Handwritten text recognition is a problem rarely studied out of specific applications for which lexical knowledge can constrain the vocabulary to a limited one. In the case of handwritten text recognition, additional information can be exploited to characterize the specificity of the writing. This knowledge can help the recognition system to find coherent solutions from both the lexical and the morphological points of view. We present the principles of a handwritten text recognition system based on the online learning of the writer shapes. The proposed scheme is shown to improve the recognition rates on a sample of fifteen writings, unknown to the system.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Handwritten text recognition through writer adaptation


    Contributors:
    Nosary, A. (author) / Paquet, T. (author) / Heutte, L. (author) / Bensefia, A. (author)


    Publication date :

    2002-01-01


    Size :

    400680 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Handwritten Text Recognition Through Writer Adaptation

    Nosary, A. / Paquet, T. / Heutte, L. et al. | British Library Conference Proceedings | 2002


    Automatic Handwriting Recognition and Writer Matching on Anthrax-Related Handwritten Mail

    Srihari, S. N. / Lee, S. | British Library Conference Proceedings | 2002



    Offline recognition of large vocabulary cursive handwritten text

    Vinciarelli, A. / Bengio, S. / Bunke, H. | IEEE | 2003


    Combining diverse systems for handwritten text line recognition

    Liwicki, M. | British Library Online Contents | 2011