A Study on the Document Zone Content Classification Problem

  • Yalin Wang
  • Ihsin T. Phillips
  • Robert M. Haralick
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2423)

Abstract

A document can be divided into zones on the basis of its content. For example, a zone can be either text or non-text. Given the segmented document zones, correctly determining the zone content type is very important for the subsequent processes within any document image understanding system. This paper describes an algorithm for the determination of zone type of a given zone within an input document image. In our zone classification algorithm, zones are represented as feature vectors. Each feature vector consists of a set of 25 measurements of pre-defined properties. A probabilistic model, decision tree, is used to classify each zone on the basis of its feature vector. Two methods are used to optimize the decision tree classifier to eliminate the data over-fitting problem. To enrich our probabilistic model, we incorporate context constraints for certain zones within their neighboring zones.We also model zone class context constraints as a Hidden Markov Model and usedViterbi algorithm to obtain optimal classification results. The training, pruning and testing data set for the algorithm include 1, 600 images drawn from theUWCDROM-III document image database. With a total of 24, 177 zones within the data set, the cross-validation methodwas used in the performance evaluation of the classifier. The classifier is able to classify each given scientific and technical document zone into one of the nine classes, 2 text classes (of font size 418pt and font size 1932 pt), math, table, halftone, map/drawing, ruling, logo, and others. A zone content classification performance evaluation protocol is proposed. Using this protocol, our algorithm accuracy is 98.45% with a mean false alarm rate of 0.50%.

Keywords

Feature Vector Hide Markov Model False Alarm Rate Document Image Optical Character Recognition 
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.
    R. Haralick and L. Shapiro. Computer and Robot Vision, volume 1. AddisonWesley, 1997.Google Scholar
  2. 2.
    L. R. Rabiner. A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 77:257–285, February 1989.Google Scholar
  3. 3.
    Y. Wang, R. Haralick, and I. T. Phillips. Improvement of zone content classification by using background analysis. In Fourth IAPR International Workshop on Document Analysis Systems. (DAS2000), Rio de Janeiro, Brazil, December 2000.Google Scholar
  4. 4.
    Y. Wang, R. Haralick, and I. T. Phillips. Zone content classification and its performance evaluation. In Sixth International Conference on Document Analysis and Recognition(ICDAR01), pages 540–544, Seattle,WA, September 2001.Google Scholar
  5. 5.
    J. Liang, R. Haralick, and I. T. Phillips. Document zone classification using sizes of connected components. Document Recognition III, SPIE’96, pages 150–157, 1996.Google Scholar
  6. 6.
    D. Chetverikov, J. Liang, J. Komuves, and R. Haralick. Zone classification using texture features. In Proc. International Conference on Pattern Recognition, pages 676–680, Vienna, 1996.Google Scholar
  7. 7.
    D. X. Le, J. Kim, G. Pearson, and G. R. Thom. Automated labeling of zones from scanned documents. Proceedings SDIUT99, pages 219–226, 1999.Google Scholar
  8. 8.
    I. Phillips. Users’ reference manual. CD-ROM, UW-III Document Image Database-III, 1995.Google Scholar
  9. 9.
    W. Press, B. Flannery, S. Teukolsky, and W. Vetterling. Numerical Recipes in C. Cambridge University Press, 1988.MATHGoogle Scholar
  10. 10.
    A. Antonacopoulos. Page segmentation using the description of the background. Computer Vision and Image Understanding, pages 350–369, June 1998.Google Scholar
  11. 11.
    H. S. Baird. Background structure in document images. Document Image Analysis, pages 17–34, 1994.Google Scholar
  12. 12.
    W. Buntine. Learning classification trees. Statistics and Computing journal, pages 63–76, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Yalin Wang
    • 1
  • Ihsin T. Phillips
    • 2
  • Robert M. Haralick
    • 3
  1. 1.Dept. of Elect. Eng. Univ. of WashingtonSeattleUS
  2. 2.Dept. of Comp. Science, Queens CollegeCity Univ. of NewYorkFlushingUS
  3. 3.The Graduate SchoolCity Univ. Of NewYorkNewYorkUS

Personalised recommendations