Advertisement

Blind Image Deblurring Based on Local Rank

  • Li Zhu
  • Long Jin
  • Jihua ZhuEmail author
  • Zhongyu Li
  • Zhiqiang Tian
  • Huimin Lu
Article
  • 12 Downloads

Abstract

Conventional algorithms for blind image deblurring are often inaccurate at blur kernel estimation, and the recovery effect is far from perfect. To address this, we propose a single-image blind deblurring method based on local rank. For this, we first impose adaptive threshold segmentation on a conventional local rank transform, which is subsequently used to construct a novel model for blind image deblurring. Next, a half-quadratic splitting method is adopted to estimate the blur kernel and an intermediate latent image, in alternating iterations. Finally, the desired latent image is obtained by linear combination of the hyper-Laplacian model and the total-variation-l2 model, where the weights are calculated from the adaptive local ranks. Experimental results using public datasets show that the proposed approach can accurately estimate the blur kernel and effectively suppress ringing effects.

Keywords

Blind deblurring Local rank Kernel estimation Image reconstruction 

Notes

Acknowledgements

This work was supported by the National Natural Science Foundation of China under Grant no. 61573273. It is also supported by the State Key Laboratory of Rail Transit Engineering Informatization (FSDI) under Grant no.SKLKZ19-01.

References

  1. 1.
    Fergus R, Singh B, Hertzmann A, et al. (2006) Removing camera shake from a single photograph. ACM Trans Graph 25(3):787–794CrossRefzbMATHGoogle Scholar
  2. 2.
    Shan Q, Jia J, Agarwala A (2008) High-quality motion deblurring from a single image. ACM Trans Graph 27(3):1CrossRefGoogle Scholar
  3. 3.
    Krishnan D, Tay T, Fergus R (2011) Blind deconvolution using a normalized sparsity measureGoogle Scholar
  4. 4.
    Xu L, Zheng S, Jia J (2013) Unnatural l0 sparse representation for natural image deblurring. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR)Google Scholar
  5. 5.
    Pan J, Su Z (2013) Fast l0-regularized kernel estimation for robust motion deblurring. IEEE Signal Process Lett 20(9):841–844CrossRefGoogle Scholar
  6. 6.
    Shao WZ, Li HB, Elad M (2015) Bi-l0-l2-norm regularization for blind motion deblurring. J Vis Commun Image Represent 33:42–59CrossRefGoogle Scholar
  7. 7.
    Hu Z, Huang JB, Yang MH (2010) Single image deblurring with adaptive dictionary learning. In: Proceedings of IEEE international conference on image processing (ICIP), pp 1169–1172Google Scholar
  8. 8.
    Zhang H, Yang J, Zhang Y et al (2011) Sparse representation based blind image deblurring. In: Proceedings of IEEE international conference on multimedia and expo (ICME), pp 1–6Google Scholar
  9. 9.
    Cai JF, Ji H, Liu C et al (2012) Framelet-based blind motion deblurring from a single image. IEEE Trans Image Process 21(2):562–572MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Ren W, Cao X, Pan J et al (2016) Image deblurring via enhanced low-rank prior. IEEE Trans Image Process 25(7):3426–3437MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Pan J, Sun D, Pfister H et al (2016) Blind image deblurring using dark channel prior. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR)Google Scholar
  12. 12.
    Yan Y, Ren W, Guo Y et al (2017) Image deblurring via extreme channels prior. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR)Google Scholar
  13. 13.
    Chan TF, Wong CK (1998) Total variation blind deconvolution. IEEE Trans Image Process 7(3):370–375CrossRefGoogle Scholar
  14. 14.
    Perrone D, Favaro P (2014) Total variation blind deconvolution: the devil is in the details. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2909–2916Google Scholar
  15. 15.
    Cho S, Lee S (2009) Fast motion deblurring. ACM Trans Graph 28(5):145CrossRefGoogle Scholar
  16. 16.
    Xu L, Jia J (2010) Two-phase kernel estimation for robust motion deblurring. In: Proceedings of IEEE European conference on computer vision (ECCV), pp 157–170Google Scholar
  17. 17.
    Pan J, Liu R, Su Z et al (2013) Kernel estimation from salient structure for robust motion deblurring. Signal Process Image Commun 28(9):1156–1170CrossRefGoogle Scholar
  18. 18.
    Dong J, Pan J, Su Z et al (2017) Blind image deblurring with outlier handling. In: Proceedings of IEEE international conference on computer vision (ICCP), pp 2478–2486Google Scholar
  19. 19.
    Hu Z, Cho S, Wang J et al (2014) Deblurring low-light images with light streaks. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR), pp 3382–3389Google Scholar
  20. 20.
    Cho H, Wang J, Lee S (2012) Text image deblurring using text-specific properties. In: Proceedings of European conference on computer vision (ECCV), pp 524–537Google Scholar
  21. 21.
    Pan J, Hu Z, Su Z et al (2014) Deblurring text images via l0-regularized intensity and gradient prior. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR), pp 2901–2908Google Scholar
  22. 22.
    Pan J, Hu Z, Su Z et al (2014) Deblurring face images with exemplars. In: Proceedings of IEEE European conference on computer vision (ECCV), pp 47–62Google Scholar
  23. 23.
    Zabih R, Woodfill J (1994) Non-parametric local transforms for computing visual correspondence. In: Proceedings of IEEE European conference on computer vision (ECCV), pp 151–158Google Scholar
  24. 24.
    Mukherjee J (2011) Local rank transform: properties and applications. Pattern Recogn Lett 32(7):1001–1008CrossRefGoogle Scholar
  25. 25.
    Gong W, Hu L, Li J et al (2015) Combining sparse representation and local rank constraint for single image super resolution. Inf Sci 325:1–19MathSciNetCrossRefGoogle Scholar
  26. 26.
    Lan R, Zhou Y, Tang YY (2016) Quaternionic local ranking binary pattern: a local descriptor of color images. IEEE Trans Image Process 25(2):566–579MathSciNetCrossRefzbMATHGoogle Scholar
  27. 27.
    Krishnan D, Fergus R (2009) Fast image deconvolution using hyper-Laplacian priors. In: Proceedings of IEEE advances in neural information processing systems (NIPS), pp 1033–1041Google Scholar
  28. 28.
    Chan SH, Khoshabeh R, Gibson KB, et al. (2011) An augmented Lagrangian method for total variation video restoration. IEEE Trans Image Process 20(11):3097–3111MathSciNetCrossRefzbMATHGoogle Scholar
  29. 29.
    Zhang X, Wang R, Tian Y et al (2015) Image deblurring using robust sparsity priors. In: Proceedings of IEEE international conference on image processing (ICIP)Google Scholar
  30. 30.
    Köhler R, Hirsch M, Mohler B et al (2012) Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database. In: Proceedings of European conference on computer vision (ECCV), pp 27–40Google Scholar
  31. 31.
    Levin A, Weiss Y, Durand F et al (2009) Understanding and evaluating blind deconvolution algorithms. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR), pp 1964–1971Google Scholar
  32. 32.
    Zhong L, Cho S, Metaxas D et al (2013) Handling noise in single image deblurring using directional filters. In: Proceedings of IEEE computer vision and pattern recognition (CVPR)Google Scholar
  33. 33.
    Liu Y, Wang J, Cho S et al (2013) A no-reference metric for evaluating the quality of motion deblurring. ACM Trans Graph 32(6):1–12Google Scholar
  34. 34.
    Zhou Q, Yang W, Gao G et al (2019) Multi-scale deep context convolutional neural networks for semantic segmentation. World Wide Web 22(2):555–570CrossRefGoogle Scholar
  35. 35.
    Zhou Q, Zheng B, Zhu W et al (2016) Multi-scale context for scene labeling via flexible segmentation graph. Pattern Recogn 59:312–324CrossRefGoogle Scholar
  36. 36.
    Zhao W, Lu H, Wang D (2018) Multisensor image fusion and enhancement in spectral total variation domain. IEEE Trans Multimedia 20(4):866–879CrossRefGoogle Scholar
  37. 37.
    Zhao W, Zhao F, Wang D et al (2018) Multisensor image fusion and enhancement in spectral total variation domain. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 3080–3088Google Scholar

Copyright information

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

Authors and Affiliations

  1. 1.School of Software EngineeringXi’an Jiaotong UniversityXi’anPeople’s Republic of China
  2. 2.Kyushu Institute of TechnologyFukuokaJapan

Personalised recommendations