Much research in handwriting recognition has focused on how to improve recognizers with constrained training set sizes. This paper presents the results of training a nearest-neighbor based online Japanese Kanji recognizer and a neural-network based online cursive English recognizer on a wide range of training set sizes, including sizes not generally available. The experiments demonstrate that increasing the amount of training data improves the accuracy, even when the recognizer's representation power is limited.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    The effect of large training set sizes on online Japanese Kanji and English cursive recognizers


    Contributors:
    Rowley, H.A. (author) / Goyal, M. (author) / Bennett, J. (author)


    Publication date :

    2002-01-01


    Size :

    257996 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    The Effect of Large Training Set Sizes on Online Japanese Kanji and English Cursive Recognizers

    Rowley, H. A. / Goyal, M. / Bennett, J. | British Library Conference Proceedings | 2002


    On-Line Cursive Kanji Character Recognition as Stroke Correspondence Problem

    Wakahara, T. / Suzuki, A. / Nakajima, N. et al. | British Library Conference Proceedings | 1995


    Offline Recognition of Large Vocabulary Cursive Handwritten Text

    Vinciarelli, A. / Bengio, S. / Bunke, H. et al. | British Library Conference Proceedings | 2003


    Offline recognition of large vocabulary cursive handwritten text

    Vinciarelli, A. / Bengio, S. / Bunke, H. | IEEE | 2003


    Persian Cursive Script Recognition

    Hashemi, M. R. / Fatemi, O. / Safavi, R. | British Library Conference Proceedings | 1995