Advertisement

Towards the Understanding of Printed Documents

  • Thomas Bayer
  • Jürgen Franke
  • Ulrich Kressel
  • Eberhard Mandler
  • Matthias Oberländer
  • Jürgen Schürmann

Abstract

Document analysis aims at the transformation of data presented on paper and addressed to human comprehension into a computer-revisable form. The pixel representation of a scanned document must be converted into a structured set of symbolic entities, which are appropriate for the intended kind of computerized information processing. It can be argued that the achieved symbolic description level resembles the degree of understanding acquired by a document analysis system. This interpretation of the term ‘understanding’ shall be explained a little more deeply. An attempt shall be made to clarify the important question: “Up to what level can a machine really understand a given document?” Looking at the many problems still unsolved, this is indeed questionable.

Keywords

Belief Function Viterbi Algorithm Evidence Theory Logical Object Basic Probability Assignment 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Baird 86]
    H. S. Baird, S. Kahan, and T. Pavlidis, “Components of an Omnifont Page Reader,” Proc. 8th ICPR, Paris, 1986.Google Scholar
  2. [Barnett 81]
    J. A. Barnett, “Computational Methods for a Mathematical Theory of Evidence,” Proc. 7th InVl Joint Conf. on AI, Vancouver, BC, 1981.Google Scholar
  3. [Bartneck 89]
    N. Bartneck, “A general data structure for image analysis based on a description of connected components,” Computing 42, pp. 17–34, 1989.CrossRefMATHGoogle Scholar
  4. [Bayer 86]
    T. Bayer and M. Oberländer, “Ein erweiterter Viterbi Algorithmus zur Berechnung der n-besten Wege in zyklenfreien Modellgraphen,” In G. Hartmann (ed.), Proc. 8th DAGM-Symposium Mustererkennung, Springer-Verlag, Berlin, 1986.Google Scholar
  5. [Bayer 87]
    T. Bayer, “Segmentation of Merged Character Patterns with AI- Techniques,” In Proc. 5th Scandinavian Conf. on Image Analysis, Stockholm, 1987.Google Scholar
  6. [Bayer 90]
    T. Bayer, “Representation of Structured Documents in a Frame System,” In H. Baird (ed.), Pre-Proc. IAPR Workshop on SSPR, Murray Hill, NJ, 1990.Google Scholar
  7. [Dempster 67]
    A. P. Dempster, “Upper and Lower Probabilities Induced by a Multivalued Mapping,” Annals of Mathematical Statistics, 38, pp. 325–339, 1967.CrossRefMATHMathSciNetGoogle Scholar
  8. [Forney 73]
    G. D. Forney, “The Viterbi Algorithm,” Proc. IEEE, Vol. 61, No. 3, March 1973.Google Scholar
  9. [Horak 85]
    W. Horak, “Office Document Architecture and Office Document In terchange Format, Current Status of International Standardization,” IEEE Computer, October 1985.Google Scholar
  10. [Hornik 89]
    K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” Neural Networks, Vol. 2, pp. 359–366, 1989.CrossRefGoogle Scholar
  11. [Kressel 90]
    U. Kressel, J. Franke, and J. Schürmann, “Polynomklassifikator versus Multilayer-Perzeptron,” In R.E. Grosskopf (ed.), Proc. 12th DAGM-Symposium Mustererkennung, Springer-Verlag, Berlin, pp. 75–80, 1990.Google Scholar
  12. [Kohlas 90]
    J. Kohlas, “A Mathematical Theory of Hints: Preliminary Version of the Paper,” Univ. Fribourg, Fribourg, CH, 1990.Google Scholar
  13. [Lee 90]
    D.-S. Lee, S. N. Srihari, and R. Gaborski, “Experiments in Hand written Character Recognition with Pattern Recognition and Neural Network Approaches,” Fourth Advanced Technology Conf, Vol. 2, pp. 1013–1027, 1990.Google Scholar
  14. [Mandler 88]
    E. Mandler and J. Schürmann, “Combining the Classification Results of Independent Classifiers based on the Dempster/Shafer Theory of Evidence,” Pattern Recognition in Practice, Amsterdam, 1988.Google Scholar
  15. [Mandler 90a]
    E. Mandler and M. Oberländer, “Ein single-pass Algorithmus für die schnelle Konturkodierung von Binärbildern,” In R.E. Grosskopf (ed.), Proc. 12th DAGM-Symposium Mustererkennung, Springer-Verlag, Berlin, 1990.Google Scholar
  16. [Mandler 90b]
    E. Mandler and M. Oberländer, “One-Pass Encoding of Connected Components in Multi-Valued Images,” Proc. 10th ICPR, Atlantic City, 1990.Google Scholar
  17. [Meisel 68]
    W. S. Meisel, “Least-Square Methods in Abstract Pattern Recognition,” Information Sciences 1, pp. 43 - 54, 1968.CrossRefGoogle Scholar
  18. [Nilsson 82]
    J. N. Nilsson, Principles of Artificial Intelligence, Springer-Verlag, Berlin, 1982.MATHGoogle Scholar
  19. [Pao 89]
    Y. H. Pao, Adaptive Pattern Recognition and Neural Networks, Addison-Wesley, Reading, MA, pp. 197–222, 1989.MATHGoogle Scholar
  20. [Pearl 84]
    J. Pearl, Heuristics, Intelligent Search Strategies For Computer Problem Solving, Addison-Wesley, Reading, MA, 1984.Google Scholar
  21. [Rastogi 86]
    A. Rastogi and S.N. Srihari, “Recognizing Textual Blocks in Document Images Using the Hough Transform,” TR 86–101, Dept of Computer Science, SUNY at Buffalo, 1986.Google Scholar
  22. [Schürmann 77]
    J. Schürmann, “Polynomklassifikatoren für die Zeichenerkennung,” Oldenbourg Verlag, München Wien, 1977.MATHGoogle Scholar
  23. [Schürmann 78]
    J. Schürmann, “A Multi-Font Word Recognition System for Postal Address Readings,” IEEE Trans, G27, 1978 3, pp. 359–369, 1984.Google Scholar
  24. [Schürmann 84]
    J. Schürmann and W. Doster, “A Decision Theoretic Approach to Hierarchical Classifier Design,” Pattern Recognition, Vol. 17, No. 3, pp. 359 - 369, 1984.CrossRefGoogle Scholar
  25. [Shafer 76]
    G. Shafer, A Mathematical Theory of Evidence, Princeton Univ. Press, Princeton, 1976.Google Scholar
  26. [Watanabe 72]
    S. Watanabe, Frontiers of Pattern Recognition, Academic Press, New York, 1972.MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Thomas Bayer
    • 1
  • Jürgen Franke
    • 1
  • Ulrich Kressel
    • 1
  • Eberhard Mandler
    • 1
  • Matthias Oberländer
    • 1
  • Jürgen Schürmann
    • 1
  1. 1.Research Center UlmDaimler-Benz AGUlmGermany

Personalised recommendations