Advertisement

Structure Analysis of Low Resolution Fax Cover Pages

  • Young-Kyu Lim
  • Hee-Joong Kang
  • Chang Ahn
  • Seong-Whan Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1655)

Abstract

The increase in the use of faxed documents calls for the need to handle them automatically and intelligently for efficient storage, retrieval and interpretation. A lot of work has been accomplished for page segmentation in high resolution document images. But conventional methods for page segmentation are not suitable for faxed document processing. The well-known difficulties in faxed document processing are concerned with low resolution images and non-standardized formats. In this paper, we propose an effective structure analysis method for low resolution fax cover pages, based on region segmentation and keyword recognition. The main advantages of the proposed method are its capability of accommodating various types of fax cover pages and its fast processing speed. We divide fax cover pages into three regions-header, sender/recipient information and message-to easily identify the recipient’s field. The recipient’s name is then extracted through the recognition of keyword. The proposed method was tested on 164 fax cover pages. The experimental results show that the proposed method works well on the various types of fax cover pages.

Keywords

Character Recognition Document Image Region Separator Black Pixel Region Segmentation 
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.

Reference

  1. 1.
    S.-W. Lee, Character Recognition: Theory and Practice, Hongneung Publisher, Seoul, 1993. (in Korean)Google Scholar
  2. 2.
    J. Li and S. N. Srihari: Location of Name and Address on Fax Cover Pages. Proc. of 3rd Int. Conf. on Document Analysis and Recognition, Montreal, Canada, August 1995, pp. 756–759.Google Scholar
  3. 3.
    Y. Y. Tang, S.-W. Lee and C. Y. Suen: Automatic Document Processing: A Survey. Pattern Recognition, Vol. 29, No. 12, 1996, pp. 1931–1952.CrossRefGoogle Scholar
  4. 4.
    T. Akiyama: Addressee Recognition for Automated FAX Mail Distribution. Proc. of SPIE Conference on Document Recognition(III), Vol. 2660, San Jose, California, January 1996, pp. 677–680.Google Scholar
  5. 5.
    G. Ricker and A. Winkler: Recognition of Faxed Documents. Proc. of SPIE Conference on Document Recognition, Vol. 2181, San Jose, California, February 1994, pp. 371–377.Google Scholar
  6. 6.
    J. Ha, R. M. Haralick and I. T. Philips: Document Page Decomposition by the Bounding-Box Projection Technique. Proc. of 3rd Int. Conf. on Document Analysis and Recognition, Montreal, Canada, August 1995, pp. 1119–1122.Google Scholar
  7. 7.
    M. Y. Yoon, S.-W. Lee and J. S. Kim: Faxed Image Restoration Using Kalman Filtering. Proc. 3rd Int. Conf. on Document Analysis and Recognition, Montreal, Canada, August 1995, pp. 677–680.Google Scholar
  8. 8.
    J. C Handley and E. R. Dougherty: Optimal Nonlinear Fax Restoration. Proc. of SPIE Conference on Document Recognition, Vol. 2181, San Jose, California, February 1994, pp. 232–235.Google Scholar
  9. 9.
    J. Liang and R. M. Haralick: Document Image Restoration Using Binary Morphological Filters. Proc. of SPIE Conference on Document Recognition(III), Vol. 2660, San Jose, California, January 1996, pp. 274–285.Google Scholar
  10. 10.
    B. Yu and A. Jain: A Robust and Fast Skew Detection Algorithm for Generic Documents. Pattern Recognition, Vol.29, 1996, pp. 1599–1629.CrossRefGoogle Scholar
  11. 11.
    D. S. Kim and S.-W. Lee: An Efficient Skew Correction and Character Segmentation Method for Constructing Digital Libraries from Mixed Documents. Proc. of The 23rd KISS Fall Conference, Vol. 23, Taegu, Korea, April 1996, pp. 293-206. (in Korean)Google Scholar
  12. 12.
    K. Fan and L. Wang: Classification of Document Block Using Density Features and Connectivity Histogram. Pattern Recognition Letters, Vol. 16, 1995, pp. 955–962.Google Scholar
  13. 13.
    S. W. Lam, L. Javanbakht and S. N. Srihari,: Anatomy of a From Reader. Proc. of the 2th Int. Conf. on Document Analysis and Recognition, Tsukuba Science City, Japan, October 1993, pp. 506–509.CrossRefGoogle Scholar
  14. 14.
    Y. Katsuyama and S. Naoi,: Fast Title Extraction Method for Business Documents. Proc. of SPIE Conference on Document Recognition(IV), Vol 3027, San Jose, California. February 1997, pp. 192–201.Google Scholar
  15. 15.
    A. J. Elms, S. Procter and J. Illingworth: The Advantage of Using HMM-based Approach for Faxed Word Recognition. International Journal on Document Analysis and Recognition, Vol. 1, No. 1, 1998, pp. 18–36.CrossRefGoogle Scholar
  16. 16.
    D. S. Kim and S.-W. Lee: Performance Comparison of Two Methods for Low Resolution Printed Hangul Recognition. Proc. of The 23rd KISS Fall Conference, Vol. 23, Seoul, Korea, October 1996, pp. 587–590. (in Korean)Google Scholar
  17. 17.
    S.-W. Lee and E. S. Kim: Efficient Postprocessing Algorithms for Error Correction in Handwritten Hangul Address and Human Name Recognition. Pattern Recognition, Vol. 27, No. 12, 1994, pp. 1–10.zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Young-Kyu Lim
    • 1
  • Hee-Joong Kang
    • 1
  • Chang Ahn
    • 1
  • Seong-Whan Lee
    • 1
  1. 1.Center for Artificial Vision ResearchKorea UniversitySeoulKorea

Personalised recommendations