This paper describes a complete system for reading type-written lexicon words in noisy images - in this case museum index cards. The system is conceptually simple, and straightforward to implement. It involves three stages of processing. The first stage extracts row-regions from the image, where each row is a hypothesized line of text. The next stage scans an OCR classifier over each row image, creating a character hypothesis graph in the process. This graph is then searched using a priority-queue based algorithm for the best matches with a set of words (lexicon). Performance evaluation on a set of museum archive cards indicates competitive accuracy and also reasonable throughput. The priority queue algorithm is over two hundred times faster than using flat dynamic programming on these graphs.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fast lexicon-based word recognition in noisy index card images


    Contributors:
    Lucas, S.M. (author) / Patoulas, G. (author) / Downton, A.C. (author)


    Publication date :

    2003-01-01


    Size :

    278550 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Fast Lexicon-Based Word Recognition in Noisy Index Card Images

    Lucas, S. / Patoulas, G. / Downton, A. et al. | British Library Conference Proceedings | 2003


    Lexicon-Driven Word Recognition

    Chen, C.-H. | British Library Conference Proceedings | 1995


    Medical Word Recognition Using a Computational Semantic Lexicon

    Milewski, R. / Govindaraju, V. | British Library Conference Proceedings | 2002


    Fast Object Recognition in Noisy Images Using Simulated Annealing

    Betke, Margrit / Makris, Nicholas | DSpace@MIT | 1995

    Free access

    Fast Object Recognition in Noisy Images Using Simulated Annealing

    Betke, M. / Makris, N. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995