Ridges Based Curled Textline Region Detection from Grayscale Camera-Captured Document Images

  • Syed Saqib Bukhari
  • Faisal Shafait
  • Thomas M. Breuel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5702)

Abstract

As compared to scanners, cameras offer fast, flexible and non-contact document imaging, but with distortions like uneven shading and warped shape. Therefore, camera-captured document images need preprocessing steps like binarization and textline detection for dewarping so that traditional document image processing steps can be applied on them. Previous approaches of binarization and curled textline detection are sensitive to distortions and loose some crucial image information during each step, which badly affects dewarping and further processing. Here we introduce a novel algorithm for curled textline region detection directly from a grayscale camera-captured document image, in which matched filter bank approach is used for enhancing textline structure and then ridges detection is applied for finding central line of curled textlines. The resulting ridges can be potentially used for binarization, dewarping or designing new techniques for camera-captured document image processing. Our approach is robust against bad shading and high degrees of curl. We have achieved around 91% detection accuracy on the dataset of CBDAR 2007 document image dewarping contest.

Keywords

Curled Textline Finding Camera-Captured Document Images Grayscale Document Images Ridges Anisotropic Gaussian Smoothing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Shafait, F., Keysers, D., Breuel, T.M.: Efficient implementation of local adaptive thresholding techniques using integral images. In: Proc. Document Recognition and Retrieval XV, San Jose, CA, USA, vol. 6815, p. 81510 (2008)Google Scholar
  2. 2.
    Zhang, Z., Tan, C.L.: Correcting document image warping based on regression of curved text lines. In: Proc. 7th Int. Conf. on Document Analysis and Recognition, Edinburgh, Scotland, pp. 589–593 (2003)Google Scholar
  3. 3.
    Lu, S.J., Tan, C.L.: The restoration of camera documents through image segmentation. In: Proc. 7th IAPR workshop on Document Analysis Systems, Nelson, New Zealand, pp. 484–495 (2006)Google Scholar
  4. 4.
    Fu, B., Wu, M., Li, R., Li, W., Xu, Z.: A model-based book dewarping method using text line detection. In: Proc. 2nd Int. Workshop on Camera Based Document Analysis and Recognition, Curitiba, Barazil, pp. 63–70 (2007)Google Scholar
  5. 5.
    Gatos, B., Pratikakis, I., Ntirogiannis, K.: Segmentation based recovery of arbitrarily warped document images. In: Proc. 9th Int. Conf. on Document Analysis and Recognition, Curitiba, Barazil, pp. 989–993 (2007)Google Scholar
  6. 6.
    Stamatopoulos, N., Gatos, B., Pratikakis, I., Perantonis, S.J.: A two-step dewarping of camera document images. In: Proc. 8th IAPR Workshop on Document Analysis Systems, Nara, Japan, pp. 209–216 (2008)Google Scholar
  7. 7.
    Ulges, A., Lampert, C.H., Breuel, T.M.: Document image dewarping using robust estimation of curled text lines. In: Proc. 8th Int. Conf. on Document Analysis and Recognition, Seoul, Korea, pp. 1001–1005 (2005)Google Scholar
  8. 8.
    Bukhari, S.S., Shafait, F., Breuel, T.M.: Segmentation of curled textlines using active contours. In: Proc. 8th IAPR Workshop on Document Analysis Systems, Nara, Japan, pp. 270–277 (2008)Google Scholar
  9. 9.
    Bukhari, S.S., Shafait, F., Breuel, T.M.: Coupled snakelet model for curled textline segmentation of camera-captured document images. In: Proc. 10th Int. Conf. on Document Analysis and Recognition, Barcelona, Spain (2009)Google Scholar
  10. 10.
    Bukhari, S.S., Shafait, F., Breuel, T.M.: Script-independent handwritten textlines segmentation using active contours. In: Proc. 10th Int. Conf. on Document Analysis and Recognition, Barcelona, Spain (2009)Google Scholar
  11. 11.
    Horn, B.K.P.: Shape from shading: A method for obtaining the shape of a smooth opaque object from one view. PhD Thesis, MIT (1970)Google Scholar
  12. 12.
    Riley, M.D.: Time-frequency representation for speech signals. PhD Thesis, MIT (1987)Google Scholar
  13. 13.
    Li, Y., Zheng, Y., Doermann, D., Jaeger, S.: Script-independent text line segmentation in freestyle handwritten documents. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(8), 1313–1329 (2008)CrossRefGoogle Scholar
  14. 14.
    Du, X., Pan, W., Bui, T.D.: Text line segmentation in handwritten documents using Mumford-Shah model. In: Proc. Int. Conf. on Frontiers in Handwriting Recognition, Montreal, Canada, pp. 1–6 (2008)Google Scholar
  15. 15.
    Shafait, F., Breuel, T.M.: Document image dewarping contest. In: Proc. 2nd Int. Workshop on Camera Based Document Analysis and Recognition, Curitiba, Brazil, pp. 181–188 (2007)Google Scholar
  16. 16.
    Shafait, F., Keysers, D., Breuel, T.M.: Performance evaluation and benchmarking of six page segmentation algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(6), 941–954 (2008)CrossRefGoogle Scholar
  17. 17.
    Gatos, B., Antonacopoulos, A., Stamatopoulos, N.: ICDAR 2007 handwriting segmenentation contest. In: Proc. 9th Intelligence Conf. on Document Analysis and Recognition, Curitiba, Brazil, pp. 1284–1288 (2007)Google Scholar
  18. 18.
    Shafait, F., Keysers, D., Breuel, T.M.: Pixel-accurate representation and evaluation of page segmentation in document images. In: Proc. Int. Conf. on Pattern Recognition, Hong Kong, China, August 2006, pp. 872–875 (2006)Google Scholar
  19. 19.
    Breuel, T.M.: Representations and metrics for off-line handwriting segmentation. In: Proc. 8th Int. Workshop on Frontiers in Handwriting Recognition, Ontario, Canada, pp. 428–433 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Syed Saqib Bukhari
    • 1
  • Faisal Shafait
    • 2
  • Thomas M. Breuel
    • 1
    • 2
  1. 1.Technical University of KaiserslauternGermany
  2. 2.German Research Center for Artificial Intelligence (DFKI)KaiserslauternGermany

Personalised recommendations