This paper presents a method for locating the points where most likely joints between successive characters within a word occur. The proposed method, whose basic assumptions follow from handwriting generation studies, relies upon a set of morphological criteria applied to both the ligatures and the terminal regions of successive characters in order to decide the most appropriate position for the segmentation points. It does not exploit any temporal information, but rather it manipulates shape information, thus is suitable for both online and off-line handwriting processing. An experimental procedure, adopted to quantitatively evaluate the performance of the proposed algorithm without using any classification method, is also introduced.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    From ligatures to characters: a shape-based algorithm for handwriting segmentation


    Beteiligte:
    De Stefano, C. (Autor:in) / Marcelli, A. (Autor:in)


    Erscheinungsdatum :

    2002-01-01


    Format / Umfang :

    282142 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    From Ligatures to Characters: A Shape-Based Algorithm for Handwriting Segmentation

    De Stefano, C. / Marcelli, A. | British Library Conference Proceedings | 2002


    Numerical Characters and Capital Letters Segmentation Recognition in Mixed Handwriting Context

    Wehbi, H. / Oulhadj, H. / Lemoine, J. et al. | British Library Conference Proceedings | 1995


    Off-Line Cursive Handwriting Segmentation

    Han, K. / Sethi, I. K. | British Library Conference Proceedings | 1995


    Generation of Handwritten Characters with Bayesian Network Based On-line Handwriting Recognizers

    Choi, H. / Cho, S. / Kim, J. et al. | British Library Conference Proceedings | 2003