Advertisement

How to Deal with Uncertainty and Variability: Experience and Solutions

  • Hiromichi Fujisawa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4768)

Abstract

Uncertainty and variability are two of the most important concepts at the center of pattern recognition. It is especially true when patterns to be recognized are complex in nature and not controlled by any artificial constraints. Handwritten postal address recognition is one such case. This paper presents five principles of dealing with uncertainty and variability, and discusses how to decompose the complex recognition task into manageable sub-tasks. When applicable, block diagrams will clarify the structure of various recognition components. This paper also presents implementation of those principles into real recognition engines. It will demonstrate that high accuracy and robustness of a recognition system, which relates to uncertainty and variability, respectively, can occur only with comprehensive approaches.

Keywords

Postal Code Recognition Performance Hill Climbing Read Rate Handwritten Character 
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. 1.
    Kagehiro, T., Koga, M., Sako, H., Fujisawa, H.: Address-Block Extraction by Bayesian Rule. In: Proc. ICPR 2004, vol. 2, pp. 582–585 (2004)Google Scholar
  2. 2.
    Fu, K.S., Chien, Y.T., Cardillo, G.P.: A Dynamic Programming Approach to Sequential Pattern Recognition. IEEE Trans. Electronic Computers EC16, 313–326 (1967)Google Scholar
  3. 3.
    Winston, P.H.: Artificial Intelligence, pp. 89–105. Addison-Wesley Publishing Company, Reading (1979)zbMATHGoogle Scholar
  4. 4.
    Fujisawa, H., Nakano, Y., Kurino, K.: Segmentation Methods for Character Recognition: From Segmentation to Document Structure Analysis. Proc. IEEE 80(7), 1079–1092 (1992)CrossRefGoogle Scholar
  5. 5.
    Marukawa, K., Koga, M., Shima, Y., Fujisawa, H.: An Error Correction Algorithm for Handwritten Chinese Character Address Recognition. In: Proc. 1st ICDAR, Saint-Malo, France, pp. 916–924 (1991)Google Scholar
  6. 6.
    Kimura, F., Sridhar, M., Chen, Z.: Improvements of Lexicon-Directed Algorithm for Recognition of Unconstrained Hand-Written Words. In: Proc. 2nd ICDAR, Tsukuba, Japan, pp. 18–22 (1993)Google Scholar
  7. 7.
    Chen, C.H.: Lexicon-Driven Word Recognition. In: Proc. 3rd ICDAR, Montreal, Canada, pp. 919–922 (1995)Google Scholar
  8. 8.
    Koga, M., Mine, R., Sako, H., Fujisawa, H.: Lexical Search Approach for Char-acter-String Recognition. In: Lee, S.-W., Nakano, Y. (eds.) Document Analysis Systems: Theory and Practice, pp. 115–129. Springer, Heidelberg (1999)Google Scholar
  9. 9.
    Liu, C.-L., Koga, M., Fujisawa, H.: Lexicon-driven Segmentation and Recognition of Handwritten Character Strings for Japanese Address Reading. IEEE Trans. Pattern Analysis and Machine Intelligence 24(11), 425–437 (2002)Google Scholar
  10. 10.
    Ikeda, H., Furukawa, N., Koga, M., Sako, H., Fujisawa, H.: A Context-Free Grammar-Based Language Model for Document Understanding. In: Proc. DAS2000, Rio de Janeiro, Brazil, pp. 135–146 (2000)Google Scholar
  11. 11.
    Suen, C.Y., Nadal, C., Mai, T.A., Legault, R., Lam, L.: Recognition of Totally Unconstrained Handwritten Numerals Based on the Concept of Multiple Experts. In: Proc. 1st IWFHR, Montreal, Canada, pp. 131–143 (1990)Google Scholar
  12. 12.
    Xu, L., Krzyzak, A., Suen, C.Y.: Methods of Combining Multiple Classifiers and Their Applications to Handwriting Recognition. IEEE Trans. Systems, Man and Cybernetics 22(3), 418–435 (1992)CrossRefGoogle Scholar
  13. 13.
    Ho, T.K., Hull, J.J., Srihari, S.N.: Decision Combination in Multiple Classifier Systems. IEEE Trans. Pattern Analysis and Machine Intelligence 16(1), 66–75 (1994)CrossRefGoogle Scholar
  14. 14.
    Houle, G.F., Aragon, D.B., Smith, R.W., Shridhar, M., Kimura, F.: A Multi-Layered Corroboration-Based Check Reader. In: Proc. IAPR Workshop on Document Analysis Systems, Malvern, USA, pp. 495–546 (1996)Google Scholar
  15. 15.
    Ha, T.M., Bunke, H.: Off-Line, Handwritten Numeral Recognition by Perturba-tion. IEEE Trans. Pattern Analysis and Machine Intelligence 19(5), 535–539 (1997)CrossRefGoogle Scholar
  16. 16.
    Tang, H., Augustin, E., Suen, C.Y., Baret, O., Cheriet, M.: Spiral Recognition Methodology and Its Application for Recognition of Chinese Bank Checks. In: Proc. 9th IWFHR, Kokubunji, Japan, pp. 263–268 (2004)Google Scholar
  17. 17.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn., p. 480. John Wiley & Sons, Chichester (2001)zbMATHGoogle Scholar
  18. 18.
    Fujisawa, H., Sako, H.: Balance between Optimistic Planning and Pessimistic Planning in a Mission Critical Project. In: Proc. IEMC2003, Albany, NY, pp. 605–609 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Hiromichi Fujisawa
    • 1
  1. 1.Central Research LaboratoryHitachi, Ltd.TokyoJapan

Personalised recommendations