholar 

  22. S. Lyu, Divisive normalization: justification and effectiveness as efficient coding transform. Adv. Neural Inf. Process. Syst. 23, 1522–1530 (2010)

    Google Scholar 

  23. K. Ma, W. Liu, K. Zhang et al., End-to-end blind image quality assessment using deep neural networks. IEEE Trans. Image Process. 27(3), 1202–1213 (2017)

    Article  MathSciNet  Google Scholar 

  24. O. Martínez-Fuentes, F. Meléndez-Vázquez, G. Fernández-Anaya et al., Analysis of fractional-order nonlinear dynamic systems with general analytic kernels: lyapunov stability and inequalities. Mathematics 9(17), 2084 (2021)

    Article  Google Scholar 

  25. A. Mittal, A K. Moorthy, A C. Bovik . Blind/referenceless image spatial quality evaluator. In 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR). IEEE, 2011: 723–727

  26. A. Mittal, W. Lu et al., Deep multi-label learning for image distortion identification. Signal Process. 172, 107536 (2020)

    Article  Google Scholar 

  27. P. Nollau, C. Wagener, I.S. Division et al., Methods for detection of point mutations: performance and quality assessment. Clin. Chem. 43(7), 1114–1128 (1997)

    Article  Google Scholar 

  28. O. Schwartz, E.P. Simoncelli, Natural signal statistics and sensory gain control. Nat. Neurosci. 4(8), 819–825 (2001)

    Article  Google Scholar 

  29. K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

  30. J.E. Solís-Pérez, J.F. Gómez-Aguilar, R.F. Escobar-Jiménez et al., Blood vessel detection based on fractional Hessian matrix with non-singular Mittag–Leffler Gaussian kernel. Biomed. Signal Process. Control 54, 101584 (2019)

    Article  Google Scholar 

  31. N.H. Tuan, V.A. Khoa, P.T.K. Van et al., An improved quasi-reversibility method for a terminal-boundary value multi-species model with white Gaussian noise. J. Comput. Appl. Math. 384, 113176 (2021)

    Article  MathSciNet  Google Scholar 

  32. J. Wu, J. Ma, F. Liang et al., End-to-end blind image quality prediction with cascaded deep neural network. IEEE Trans. Image Process. 29, 7414–7426 (2020)

    Article  Google Scholar 

  33. J. Wu, J. Ma, F. Liang, et al. End-to-end blind image quality assessment with cascaded deep features. In 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2019: 1858–1863

  34. C. Yang, X. Zhang, P. An et al., Blind image quality assessment based on multi-scale KLT. IEEE Trans. Multimedia 23, 1557–1566 (2020)

    Article  Google Scholar 

  35. P. Ye, J. Kumar, L. Kang, et al. Unsupervised feature learning framework for no-reference image quality assessment. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2012: 1098–1105

  36. P. Ye, J. Kumar, D. Doermann. Beyond human opinion scores: blind image quality assessment based on synthetic scores. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014: 4241–4248

  37. P. Zhang, W. Zhou, L. Wu, et al. SOM: semantic obviousness metric for image quality assessment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 2394–2402

  38. W. Zhang, K. Zhai, G. Zhai, et al. Learning to blindly assess image quality in the laboratory and wild. In 2020 IEEE International Conference on Image Processing (ICIP). IEEE, 2020: 111–115

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China under Grant 61301250, China Scholarship Council under Grant [2020]1417, Key Research and Development Project of Shanxi Province under Grant 201803D421035, Natural Science Foundation for Young Scientists of Shanxi Province under Grant 201901D211313, Shanxi Scholarship Council of China under Grant HGKY2019080 and 2020-127, Shanxi Province Postgraduate Excellent Innovation Project Plan under Grant 2021Y679, Open project of Guangdong Provincial Key Laboratory of Digital Signal and Image Processing in 2021, Natural Science Foundation of Fujian Province under Grant 2020J01937.

Author information

Author notes

  1. Xiangning Zhao contributed equally to this study.

Authors and Affiliations

  1. College of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan, 030024, Shanxi, China

    Chao Jin, Qi Xiong & Yina Guo

  2. Shanxi Equipment Manufacturing Group Co. Ltd, China Railway Taiyuan Group Co., Ltd, Taiyuan, 030000, Shanxi, China

    Xiangning Zhao

  3. Key Laboratory of Digital Signal and Image Processing of Guangdong Province, Shantou University, Shantou, 515063, Guangdong, China

    Yina Guo

Authors
  1. Chao Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiangning Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qi Xiong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yina Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yina Guo.

Ethics declarations

Conflict of interest

The authors declared that they have no conflict of interest with this work.

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jin, C., Zhao, X., Xiong, Q. et al. Blind Image Quality Assessment for Multiple Distortion Image. Circuits Syst Signal Process 41, 5807–5826 (2022). https://doi.org/10.1007/s00034-022-02055-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00034-022-02055-x

Keywords

Search

Navigation