Bleed-Through Removal from Degraded Documents Using a Color Decorrelation Method

  • Anna Tonazzini
  • Emanuele Salerno
  • Matteo Mochi
  • Luigi Bedini
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3163)

Abstract

A color decorrelation strategy to improve the human or automatic readability of degraded documents is presented. The particular degradation that is considered here is bleed-through, that is, a pattern that interferes with the text to be read due to seeping of ink from the reverse side of the document. A simplified linear model for this degradation is introduced to permit the application of very fast decorrelation techniques to the RGB components of the color data images, and to compare this strategy to the independent component analysis approach. Some examples from an extensive experimentation with real ancient documents are described, and the possibility to further improve the restoration performance by using hyperspectral/multispectral data is envisaged.

Keywords

Main Text Document Image Thresholding Technique Optical Character Recognition System Degraded Document 
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.

References

  1. 1.
    van Assche, S., Denecker, K.N., Philips, W.R., Lemahieu, I.: Proc. SPIE, vol. 3653, pp. 1376–1383 (1998)Google Scholar
  2. 2.
    Chew, L.T., Cao, R., Peiyi, S.: IEEE Trans. Pattern Analysis and Machine Intelligence 24, 1399–1404 (2002)CrossRefGoogle Scholar
  3. 3.
    Cichocki, A., Amari, S.-I.: Adaptive Blind Signal and Image Processing. Wiley, New York (2002)CrossRefGoogle Scholar
  4. 4.
    Dubois, E., Pathak, A.: Proc. IS&T Image Processing, Image Quality. In: Image Capture Systems Conf., Montreal, Canada, pp. 177–180 (2001)Google Scholar
  5. 5.
    Easton, R.L.: Simulating Digital Image Processing used for the Archimedes Palimpsest (2001), http://www.cis.rit.edu/people/faculty/easton/k-12/index.htm
  6. 6.
    Hyvärinen, A., Oja, E.: Neural Networks 13, 411–430 (2000) Google Scholar
  7. 7.
    Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley, New York (2001)CrossRefGoogle Scholar
  8. 8.
    Liang, Y., Simoncelli, E.P., Lei, Z.: Computer Vision and Pattern Recognition (CVPR 2000), Hilton Head, South Carolina, pp. 1606 (2000)Google Scholar
  9. 9.
    Nishida, H., Suzuki, T.: Proc. 16th Conf. Pattern Recognition, Quebec City, Canada (2002)Google Scholar
  10. 10.
    Ohta, Y., Kanade, T., Sakai, T.: Computer Graphics, Vision, and Image Processing 13, 222–241 (1980)CrossRefGoogle Scholar
  11. 11.
    Sharma, G.: IEEE Trans. Image Processing 10, 736–754 (2001)CrossRefGoogle Scholar
  12. 12.
    Solihin, Y., Leedham, C.G.: IEEE Trans. PAMI 21, 761–768 (1999)Google Scholar
  13. 13.
    Tonazzini, A., Bedini, L., Salerno, E.: Int. J. Document Analysis and Recognition (2004) (in press)Google Scholar
  14. 14.
    Vertan, C., Boujemaa, N.: Proc. Int. Conf. on Pattern Recognition ICPR 2000, Barcelona, Spain, pp. 3584–3587 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Anna Tonazzini
    • 1
  • Emanuele Salerno
    • 1
  • Matteo Mochi
    • 1
  • Luigi Bedini
    • 1
  1. 1.Istituto di Scienza e Tecnologie dell’InformazioneCNRPisaItaly

Personalised recommendations