Correcting Book Binding Distortion in Scanned Documents

  • Rafael Dueire Lins
  • Daniel M. Oliveira
  • Gabriel Torreão
  • Jian Fan
  • Marcelo Thielo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6112)


This paper presents an exponential model to correct the distortion that appears when bound books are digitalized using flatbed scanners. The proposed algorithm infers the height of the book spine for every column in the image and fits an exponential curve. The de-warping is done regarding the scanner acquisition model and shape binding. This new de-warping method is effective, fast, accurate and easy to implement.


Shape-from-shading image processing book binding de-warping 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Tan, C.L., Zhang, L., Zhang, Z., Xia, T.: Restoring Warped Document Images through 3D Shape Modeling. IEEE Trans. Pattern Analysis and Machine Intelligence 28(2), 195–208 (2006)CrossRefGoogle Scholar
  2. 2.
    Ukida, H., Konishi, K.: 3D Shape Reconstruction Using Three Light Sources in Image Scanner. IEICE Trans. on Inf. & Syst. E84-D(12), 1713–1721 (2001)Google Scholar
  3. 3.
    Ukida, H., Tanimoto, Y., Sano, T., Yamamoto, H.: 3D Shape Reconstructions Using Image Scanner under Various Number of Illuminations. In: IEEE IST ’07, Krakow, Poland, May 5, pp. 1–6 (2007)Google Scholar
  4. 4.
    Zhang, R., Tsai, P.S., Cryer, J.E., Shah, M.: Shape from shading: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(8), 690–706 (1999)CrossRefGoogle Scholar
  5. 5.
    Durou, J.-D., Falcone, M., Sagona, M.: Numerical Methods for Shape-from-shading: A New Survey with Benchmarks. Computer Vision and Image Understanding (2007)Google Scholar
  6. 6.
    Szeliski, R.: Computer Vision: Algorithms and Applications (to be published),
  7. 7.
    Oliveira, D.M., Lins, R.D.: A New Method for Shading Removal and Binarization of Documents Acquired with Portable Digital Cameras. In: CBDAR 2009, pp. 3–10. IAPR Press, Barcelona (2009)Google Scholar
  8. 8.
    Bukhari, S.S., Shafait, F., Breuel, T.M.: Dewarping of Document Images using Coupled-Snakes. In: CBDAR 2009, pp. 17–24. IAPR Press, Barcelona (2009)Google Scholar
  9. 9.
    Stamatopoulos, N., Gatos, B., Pratikakis, I., Perantonis, S.J.: A two-step dewarping of camera document images. In: Proceedings 8th IAPR Workshop on Document Analysis Systems, pp. 209–216 (2008)Google Scholar
  10. 10.
    Pintus, R., Malzbender, T., Wang, O., Bergman, R., Nachlieli, H., Ruckenstein, G.: Photo Repair and 3D Structure from Flatbed Scanners. Computer Vision Theory and Applications, 40–50 (2009)Google Scholar
  11. 11.
    Schubert, R.: Using a Flatbed Scanner as a Stereoscopic Near-Field Camera. IEEE Computer Graphics and Applications, 38–45 (2000)Google Scholar
  12. 12.
    Fan, J.: Enhancement of Camera-captured Document Images with Watershed Segmentation. In: CBDAR’07, September 2007, pp. 87–93 (2007)Google Scholar
  13. 13.
    Fan, J.: Robust Color Image Enhancement of Digitized Books. In: Proceedings of International Conference on Document Analysis and Recognition, pp. 561–565. IEEE Press, Los Alamitos (2009)CrossRefGoogle Scholar
  14. 14.
    Wolfram Resarch. Least Squares Fitting–Exponential, (accessed October 14, 2009)
  15. 15.
    Lins, R.D., Oliveira, D.M., Torreão, G., Fan, J., Thielo, M.: A De-Warping Algorithm to Compensate Volume Binding Distortion in Scanned Documents. In: ACM SAC 2010 (March 2010)Google Scholar
  16. 16.
    Silva, G.F.P., Lins, R.D.: PhotoDoc: A Toolbox for Processing Document Images Acquired Using Portable Digital Cameras. In: CBDAR 2007, Curitiba, pp. 107–115 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Rafael Dueire Lins
    • 1
  • Daniel M. Oliveira
    • 1
  • Gabriel Torreão
    • 1
  • Jian Fan
    • 2
  • Marcelo Thielo
    • 3
  1. 1.Departamento de Eletrônica e Sistemas.Universidade Federal de PernambucoRecifeBrasil
  2. 2.Hewlett-Packard LabsPalo AltoUSA
  3. 3.Hewlett-Packard LabsPorto AlegreBrazil

Personalised recommendations