Adaptive Deblurring for Camera-Based Document Image Processing

  • Yibin Tian
  • Wei Ming
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5876)


With increasing resolution of cameras on mobile devices and their computing capacity, camera-based document processing becomes more attractive. However, there are several unique challenges, one of which is defocus. It is common that a camera-captured image is blurred by variable amount of location-dependent defocus. To improve image quality, we developed a novel method to adaptively deblur camera-based document images. In this method, sub-images of interest are first extracted from the captured image, and a point-spread function is derived for each sub-image by analyzing the gradient information along edges. Then the sub-image is deblurred by its local point-spread function. Preliminary experimental results indicate that the proposed adaptive deblurring method significantly improves focusing quality as evaluated by both human observers and objective focus measures compared with single-PSF deblurring.


Point Spread Function Document Image Optical Character Recognition Focus Measure Edge Response 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gye, L.: Picture This: the Impact of Mobile Camera Phones on Personal Photographic Practices. Journal of Media and Cultural Studies, 279–288 (2007)Google Scholar
  2. 2.
    Shen, H., Coughlan, J.: Grouping Using Factor Graphs: an Approach for Finding Text with a Camera Phone. In: Escolano, F., Vento, M. (eds.) GbRPR. LNCS, vol. 4538, pp. 394–403. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Yang, J., Gao, J., Zhang, Y., Waibel, A.: Towards Automatic Sign Translation. In: Proceedings of Human Language Technology, pp. 269–274 (2001)Google Scholar
  4. 4.
    Lee, C.M., Kankanhalli, A.: Automatic Extraction of Characters in Complex Scene Images. International Journal of Pattern Recognition and Artificial Intelligence, 67–82 (1995)Google Scholar
  5. 5.
    Newman, W., Dance, C., Taylor, A., Taylor, S., Taylor, M., Aldhous, T.: CamWorks: A Video-based Tool for Efficient Capture from Paper Source Documents. In: Proceedings of IEEE International Conference on Multimedia Computing and Systems, pp. 647–653 (1999)Google Scholar
  6. 6.
    Doermann, D., Liang, J., Li, H.: Progress in Camera-Based Document Image Analysis. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 606–616 (2003)Google Scholar
  7. 7.
    Tian, Y., Feng, H., Xu, Z., Huang, J.: Dynamic Focus Window Selection Strategy for Digital Cameras. In: Proceedings of SPIE, vol. 5678, pp. 219–229 (2005)Google Scholar
  8. 8.
    Tian, Y.: Dynamic Focus Window Selection Using a Statistical Color Model. In: Proceedings of SPIE, vol. 6069, pp. 98–106 (2006)Google Scholar
  9. 9.
    Smith, E.H.B.: PSF Estimation by Gradient Descent Fit to the ESF. In: Proceedings of SPIE, vol. 6059, pp. 129–137 (2006)Google Scholar
  10. 10.
    Tian, Y., Arnoldussen, M., Tuan, A., Logan, B., Wildsoet, C.F.: Evaluation of Retinal Image Degradation by Higher-order Aberrations and Light Scatter in Chick Eyes after PhotoRefractive Keratectomy (PRK). Journal of Modern Optics, 805–818 (2008)Google Scholar
  11. 11.
    Tian, Y., Shieh, K., Wildsoet, C.F.: Performance of Focus Measures in the Presence of Non-defocus Aberrations. Journal of the Optical Society of America A, 165–173 (2007)Google Scholar
  12. 12.
    Canny, J.: A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 679–698 (1986)Google Scholar
  13. 13.
    Young, S., Driggers, R.G., Teaney, B.P., Jacobs, E.L.: Adaptive Deblurring of Noisy Images. Applied Optics, 744–752 (2007)Google Scholar
  14. 14.
    Richardson, W.H.: Bayesian-based Iterative Method of Image Restoration. Journal of the Optical Society of America, 55–59 (1972)Google Scholar
  15. 15.
    Tian, Y.: Monte Carlo Evaluations of Ten Focus Measures. In: Proceedings of SPIE, Vol.6502, p. 65020C (2007)Google Scholar
  16. 16.
    Mubbarao, M., Choi, T., Nikzad, A.: Focusing Techniques. Optical Engineering, 2824–2836 (1993)Google Scholar
  17. 17.
    Fisher, F.: Digital Camera for Document Acquisition. In: Proceedings of Symposium on Document Image Understanding Technology, pp. 75–83 (2001)Google Scholar
  18. 18.
    Kuo, S., Ranganath, M.V.: Real Time Image Enhancement for both Text and Color Photo Images. In: Proceedings of International Conference on Image Processing, pp. 159–162 (1995)Google Scholar
  19. 19.
    Clark, P., Mirmehdi, M.: Recognising Text in Real Scenes. International Journal on Document Analysis and Recognition, 243–257 (2002)Google Scholar
  20. 20.
    Yu, B., Jain, A.K.: A Robust and Fast Skew Detection Algorithm for Generic Documents. Pattern Recognition, 1599–1629 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Yibin Tian
    • 1
  • Wei Ming
    • 1
  1. 1.Konica Minolta Systems LabFoster CityUSA

Personalised recommendations