Skip to main content
Springer Nature Link
Log in

How to Deal with Uncertainty and Variability: Experience and Solutions

  • Conference paper
Arabic and Chinese Handwriting Recognition (SACH 2006)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 4768))

Included in the following conference series:

  • 885 Accesses

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.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  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. 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. Winston, P.H.: Artificial Intelligence, pp. 89–105. Addison-Wesley Publishing Company, Reading (1979)

    MATH  Google Scholar 

  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)

    Article  Google Scholar 

  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. 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. Chen, C.H.: Lexicon-Driven Word Recognition. In: Proc. 3rd ICDAR, Montreal, Canada, pp. 919–922 (1995)

    Google Scholar 

  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. 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. 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. 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. 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)

    Article  Google Scholar 

  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)

    Article  Google Scholar 

  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. 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)

    Article  Google Scholar 

  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. Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn., p. 480. John Wiley & Sons, Chichester (2001)

    MATH  Google Scholar 

  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 

Download references

Author information

Authors and Affiliations

  1. Central Research Laboratory, Hitachi, Ltd., Tokyo, Japan, 185-8601

    Hiromichi Fujisawa

Authors
  1. Hiromichi Fujisawa
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

David Doermann Stefan Jaeger

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Fujisawa, H. (2008). How to Deal with Uncertainty and Variability: Experience and Solutions. In: Doermann, D., Jaeger, S. (eds) Arabic and Chinese Handwriting Recognition. SACH 2006. Lecture Notes in Computer Science, vol 4768. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78199-8_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-78199-8_8

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-78198-1

  • Online ISBN: 978-3-540-78199-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics