Advertisement

Configurable Text Stamp Identification Tool with Application of Fuzzy Logic

  • J. He
  • Andy C. Downton
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3163)

Abstract

This paper presents our work on locating and removing unwanted text stamps within archive documents which are being prepared for OCR. Text stamps mainly comprise one or several text lines with a fixed shape, font size and colour, and may appear anywhere on the document with variable orientation and overlap of other text fields. We apply a configurable user interface to register features of a sample stamp (such as corners, font-size and print colour) as a template using fuzzy rules, and then analyse each document image to find matching stamps using fuzzy functions as a classification mechanism. The configurable interface allows the user to decide which and how many features should be used to describe the target stamp. Evaluation was very encouraging. We tested 1,241 specimen index cards from a biological archive card index, and achieved 92-95% correct detection rate and 85-95% complete removal rate.

References

  1. 1.
    Lee, S.W., Kim, J.H.: Unconstrained seal imprint verification using attributed stroke graph matching. Pattern Recognition 22, 653–664 (1989)CrossRefGoogle Scholar
  2. 2.
    Ueda, K.: Automatic seal imprint verification system with imprint quality assessment function and its performance evaluation. IEICE Trans.Inf. and Syst. E-77D, 885–894 (1994)Google Scholar
  3. 3.
    Haruki, R., Horiuchi, T., Yamada, H., Yamamoto, K.: Automatic seal verification using threedimensional reference seals. In: Proc. ICPR 1996 13th Int.Conf. on Pattern Recognition, vol. 1, pp. 199–203 (1996)Google Scholar
  4. 4.
    Ueda, K., Mutoh, T., Matsuo, K.: Automatic verification system for seal imprints on japanese bankchecks. In: Proc. ICPR 1998 14th Int.Conf. on Pattern Recognition, vol. 1, pp. 629–632 (1998)Google Scholar
  5. 5.
    Plamondon, R., Lorette, G.: Automatic signature verification and writer recognition -the state of the art-. Pattern Recognition 22, 107–131 (1989)CrossRefGoogle Scholar
  6. 6.
    Wirtz, B.: Stroke-based time warping for signature verification. In: Proc. ICDAR 1995 the Third Int.Conf.on Document Analysis and Recognition, vol. 1, pp. 179–182 (1995)Google Scholar
  7. 7.
    Schmidt, C., Kraiss, K.F.: Establishment of personalized templates for automatic signature verification. In: Proc. ICDAR 1997 4th Int.Conf.on Document Analysis and Recognition, vol. 1, pp. 263–267 (1997)Google Scholar
  8. 8.
    Hanmandlu, M., Murali Mohan, K.R., Chakraborty, S., Garg, G.: Fuzzy modeling based signature verification system. In: Proc. ICDAR 2001 6th Int.Conf.on Document Analysis and Recognition, pp. 110–114 (2001)Google Scholar
  9. 9.
    Doerman, D.s., Rivlin, E., Weiss, I.: Logo recognition using geometric invariants. In: Proc. ICDAR 1993 2nd Int.Conf.on Document Analysis and Recognition, pp. 894–897 (1993)Google Scholar
  10. 10.
    Suda, P., Bridoux, C., Kammerer, B., Maderlechner, G.: Logo and word matching using a general approach to signal registration. In: Proc. ICDAR 1997 4th Int.Conf.on Document Analysis and Recognition, vol. 1, pp. 61–65 (1997)Google Scholar
  11. 11.
    Cheng, T., Khan, J., Liu, H., Yun, D.Y.Y.: A symbol recogonition system. In: Proc. ICDAR 1993 2nd Int.Conf.on Document Analysis and Recognition, pp. 918–921 (1993)Google Scholar
  12. 12.
    Zadeh, L.A., Kacprayk, J.: Fuzzy Logic for the Management of Uncertainty. John-Wiley, New York (1992)Google Scholar
  13. 13.
    Dubois, D., Prade, H., Yager, R.Y.: Fuzzy Sets for Intelligent Systems. Morgan Kaufmann Publishers, San Mateo (1993)Google Scholar
  14. 14.
    Downton, A.C., Tams, A.C., Wells, G.J., Holmes, A.C., Lucas, S.M.: Constructing web-based legacy index card archives-architectural design issues and initial data acquisition. In: ICDAR 2001 6th Int.Conf.on Document Analysis and Recognition, pp. 854–858 (2001)Google Scholar
  15. 15.
  16. 16.
    He, J., Downton, A.C.: Colour map detection for archive documents. In: Marinai, S., Dengel, A.R. (eds.) DAS 2004. LNCS, vol. 3163, pp. 241–251. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  17. 17.
    Hinds, S.C., Fisher, J.L., D’Amato, D.P.: A document skew detection method using run-length encoding and the hough transform. In: Proc. 10th Int’l Conf. Pattern Recognition (ICPR), pp. 464–468. IEEE CS Press, Los Alamitos (1990)CrossRefGoogle Scholar
  18. 18.
    Illingworth, J., Kittler, J.: A survey of the hough transform. Computer Graphics and Image Processing 44, 87–116 (1988)CrossRefGoogle Scholar
  19. 19.
    He, J., Downton, A.C.: User-assisted archive document image analysis for digital library construction. In: Proc. ICDAR 2003 7th Int.Conf.on Document Analysis and Recognition, vol. 1, pp. 498–502 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • J. He
    • 1
  • Andy C. Downton
    • 1
  1. 1.Department of Electronic Systems EngineeringUniversity of EssexUK

Personalised recommendations