Our site uses Javascript to enhance its usability.You can disable your ad blocker or whitelist our website www.worldscientific.com to view the full content.

Select your blocker:

Adblock Plus Instructions

  1. Click the AdBlock Plus icon in the extension bar
  2. Click the blue power button
  3. Click refresh
World Scientific
  • Search
    Quick Search in Journals
    Access type:
    Quick Search anywhere
    Access type:
    Advanced Search
  • My Cart
  •   
Skip main navigation

Cookies Notification

We use cookies on this site to enhance your user experience. By continuing to browse the site, you consent to the use of our cookies. Learn More
×

System Upgrade on Tue, May 28th, 2024 at 2am (EDT)

Existing users will be able to log into the site and access content. However, E-commerce and registration of new users may not be available for up to 12 hours.
For online purchase, please visit us again. Contact us at [email protected] for any enquiries.
SPECIAL ISSUE: Advances in Graphonomics for Handwriting Analysis and Recognition; Edited by A. Marcelli and C. De StefanoNo Access

WRITER STYLE ADAPTATION IN ONLINE HANDWRITING RECOGNIZERS BY A FUZZY MECHANISM APPROACH: THE ADAPT METHOD

    https://doi.org/10.1142/S0218001407005326Cited by:8 (Source: Crossref)
    Previous
    Next

    Abstract

    This study presents an automatic online adaptation mechanism to the handwriting style of a writer for the recognition of isolated handwritten characters. The classifier we use here is based on a Fuzzy Inference System (FIS) similar to those we have designed for handwriting recognition. In this FIS each premise rule is composed of a fuzzy prototype which represents intrinsic properties of a class. Furthermore, the conclusion part of rules associates a score to the prototype for each class. The adaptation mechanism affects both the conclusions of the rules and the fuzzy prototypes by recentering and reshaping them thanks to a new approach called ADAPT inspired by the Learning Vector Quantization. Thus the FIS is automatically fitted to the handwriting style of the writer that currently uses the system. Our adaptation mechanism is compared with well known adaptation techniques. The tests were based on eight different writers and the results illustrate the benefits of the method in terms of error rate reduction (86% in average). This allows such kind of simple classifiers to achieve up to 98.4% of recognition accuracy on the 26 Latin letters in a writer dependent context.

    References

    • E. Anquetil and H. Bouchereau, Integration of an on-line handwriting recognition system in a smart phone device, Proc. 16th Int. Conf. Pattern Recognition3 (2002) pp. 192–195. Google Scholar
    • E. Anquetil and G. Lorette, Automatic generation of hierarchical fuzzy classification systems based on explicit fuzzy rules deduced from possibilistic clustering: Application to on-line handwritten character recognition, Proc. 6th Conf. Information Processing and Management of Uncertainty in Knowledge-Based Systems (1996) pp. 259–264. Google Scholar
    • E. Anquetil and G. Lorette, On-line handwriting character recognition system based on hierarchical qualitative fuzzy modeling, Proc. 5th Int. Workshop on Frontiers in Handwriting Recognition (1996) pp. 47–52. Google Scholar
    • C.   Bishop , Neural Network for Pattern Recognition ( Oxford University Press , 1995 ) . Crossref, Google Scholar
    • F. Bouterucheet al., Design and evaluation of handwriting input interfaces for small-size mobile devices, Proc. 1st Workshop on Improving and Assessing Pen-Based Input Techniques (2005) pp. 49–56. Google Scholar
    • A. Brakensiek, A. Kosmala and G. Rigoll, Comparing adaptation techniques for on-line handwriting recognition, Proc. 6th Int. Conf. Document Analysis and Recognition (2001) pp. 486–490. Google Scholar
    • F. Chung and T. Lee, IEEE Trans. Neural Networks 7(3), 539 (1994). Crossref, Web of Science, Google Scholar
    • S. Connell and A. Jain, IEEE Trans. Patt. Analysis Mach. Intell. 24(3), 329 (2002). Crossref, Web of Science, Google Scholar
    • S. De Backer and P. Scheunders, Imag. Vis. Comput. 19(9–10), 639 (2001). Crossref, Web of Science, Google Scholar
    • T. Kohonen, Proc. IEEE 78(9), 1464 (1990). Crossref, Web of Science, Google Scholar
    • R. Krishnapuram and J. Keller, IEEE Trans. Fuzzy Syst. 1(2), 98 (1993). Crossref, Web of Science, Google Scholar
    • B. Mitaim and S. Kosko, IEEE Trans. Fuzzy Syst. 9(4), 637 (2001). Crossref, Web of Science, Google Scholar
    • A. Nakamura, A method to accelerate adaptation for on-line handwriting recognition of large character set, Proc. 9th Int. Workshop on Frontiers in Handwriting Recognition (2004) pp. 426–431. Google Scholar
    • L. Oudotet al., Self-supervised writer adaptation using perceptive concepts: application to on-line text recognition, Proc. 17th Int. Conf. Pattern Recognition2 (2004) pp. 598–601. Google Scholar
    • N. Ragot and E. Anquetil, Melidis: pattern recognition by intrinsic/discriminant dual modeling based on a hierarchical organization of fuzzy inference systems, Proc. 10th Conf. Information Processing and Management of Uncertainty in Knowledge-Based Systems (2004) pp. 2069–2076. Google Scholar
    • J.   Schürmann , Pattern Classification: A Unified View of Statistical and Neural Approaches ( Wiley-Interscience , 1996 ) . Google Scholar
    • T. Takagi and M. Sugeno, IEEE Trans. Syst. Man Cybern. 15(1), 116 (1985). Web of Science, Google Scholar
    • C. Viard-Gaudinet al., The irest on/off dual handwriting database, Proc. 5th Int. Conf. Document Analysis and Recognition (1999) pp. 455–458. Google Scholar
    • V. Vuori, J. Laaksonen and E. Oja, On-line adaptation in recognition of handwritten alphanumeric characters, Proc. 5th Int. Conf. Document Analysis and Recognition (1999) pp. 792–795. Google Scholar