In this paper we tackle the problem of unconstrained handwritten character recognition using different classification strategies. For such an aim, four multilayer perceptron classifiers (MLP) were built and used into three different classification strategies: combination of two 26-class classifiers; 26-metaclass classifier; 52-class classifier. Experimental results on the NIST SD19 database have shown that the recognition rate achieved by the metaclass classifier (87.8%) outperforms the other approaches (82.9% and 86.3%).


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Unconstrained handwritten character recognition using metaclasses of characters


    Beteiligte:
    Koerich, A.L. (Autor:in) / Kalva, P.R. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    140823 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Unconstrained Handwritten Character Recognition using Metaclasses of Characters

    Koerich, A. L. / Kalva, P. R. | British Library Conference Proceedings | 2005




    Automatic Construction of Structural Models for Unconstrained Handwritten Characters

    Nishida, H. | British Library Conference Proceedings | 1995