Lexical Search Approach for Character-String Recognition

  • M. Koga
  • R. Mine
  • H. Sako
  • H. Fujisawa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1655)


A novel method for recognizing character strings, based on a lexical search approach, is presented. In this method, a character string is recognized by searching for a sequence of segmented patterns that fits a string in a lexicon. A remarkable characteristic of this method is that character segmentation and character classification work as subfunctions of the search. The lexical search approach enables the parameters of character classifier to adapt to each segmented pattern. As a result, it improves the recognition accuracy by omitting useless candidates of character classification and by changing the criterion of rejection dynamically. Moreover, the processing time is drastically reduced by using minimum sets of categories for each segmented pattern. The validity of the developed method is shown by the experimental results using a lexicon including 44,700 character strings.


Target Word Search Tree Text Line Character String Reference Pattern 
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.


  1. 1.
    E. Fredkin, Trie Memory, Commun. ACM, Vol. 3, No. 9, pp. 490–500, (1960)CrossRefGoogle Scholar
  2. 2.
    H. Murase, Segmentation and Recognition of Hand-Written Character String Using Linguistic Information, Trans. of the Institute of Electronics, Information and Communication Engineers, vol. J69-D No. 9, pp. 1292–1301 (1986 in (Japanese)Google Scholar
  3. 3.
    H. al, ” Segmentation Methods for Character Recognition: From Segmentation to Document Structure Analysis, Proc. of the IEEE vol. 80, No. 7, (1992)Google Scholar
  4. 4.
    F. Kimura et al, Improvements of a Lexicon Directed Algorithhm for Recognition of Unconstrained Handwritten Words, Proc. of ICDAR '93, pp.18–22(1993)Google Scholar
  5. 5.
    E. Cohen et al, Control Structure for Interpreting Handwritten Addresses, IEEE Trans. PAMI vol. 16. no. 10, pp. 1049–1056 (1994)Google Scholar
  6. 6.
    K. Marukawa et al, A Paper Form Processing System with an Error Correcting Function for Reading Handwritten String, Proc. 3rd Annual Symposium on Document Analysis and Information Retrieval, pp. 469–481 (1994)Google Scholar
  7. 7.
    C. Chen, Lexicon-DrivenWord Recognition, proc. of ICDAR '95, pp. 919–922 (1995)Google Scholar
  8. 8.
    J. J. Hull, Incorporating Language Syntax in Visual Text Recognition with a Statistical Model, IEEE Trans. PAMI vol. 18, no. 12, pp. 1251–1256, (1996)Google Scholar
  9. 9.
    R. G. al, A survey of Methods and Strategies in Character Segmentation, IEEE Trans. PAMI vol.18, no. 7, pp.690–706 (1996)Google Scholar
  10. 10.
    P. D. Gader et al, Neural and Fuzzy Methods in Handwriting Recognition, IEEE Computer, Feb. 1997, pp. 79-8 (1997)Google Scholar
  11. 11.
    L. S. Yaeger et al, Combining Neural Networks and Context-Driven Search for Online, Printed Handwriting Recognition in the NEWTON, AI Magazine, Spring 1998, 73–89 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • M. Koga
    • 1
  • R. Mine
    • 1
  • H. Sako
    • 1
  • H. Fujisawa
    • 1
  1. 1.Central Research LaboratoryHitachi, Ltd.Kokubunji-shi, TokyoJapan

Personalised recommendations