Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs

  • Lei Xiao
  • Jue Wang
  • Wolfgang Heidrich
  • Michael Hirsch
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9907)

Abstract

Photographs of text documents taken by hand-held cameras can be easily degraded by camera motion during exposure. In this paper, we propose a new method for blind deconvolution of document images. Observing that document images are usually dominated by small-scale high-order structures, we propose to learn a multi-scale, interleaved cascade of shrinkage fields model, which contains a series of high-order filters to facilitate joint recovery of blur kernel and latent image. With extensive experiments, we show that our method produces high quality results and is highly efficient at the same time, making it a practical choice for deblurring high resolution text images captured by modern mobile devices.

Keywords

Text document Camera motion Blind deblurring High-order filters 

Notes

Acknowledgement

This work was supported in part by Adobe and Baseline Funding of KAUST. Part of this work was done when the first author was an intern at Adobe Research. The authors thank the anonymous reviewers for helpful suggestions.

Supplementary material

419975_1_En_45_MOESM1_ESM.pdf (2.9 mb)
Supplementary material 1 (pdf 2960 KB)

References

  1. 1.
    Robust deblurring software. www.cse.cuhk.edu.hk/~leojia/deblurring.htm
  2. 2.
    Anwar, S., Phuoc Huynh, C., Porikli, F.: Class-specific image deblurring. In: ICCV (2015)Google Scholar
  3. 3.
    Chen, X., He, X., Yang, J., Wu, Q.: An effective document image deblurring algorithm. In: CVPR (2011)Google Scholar
  4. 4.
    Chen, Y., Yu, W., Pock, T.: On learning optimized reaction diffusion processes for effective image restoration. In: CVPR (2015)Google Scholar
  5. 5.
    Cho, H., Wang, J., Lee, S.: Text image deblurring using text-specific properties. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 524–537. Springer, Heidelberg (2012)Google Scholar
  6. 6.
    Cho, S., Lee, S.: Fast motion deblurring. ACM Trans. Graph. 28(5) (2009)Google Scholar
  7. 7.
    Geman, D., Yang, C.: Nonlinear image recovery with half-quadratic regularization. IEEE Trans. Image Process. 4(7), 932–946 (1995)CrossRefGoogle Scholar
  8. 8.
    Goldstein, A., Fattal, R.: Blur-Kernel estimation from spectral irregularities. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 622–635. Springer, Heidelberg (2012)Google Scholar
  9. 9.
    Hirsch, M., Sra, S., Scholkopf, B., Harmeling, S.: Efficient filter flow for space-variant multiframe blind deconvolution. In: CVPR (2010)Google Scholar
  10. 10.
    Hradiš, M., Kotera, J., Zemcík, P., Šroubek, F.: Convolutional neural networks for direct text deblurring. In: BMVC (2015)Google Scholar
  11. 11.
    Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: CVPR (2011)Google Scholar
  12. 12.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: CVPR (2009)Google Scholar
  13. 13.
    Michaeli, T., Irani, M.: Blind deblurring using internal patch recurrence. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part III. LNCS, vol. 8691, pp. 783–798. Springer, Heidelberg (2014)Google Scholar
  14. 14.
    Pan, J., Hu, Z., Su, Z., Yang, M.H.: Deblurring text images via. l0-regularized intensity and gradient prior. In: CVPR (2014)Google Scholar
  15. 15.
    Roth, S., Black, M.J.: Fields of experts: a framework for learning image priors. In: CVPR (2005)Google Scholar
  16. 16.
    Schelten, K., Nowozin, S., Jancsary, J., Rother, C., Roth, S.: Interleaved regression tree field cascades for blind image deconvolution. In: WACV (2015)Google Scholar
  17. 17.
    Schmidt, M.: minfunc: unconstrained differentiable multivariate optimization in matlab. http://www.cs.ubc.ca/~schmidtm/Software/minFunc.html
  18. 18.
    Schmidt, U., Roth, S.: Shrinkage fields for effective image restoration. In: CVPR (2014)Google Scholar
  19. 19.
    Schmidt, U., Rother, C., Nowozin, S., Jancsary, J., Roth, S.: Discriminative non-blind deblurring. In: CVPR (2013)Google Scholar
  20. 20.
    Schuler, C.J., Hirsch, M., Harmeling, S., Schölkopf, B.: Learning to deblur (2014). arXiv preprint arXiv:1406.7444
  21. 21.
    Sun, L., Cho, S., Wang, J., Hays, J.: Edge-based blur kernel estimation using patch priors. In: ICCP (2013)Google Scholar
  22. 22.
    Xiao, L., Gregson, J., Heide, F., Heidrich, W.: Stochastic blind motion deblurring. IEEE Trans. Image Process. 24(10), 3071–3085 (2015)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Xu, L., Jia, J.: Two-Phase Kernel estimation for robust motion deblurring. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 157–170. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  24. 24.
    Xu, L., Zheng, S., Jia, J.: Unnatural l0 sparse representation for natural image deblurring. In: CVPR (2013)Google Scholar
  25. 25.
    Yue, T., Cho, S., Wang, J., Dai, Q.: Hybrid image deblurring by fusing edge and power spectrum information. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 79–93. Springer, Heidelberg (2014)Google Scholar
  26. 26.
    Zuo, W., Ren, D., Gu, S., Lin, L., Zhang, L.: Discriminative learning of iteration-wise priors for blind deconvolution. In: CVPR (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Lei Xiao
    • 2
    • 1
  • Jue Wang
    • 3
  • Wolfgang Heidrich
    • 1
    • 2
  • Michael Hirsch
    • 4
  1. 1.KAUSTThuwalSaudi Arabia
  2. 2.University of British ColumbiaVancouverCanada
  3. 3.Adobe ResearchSeattleUSA
  4. 4.MPI for Intelligent SystemsTübingenGermany

Personalised recommendations