Handwriting recognition and OCR systems need to cope with a wide variety of writing styles and fonts, many of them possibly not previously encountered during training. This paper describes a notion of Bayesian statistical similarity and demonstrates how it can be applied to rapid adaptation to new styles. The ability to generalize across different problem instances is illustrated in the Gaussian case, and the use of statistical similarity Gaussian case is shown to be related to adaptive metric classification methods. The relationship to prior approaches to multitask learning, as well as variable or adaptive metric classification, and hierarchical Bayesian methods, are discussed. Experimental results on character recognition from the NIST3 database are presented.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Character recognition by adaptive statistical similarity


    Contributors:


    Publication date :

    2003-01-01


    Size :

    243210 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Character Recognition by Adaptive Statistical Similarity

    Breuel, T. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003


    Character recognition using statistical moments

    Chim, Y. C. / Kassim, A. A. / Ibrahim, Y. | British Library Online Contents | 1999


    Optimizing Binary Feature Vector Similarity Measure Using Genetic Algorithm and Handwritten Character Recognition

    Cha, S. / Tappert, C. / Srihari, S. et al. | British Library Conference Proceedings | 2003



    Improving optical character recognition accuracy using adaptive image restoration

    Stubberud, P. A. / Kanai, J. / Kalluri, V. | British Library Online Contents | 1996