Book Scanner Dewarping with Weak 3d Measurements and a Simplified Surface Model

  • Erik Lilienblum
  • Bernd Michaelis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4992)


For book scanner technologies projective distortions are the main problem. In general, the use of 3d measurements of a warped surface is the best way to remove the projective distortions. But if the quality of the 3d measurements is very low, it is difficult to get satisfying dewarping results. In our paper we present a new technique handling this problem by introducing a simplified surface model. We use this model as a basis to compute a linear approximation parallel to the geometrical position of the book crease. The resulting method leads to a robust and fast computation. It provides us with a reliable dewarping output even for weak measurements given by a light sectioning method of top view scanners.


  1. 1.
    Wada, T., Ukida, H., Matsuyama, T.: Shape from shading with interreflections under a proximal light source: Distorsion-free copying of an unfolded book. International Journal of Computer Vision 24(2), 125–135 (1997)CrossRefGoogle Scholar
  2. 2.
    Tan, C.L., Zhang, L., Zhang, Z., Xia, T.: Restoring warped document images through 3d shape modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(2), 195–208 (2006)CrossRefGoogle Scholar
  3. 3.
    Wu, C., Agam, G.: Document image de-warping for text/graphics recognition. In: Proc. of Joint IAPR and SPR, pp. 348–357 (2002)Google Scholar
  4. 4.
    Zhang, Z., Tan, C.L.: Correcting document image warping based on regression of curved text lines. In: Proc. of 7th International Conference on Document Analysis and Recognition, vol. 1, pp. 589–595 (2003)Google Scholar
  5. 5.
    Ulges, A., Lampert, C.H., Breuel, T.M.: Document image dewarping using robust estimation of curled text lines. In: Proc. of 8th International Conference on Document Analysis and Recognition, vol. 2, pp. 1001–1005. IEEE Computer Society, Washington, DC (2005)Google Scholar
  6. 6.
    Rebmann, R., Michaelis, B., Krell, G., Seiffert, U., Püschel, F.: Improving image processing systems by artificial neural networks. In: Dengel, A., Junker, M., Weisbecker, A. (eds.) Reading and Learning. LNCS, vol. 2956, pp. 37–64. Springer, Heidelberg (2004)Google Scholar
  7. 7.
    Frei, B.: Method and device for the correction of a scanned image. Patent US020050053304A1 (2002)Google Scholar
  8. 8.
    Donescu, A., Bouju, A., Quillet, V.: Former books digital processing: image warping. In: Proc. Workshop on Document Image Analysis, pp. 5–9 (1997)Google Scholar
  9. 9.
    Yamashita, A., Kawarago, A., Kaneko, T., Miura, K.: Shape reconstruction and image restoration for non-flat surfaces of documents with a stereo vision system. In: Proc. of 17th International Conference on Pattern Recognition, vol. 1, pp. 486–489. IEEE Computer Society, Washington, DC (2004)CrossRefGoogle Scholar
  10. 10.
    Chu, K.B., Zhang, L., Zhang, Y., Tan, C.L.: A fast and stable approach for restoration of warped document images. In: Proceedings of the Eighth International Conference on Document Analysis and Recognition, pp. 384–388. IEEE Computer Society, Washington, DC (2005)Google Scholar
  11. 11.
    Klette, R., Koschan, A., Schlüns, K.: Copmuter Vision: Three-Dimensional Data from Images. Springer, Heidelberg (1998)Google Scholar
  12. 12.
    Brown, M., Seales, W.: Image restoration of arbitrarily warped documents. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(10), 1295–1306 (2004)CrossRefGoogle Scholar
  13. 13.
    Liang, J., DeMenthon, D., Doermann, D.: Flattening curved documents in images. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 338–345 (2005)Google Scholar
  14. 14.
    Liang, J., DeMenthon, D., Doermann, D.: Geometric rectification of camera-captured document images. IEEE Transactions on Pattern Analysis and Machine Intelligence (Preprint, 2007)Google Scholar
  15. 15.
    Lilienblum, E., Michaelis, B.: Digitalisation of warped documents supported by 3d-surface reconstruction. In: The 5th International Conference on Computer Vision Systems Conference Paper (2007), doi:10.2390/biecoll-icvs2007-69Google Scholar
  16. 16.
    Lilienblum, E., Michaelis, B., Schnitzlein, M.: Verfahren zum Entzerren einer mittels einer Scanneinrichtung eingescannten zweidimensionalen Abbildung einer nicht ebenflächigen Vorlage. German patent, No. 102006032533 (2006)Google Scholar
  17. 17.
    Shirai, Y.: Recognition of polyhedrons with a range finder. Pattern Recognition 4, 243–250 (1972)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Erik Lilienblum
    • 1
  • Bernd Michaelis
    • 1
  1. 1.Institute for Electronics, Signal Processing and CommunicationsOtto-von-Guericke University MagdeburgMagdeburgGermany

Personalised recommendations