Skip to main content
SpringerLink
Log in

Automatic blur-kernel-size estimation for motion deblurring

  • Original Article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

Existing image deblurring approaches often take the blur-kernel-size as an important manual parameter. When set improperly, this parameter can lead to significant errors in the estimated blur kernels. However, manually specifying a proper kernel size for an input image is usually a tedious trial-and-error process. In this paper, we propose a new approach for automatically estimating the underlying blur-kernel-size value that can lead to good kernel estimation. Our approach takes advantage of the autocorrelation map (automap) of image gradients that is known to reflect the motion blur information. We show that the standard automap suffers from structural edges in the image and cannot be directly used for kernel size estimation. To alleviate this problem, we develop a modified automap method that contains a directional attenuation component, which can effectively reduce the influence of structural edges, leading to more accurate and reliable kernel size estimation. Experimental results suggest that the proposed approach can help state-of-the-art deblurring algorithms achieve accurate kernel estimation without relying on manual parameter tweaking.

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23

Similar content being viewed by others

Notes

  1. The four-point Laplacian filter \(\mathbf {L}\) is a \(3\times 3\) matrix, where \(\mathbf {L}(0,0)=4\) and \(\mathbf {L}(x,y)=-1\) at \(x\) and \(y\) that \(|x|+|y| = 1\), and zero otherwise.

  2. Binary executable is provided by the authors.

  3. MATLAB code available at: http://cs.nyu.edu/~dilip/research/blind-deconvolution/.

  4. MATLAB code available at: www.wisdom.weizmann.ac.il/~levina.

References

  1. Biemond, J., Tekalp, A., Lagendijk, R.: Maximum likelihood image and blur identification: a unifying approach. Opt. Eng. 29(5), 422–435 (1990)

    Article  Google Scholar 

  2. Burns, J., Hanson, A., Riseman, E.: Extracting straight lines. IEEE Trans. Pattern Anal. Mach. Intell. 8(4), 425–455 (1986)

    Article  Google Scholar 

  3. Cai, J., Ji, H., Liu C., Shen, Z.: Blind motion deblurring from a single image using sparse approximation. In: Proceedings of Computer Vision and Pattern Recognition, pp. 104–111 (2009)

  4. Chan, T., Wong, C.: Total variation blind deconvolution. IEEE Trans. Image Process. 7(3), 370–375 (1998)

    Article  Google Scholar 

  5. Chen, J., Yuan, L., Tang C., Quan, L.: Robust dual motion deblurring. In: Proceedings of Computer Vision and Pattern Recognition, pp. 1–8 (2008)

  6. Cho, T., Joshi, N., Zitnick, C., Kang, S., Szeliski R., Freeman, W.: A content-aware image prior. In: Proceedings of Computer Vision and Pattern Recognition, pp. 169–176 (2010)

  7. Cho, S., Lee. S.: Fast motion deblurring. ACM Trans. Graph., vol. 28, no. 5 (2009).

  8. Cho, T., Paris, S., Horn, B., Freeman, W., Gool, L.: Blur kernel estimation using the radon transform. In: Proceedings of Computer Vision and Pattern Recognition, pp. 241–248 (2011)

  9. Cho, T., Joshi, N., Zitnick, C., Kang, S., Szeliski, R., Freeman, W.: Image restoration by matching gradient distributions. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 683–694 (2012)

    Article  Google Scholar 

  10. Fergus, R., Singh, B., Hertzmann, A., Roweis, S., Freeman, W.: Removing camera shake from a single photograph. ACM Trans. Graph. 25(3), 787–794 (2006)

    Article  Google Scholar 

  11. Fienup, J.: Phase retrieval algorithms: a comparison. Appl. Opt. 21(15), 2758–2769 (1982)

    Article  Google Scholar 

  12. Gioi, R., Jakubowicz, J., Morel J., Randall, G.: LSD: a line segment detector. J. Image Process. Line (2012)

  13. Gioi, R., Jakubowicz, J., Morel, J., Randall, G.: On straight line segment detection. J. Math. Imag. Vis. 32(3), 317–347 (2008)

    Google Scholar 

  14. Gioi, R., Jakubowicz, J., Morel, J., Randall, G.: LSD: a fast line segment detector with a false detection control. IEEE Trans. Pattern Anal. Mach. Intell. 32(4), 722–732 (2010)

    Article  Google Scholar 

  15. Goldstein A., Fattal, R.: Blur-kernel estimation from spectral irregularities. In: Proceedings of European Conference on Computer Vision, pp. 622–635 (2012)

  16. http://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio

  17. http://en.wikipedia.org/wiki/Radon_transform

  18. Hu, W., Xue, J., Zheng, N.: PSF estimation via gradient domain correlation. IEEE Trans. Image Process. 21(1), 386–392 (2012)

    Article  MathSciNet  Google Scholar 

  19. Jia, J.: Single image motion deblurring using transparency. In: Proceedings of Computer Vision and Pattern Recognition, pp. 1–8 (2007)

  20. Joshi, N., Zitnick, C., Szeliski, R., Kriegman, D.: Image deblurring and denoising using color priors. In: Proceedings of Computer Vision and Pattern Recognition, pp. 1550–1557 (2009)

  21. Joshi, N. Szeliski, R., Kriegman, D.: PSF estimation using sharp edge prediction. In: Proceedings of Computer Vision and Pattern Recognition, pp. 1–8 (2008)

  22. Kahn, P., Kitchen, L., Riseman, E.: A fast line finder for vision-guided robot navigation. IEEE Trans. Pattern Anal. Mach. Intell. 12(11), 1098–1102 (1990)

    Article  Google Scholar 

  23. Kohler, R. , Hirsch, M., Mohler, B., Scholkopf B., Harmeling, S.: Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database. In: Proceedings of European Conference on Computer Vision, pp. 27–40 (2012)

  24. Krishnan D., Fergus, R.: Fast image deconvolution using hyper-kaplacian priors. In: Proceedings of Neural Information Processing Systems, pp. 1033–1041 (2009)

  25. Krishnan, D., Tay T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: Proceedings of Computer Vision and Pattern Recognition, pp. 233–240 (2011)

  26. Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: Proceedings of Computer Vision and Pattern Recognition, pp. 233–240 (2011)

  27. Levin, A., Weiss, Y., Durand F., Freeman, W.: Efficient marginal likelihood optimization in blind deconvolution. In: Proceedings of Computer Vision and Pattern Recognition, pp. 2657–2664 (2011)

  28. Levin, A., Weiss, Y. Durand, F., Freeman, W.: Understanding and evaluating blind deconvolution algorithms. In: Proceedings of Computer Vision and Pattern Recognition, pp. 1964–1971 (2009)

  29. Matas, J., Galambos, C., Kittler, J.: Robust detection of lines using the progressive probabilistic hough transform. Comput. Vis. Image Underst. 78(1), 119–137 (2000)

    Article  Google Scholar 

  30. Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Graph. 27(3), 73–83 (2008)

    Article  Google Scholar 

  31. Simoncelli, E.: Statistical models for images: compression, restoration and synthesis. In: Proceedings of Asilomar Conference on Signals, Systems and Computers, pp. 673–678 (1997)

  32. Sun, L., Hays, J.: Super-resolution from internet-scale scene matching: In: Proceedings of International Conference on Computational Photography, pp. 1–12 (2012)

  33. Topal, C., Akinlar, C., Genc, Y., Kriegman, D.: Edge drawing: a heuristic approach to robust real-time edge detection. In: Proceedings of International Conference on Pattern Recognition, pp. 2424–2427 (2010)

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

    Article  Google Scholar 

  35. Xu, L., Jia, J.: Two-phase kernel estimation for robust motion deblurring. In: Proceedings of European Conference on Computer Vision, pp. 157–170 (2010)

  36. Xu, L., Zheng S., Jia, J.: Unnatural \(L_0\) sparse representation for natural image deblurring. In: Proceedings of Computer Vision and Pattern Recognition, pp. 1107–1114 (2013)

  37. Xu, L., Yan, Q., Xia, Y., Jia, J.: Structure extraction from texture via relative total variation. ACM Trans. Graph. 31(6), 787–794 (2006)

    Google Scholar 

  38. Yitzhaky, Y., Mor, I., Lantzman, A., Kopeika, N.: Direct method for restoration of motion-blurred images. J. Opt. Soc. Am. A 15(6), 1512–1519 (1998)

    Article  Google Scholar 

  39. You, Y., Kaveh, M.: Feature-oriented image enhancement using shock filters. SIAM J. Numer. Anal. 27(4), 919–940 (1990)

    Article  Google Scholar 

  40. You, Y., Kaveh, M.: A regularization approach to joint blur identification an image restoration. IEEE Trans. Image Process. 5(3), 416–428 (1996)

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by the National Natural Science Foundation of China under Grants 61370039, 61175025, 61203277, 61375024 and 61203279.

Author information

Authors and Affiliations

  1. NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Shaoguo Liu & Chunhong Pan

  2. School of Control Science and Engineering, Shandong University, Jinan, China

    Haibo Wang

  3. Adobe Research, Seattle, WA, USA

    Jue Wang & Sunghyun Cho

Authors
  1. Shaoguo Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haibo Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jue Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sunghyun Cho
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chunhong Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shaoguo Liu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, S., Wang, H., Wang, J. et al. Automatic blur-kernel-size estimation for motion deblurring. Vis Comput 31, 733–746 (2015). https://doi.org/10.1007/s00371-014-0998-2

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-014-0998-2

Keywords

Search

Navigation