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.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Minimum classification error training for online handwritten word recognition


    Beteiligte:
    Biem, A. (Autor:in)


    Erscheinungsdatum :

    01.01.2002


    Format / Umfang :

    300616 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    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


    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


    Handwritten Word Recognition for Real-Time Applications

    Kim, G. / Govindaraju, V. | British Library Conference Proceedings | 1995