We present a hybrid recognition system that integrates hidden Markov models (HMM) with neural networks (NN) in a probabilistic framework. The input data is processed first by a lexicon-driven word recognizer based on HMMs to generate a list of the candidate N-best-scoring word hypotheses as well as the segmentation of such word hypotheses into characters. An NN classifier is used to generate a score for each segmented character and in the end, the scores from the HMM and the NN classifiers are combined to optimize performance. Experimental results show that for an 80,000-word vocabulary, the hybrid HMM/NN system improves by about 10% the word recognition rate over the HMM system alone.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A hybrid large vocabulary handwritten word recognition system using neural networks with hidden Markov models


    Beteiligte:
    Koerich, A.L. (Autor:in) / Leydier, Y. (Autor:in) / Sabourin, R. (Autor:in) / Suen, C.Y. (Autor:in)


    Erscheinungsdatum :

    01.01.2002


    Format / Umfang :

    330842 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    A Hybrid Large Vocabulary Handwritten Word Recognition System Using Neural Networks with Hidden Markov Models

    Koerich, A. L. / Sabourin, R. / Leydier, Y. et al. | British Library Conference Proceedings | 2002



    A Hybrid Radial Basis Function Network/Hidden Markov Model Handwritten Word Recognition System

    Gilloux, M. / Lemarie, B. / Leroux, M. | British Library Conference Proceedings | 1995


    A Complement to Variable Duration Hidden Markov Model in Handwritten Word Recognition

    Chen, M.-Y. / Kundu, A. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994