This paper describes the design and implementation of a system that recognizes machine-printed Arabic words without prior segmentation. The technique is based on describing symbols in terms of shape primitives. At recognition time, the primitives are detected on a word image using mathematical morphology operations. The system then matches the detected primitives with symbol models. This leads to a spatial arrangement of matched symbol models. The system conducts a search in the space of spatial arrangements of models and outputs the arrangement with the highest posterior probability as the recognition of the word. The advantage of using this whole word approach versus a segmentation approach is that the result of recognition is optimized with regard to the whole word. Results of preliminary experiments using a lexicon of 42,000 words show a recognition rate of 99.4% for noise-free text and 73% for scanned text.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Segmentation-free word recognition with application to Arabic


    Contributors:


    Publication date :

    1995-01-01


    Size :

    478263 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Segmentation-Free Word Recognition with Application to Arabic

    Al-Badr, B. / Haralick, R. M. | British Library Conference Proceedings | 1995


    Segmentation Free Approach for Printed Arabic Text Recognition

    Tolba, M. F. / Moty, G. A. / Mahmoud, A. | British Library Online Contents | 2003


    Cursive Arabic Script Segmentation and Recognition System

    Sari, T. / Sellami, M. | British Library Online Contents | 2005


    Segmentation versus segmentation-free for recognizing Arabic text [2422-25]

    Allam, M. / SPIE | British Library Conference Proceedings | 1995


    Structural analysis of Arabic handwriting: segmentation and recognition

    Romeo-Pakker, K. / Ameur, A. / Olivier, C. et al. | British Library Online Contents | 1995