We combine complementary features based on foreground and background information in an HMM-based classifier to recognize handwritten digits. A zoning scheme based on column and row models provides a way of dividing the digit into zones without making the features size variant. This strategy allows us to avoid the digit normalization, while it provides a way of having information from specific zones of the digit. Recognition rates around 98% have been achieved using 60,000 digit samples of the NIST SD19 database.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Complementary features combined in an HMM-based system to recognize handwritten digits


    Beteiligte:
    Britto, A.S. (Autor:in)


    Erscheinungsdatum :

    01.01.2003


    Format / Umfang :

    252559 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Complementary Features Combined in an HMM-Based System to Recognize Handwritten Digits

    Britto, A. / Sabourin, R. / Bortolozzi, F. et al. | British Library Conference Proceedings | 2003


    Handwritten Digits Parameterisation for HMM Based Recognition

    Travieso, C. M. / Morales, C. R. / Alonso, I. G. et al. | British Library Conference Proceedings | 1999



    A Novel Approach to Separate Handwritten Connected Digits

    Alhajj, R. / Elnagar, A. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003


    Fuzzy state machines to recognize totally unconstructed handwritten strokes

    Abuhaiba, I. S. I. / Datta, S. / Holt, M. J. J. | British Library Online Contents | 1995