This paper presents a new technique for the recognition of hand-printed Latin characters using machine learning. Conventional methods have relied on manually constructed dictionaries which are tedious to construct and difficult to make tolerant to variation in writing styles. The advantages of machine learning are that it can generalise over a large degree of variation between writing styles and recognition rules can be constructed by example. Characters are scanned into the computer and preprocessing techniques transform the bit-map representation of the characters into set of primitives which can be represented in an attribute base form. A set of such representations for each character is then input to C4.5 which produces a decision tree for classifying each character.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Recognition of hand printed Latin characters using machine learning


    Contributors:
    Ziino, D. (author) / Amin, A. (author) / Sammut, C. (author)


    Publication date :

    1995-01-01


    Size :

    501418 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Recognition of Hand Printed Latin Characters Using Machine Learning

    Ziino, D. / Amin, A. / Sammut, C. | British Library Conference Proceedings | 1995


    Pairwise Coupling for Machine Recognition of Hand-Printed Japanese Characters

    Roth, V. / Tsuda, K. / IEEE | British Library Conference Proceedings | 2001



    Recognition of hand-printed Latin characters based on a structural approach with a neural network classifier

    Amin, A. / Iyer, S. / Wilson, W. H. | British Library Online Contents | 1997


    Segmentation and Recognition of Hand Written Characters Using Subspace Method

    Ariki, Y. / Motegi, Y. | British Library Conference Proceedings | 1995