Text Image Deblurring Using Text-Specific Properties

  • Hojin Cho
  • Jue Wang
  • Seungyong Lee
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7576)


State-of-the-art blind image deconvolution approaches have difficulties when dealing with text images, since they rely on natural image statistics which do not respect the special properties of text images. On the other hand, previous document image restoring systems and the recently proposed black-and-white document image deblurring method [1] are limited, and cannot handle large motion blurs and complex background. We propose a novel text image deblurring method which takes into account the specific properties of text images. Our method extends the commonly used optimization framework for image deblurring to allow domain-specific properties to be incorporated in the optimization process. Experimental results show that our method can generate higher quality deblurring results on text images than previous approaches.


Text Image Latent Image Document Image Kernel Estimation Text Region 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Chen, X., He, X., Yang, J., Wu, Q.: An effective document image deblurring algorithm. In: Proc. CVPR 2011, pp. 369–376 (2011)Google Scholar
  2. 2.
    Fergus, R., Singh, B., Hertzmann, A., Roweis, S.T., Freeman, W.T.: Removing camera shake from a single photograph. ACM Trans. Graphics 25, 787–794 (2006)CrossRefGoogle Scholar
  3. 3.
    Levin, A.: Blind motion deblurring using image statistics. In: Proc. Advances in Neural Information Processing Systems, pp. 841–848 (2006)Google Scholar
  4. 4.
    Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Trans. Graphics 27, 73:1–73:10 (2008)Google Scholar
  5. 5.
    Cho, S., Lee, S.: Fast motion deblurring. ACM Trans. Graphics 28, 145:1–145:8 (2009)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.: Understanding and evaluating blind deconvolution algorithms. In: Proc. CVPR 2009, pp. 1964–1971 (2009)Google Scholar
  7. 7.
    Levin, A., Weiss, Y., Freeman, B., Durand, F.: Efficient approximations to the marginal likelihood in blind deconvolution. In: Proc. CVPR 2011 (2011)Google Scholar
  8. 8.
    Banerjee, J., Namboodiri, A., Jawahar, C.: Contextual restoration of severely degraded document images. In: Proc. CVPR 2009, pp. 517–524 (2009)Google Scholar
  9. 9.
    Li, T.H., Lii, K.S.: A joint estimation approach for two-tone image deblurring by blind deconvolution. IEEE Trans. Image Processing 11, 847–858 (2002)CrossRefGoogle Scholar
  10. 10.
    Donaldson, K., Myers, G.: Bayesian super-resolution of text in video with a text-specific bimodal prior. In: Proc. CVPR 2005, vol. 1, pp. 1188–1195 (2005)Google Scholar
  11. 11.
    Lam, E.: Blind bi-level image restoration with iterated quadratic programming. IEEE Trans. Circuits and Systems II: Express Briefs 54, 52–56 (2007)CrossRefGoogle Scholar
  12. 12.
    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
  13. 13.
    Roth, S., Black, M.J.: Fields of experts: A framework for learning image priors. In: Proc. CVPR 2005, pp. 860–867 (2005)Google Scholar
  14. 14.
    Weiss, Y., Freeman, W.T.: What makes a good model of natural images? In: Proc. CVPR 2007, pp. 1–8 (2007)Google Scholar
  15. 15.
    Joshi, N., Szeliski, R., Kreigman, D.: PSF estimation using sharp edge prediction. In: Proc. CVPR 2008, pp. 1–8 (2008)Google Scholar
  16. 16.
    Kasar, T., Kumar, J., Ramakrishnan, A.G.: Font and background color independent text binarization. In: Proc. Intl. Workshop on Camera Based Document Analysis and Recognition (ICDAR), pp. 3–9 (2007)Google Scholar
  17. 17.
    Levin, A., Fergus, R., Durand, F., Freeman, W.T.: Image and depth from a conventional camera with a coded aperture. ACM Trans. Graphics 26, 70:1–70:9 (2007)CrossRefGoogle Scholar
  18. 18.
    Geman, D., Yang, C.: Nonlinear image recovery with half-quadratic regularization. IEEE Trans. Image Processing 4, 932–946 (1995)CrossRefGoogle Scholar
  19. 19.
    Wang, Y., Yang, J., Yin, W., Zhang, Y.: A new alternating minimization algorithm for total variation image reconstruction. SIAM J. Img. Sci. 1, 248–272 (2008)MathSciNetzbMATHCrossRefGoogle Scholar
  20. 20.
    Xu, L., Lu, C., Xu, Y., Jia, J.: Image smoothing via L0 gradient minimization. ACM Trans. Graphics (2011)Google Scholar
  21. 21.
    Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: Proc. CVPR 2010, pp. 2963–2970 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Hojin Cho
    • 1
  • Jue Wang
    • 2
  • Seungyong Lee
    • 1
  1. 1.Pohang University of Science and Technology (POSTECH)Korea
  2. 2.AdobeUSA

Personalised recommendations