We describe an application of the minimum classification error (MCE) training criterion to online unconstrained-style word recognition. The described system uses allograph-HMMs to handle writer variability. The result, on vocabularies of 5k to 10k, shows that MCE training achieves around 17% word error rate reduction when compared to the baseline maximum likelihood system.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Minimum classification error training for online handwritten word recognition


    Contributors:
    Biem, A. (author)


    Publication date :

    2002-01-01


    Size :

    300616 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Minimum Classification Error Training for Online Handwritten Word Recognition

    Biem, A. | British Library Conference Proceedings | 2002


    Local minimum squared error for face and handwritten character recognition

    Fan, Z. / Wang, J. / Zhu, Q. et al. | British Library Online Contents | 2013


    Base Line Correction for Handwritten Word Recognition

    Tsuruoka, S. / Watanabe, N. / Minamide, N. et al. | British Library Conference Proceedings | 1995


    A Format-Driven Handwritten Word Recognition System

    Liu, X. / Shi, Z. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003


    Feature sets evaluation for handwritten word recognition

    de Oliveira, J.J. / de Carvalho, J.M. / de A Freitas, C.O. et al. | IEEE | 2002