Advertisement

Symbolic Learning Techniques in Paper Document Processing

  • Oronzo Altamura
  • Floriana Esposito
  • Francesca A. Lisi
  • Donato Malerba
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1715)

Abstract

WISDOM++ is an intelligent document processing system that transforms a paper document into HTML/XML format. The main design requirement is adaptivity, which is realized through the application of machine learning methods. This paper illustrates the application of symbolic learning algorithms to the first three steps of document processing, namely document analysis, document classification and document understanding. Machine learning issues related to the application are: Efficient incremental induction of decision trees from numeric data, handling of both numeric and symbolic data in first-order rule learning, learning mutually dependent concepts. Experimental results obtained on a set of real-world documents are illustrated and commented.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    O. Altamura, F. Esposito & D. Malerba (1999). WISDOM++: An Interactive and Adaptive Document Analysis System. To appear in Proc. of the 5th Int. Conf. on Document Analysis and Recognition, IEEE Computer Society Press: Los Alamitos.Google Scholar
  2. [2]
    H.S. Baird (1987). The Skew Angle of Printed Documents. Proc. Conf. Of the Society of Photographic Scientists and Engineers, 14–21 (also in R.K.L. O’Gorman (ed.), Document Image Analysis, 204-208, IEEE Computer Society: Los Alamitos, CA, 1995).Google Scholar
  3. [3]
    T. Bayer, U. Bohnacher, & H. Mogg-Schneider (1994). InforPortLab: An Experimental Document Analysis System. Proc. of the IAPR Workshop on Document Analysis Systems, Kaiserslautern, Germany.Google Scholar
  4. [4]
    J.H. Connell & M. Brady. Generating and Generalizing Models of Visual Objects. Artificial Intelligence, 31, 2, 159–183, 1987.CrossRefGoogle Scholar
  5. [5]
    A. Dengel & G. Barth. ANASTASIL: A Hybrid Knowledge-based System for Document Layout Analysis. Proc. of the 6th Int. Joint Conf. on Artificial Intelligence, 1249–1254, 1989.Google Scholar
  6. [6]
    M.A. Eshera, & K.S. Fu (1986). An Image Understanding System using Attributed Symbolic Representation and Inexact Graph-matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8, 604–618.CrossRefGoogle Scholar
  7. [7]
    F. Esposito, D. Malerba, G. Semeraro, E. Annese, &; G. Scafuro (1990). An Experimental Page Layout Recognition System for Office Document Automatic Classification: An Integrated Approach for Inductive Generalization. Proceedings of the 10th International Conference on Pattern Recognition, IEEE Computer Society Press: Los Alamitos, CA, 557–562.Google Scholar
  8. [8]
    F. Esposito, D. Malerba, & G. Semeraro (1994). Multistrategy Learning for Document Recognition. Applied Artificial Intelligence, 8, 1, 33–84.CrossRefGoogle Scholar
  9. [9]
    F. Esposito, D. Malerba, and G. Semeraro (1995). A Knowledge-based Approach to the Layout Analysis. Proc. of the 3rd Int. Conf. on Document Analysis and Recognition, IEEE Computer Society: Los Alamitos, CA, 466–471.Google Scholar
  10. [10]
    F. Esposito, D. Malerba, & G. Semeraro (1997). A Comparative Analysis of Methods for Pruning Decision Trees. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19, 5, 476–491.CrossRefGoogle Scholar
  11. [11]
    F. Esposito, D. Malerba, G. Semeraro, N. Fanizzi, & S. Ferilli (1998). Adding Machine Learning and Knowledge Intensive Techniques to a Digital Library Service. International Journal on Digital Libraries, 2, 1, 3–19.CrossRefGoogle Scholar
  12. [12]
    J.L. Fisher, S.C. Hinds, & D. P. D’Amato (1990). A Rule-based System for Document Image Segmentation. Proc. of the 10th Int. Conf. on Pattern Recognition, IEEE Computer Society Press: Los Alamitos, CA, 567–572.Google Scholar
  13. [13]
    T. Hong, & S. N. Srihari (1997). Representing OCRed Documents in HTML. Proc. of the 4th Int. Conf. on Document Analysis and Recognition, IEEE Computer Society Press: Los Alamitos, CA, 831–834.Google Scholar
  14. [14]
    D. Malerba, F. Esposito, G. Semeraro, &; L. De Filippis (1997). Processing Paper Documents with WISDOM. In M. Lenzerini (Ed.), AI*IA 97: Advances in Artificial Intelligence, Lecture Notes in Artificial Intelligence, Springer: Berlin, 1321, 439–442.Google Scholar
  15. [15]
    D. Malerba, F. Esposito, G. Semeraro, & S. Caggese (1997). Handling Continuous Data in Top-down Induction of First-order Rules. In M. Lenzerini (Ed.), AI*IA 97: Advances in Artificial Intelligence, Lecture Notes in Artificial Intelligence, Springer: Berlin, 1321, 24–35.Google Scholar
  16. [16]
    D. Malerba, F. Esposito, & F. A. Lisi (1998). Learning Recursive Theories with ATRE. In H. Prade (Ed.), Proc. of the 13th European Conf. on Artificial Intelligence, John Wiley & Sons: Chichester, UK, 435-439.Google Scholar
  17. [17]
    D. Malerba, G. Semeraro, & E. Bellisari (1995). LEX: A Knowledge­Based System for the Layout Analysis. Proc. of the 3rd Int. Conf. on the Practical Application of Prolog, 429–443.Google Scholar
  18. [18.
    D. Malerba, G. Semeraro, & F. Esposito (1997). A Multistrategy Approach to Learning Multiple Dependent Concepts. Chapter 4 in C., Taylor & R., Nakhaeizadeh (Eds.), Machine Learning and Statistics: The Interface, Wiley: London, United Kingdom, 87–106.Google Scholar
  19. [19]
    G. Nagy, S. Seth & M. Viswanathan (1992). A Prototype Document Image Analysis System for Technical Journals. IEEE Computer, 25, 7, 10–22.Google Scholar
  20. [20]
    L. O’Gorman (1992). Image and Document Processing Techniques for the RightPages Electronic Library System. Proc. of the 11th Int. Conf. on Pattern Recognition, 260–263.Google Scholar
  21. [21.
    M. Orkin & R. Drogin (1990). Vital Statistics, McGraw Hill: New York.Google Scholar
  22. [22.
    J. R. Quinlan (1993). C4.5: Programs for induction. Morgan Kaufmann: San Mateo, CA.Google Scholar
  23. [23]
    J. C. Schlimmer, & D. Fisher (1986). A Case Study of Incremental Concept Induction. Proc. of the 5th Nat. Conf. on Artificial Intelligence, Morgan Kaufmann: Philadelphia, 496–501.Google Scholar
  24. [24]
    F. Y. Shih, & S. ­S. Chen (1996). Adaptive Document Block Segmentation and Classification. IEEE Trans. on Systems, Man, and Cybernetics ­ Part B, 26, 5, 797–802.CrossRefGoogle Scholar
  25. [25]
    Y. Y. Tang, C. De Yan & C. Y. Suen. Document Processing for Automatic Knowledge Acquisition. IEEE Trans. on Knowledge and Data Engineering, 6(1) (1994) 3–21.CrossRefGoogle Scholar
  26. [26]
    P. E. Utgoff (1989). Incremental Induction of Decision Trees. Machine Learning, 4, 2, 161–186.CrossRefGoogle Scholar
  27. [27]
    P. E. Utgoff (1994). An Improved Algorithm for Incremental Induction of Decision Trees. Proc. of the 11th Int. Conf. on Machine Learning, Morgan Kaufmann: San Francisco, CA.Google Scholar
  28. [28]
    D. Wang & R.N. Srihari (1989). Classification of Newspaper Image Blocks Using Texture Analysis. Computer Vision, Graphics, and Image Processing, 47, 327–352.CrossRefGoogle Scholar
  29. [29]
    K. Y. Wong, R.G. Casey, & F. M. Wahl (1982). Document Analysis System. IBM Journal of Research Development, 26, 6, 647–656.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Oronzo Altamura
    • 1
  • Floriana Esposito
    • 1
  • Francesca A. Lisi
    • 1
  • Donato Malerba
    • 1
  1. 1.Dipartimento di InformaticaUniversità degli Studi di BariBariItaly

Personalised recommendations