We apply confidence-scoring techniques to verify the output of a handwriting recognizer. We evaluate a variety of scoring functions, including likelihood ratios and estimated posterior probabilities of correctness, in a postprocessing mode to generate confidence scores at the character or word level. Using the post-processor in conjunction with an HMM-based on-line handwriting recognizer for large-vocabulary word recognition, receiver-operating-characteristic (ROC) curves reveal that our post-processor is able to reject correctly 90% of recognizer errors while only falsely rejecting 33% of correctly-recognized words. For isolated-digit recognition, we achieve a correct rejection rate of 90% while keeping false rejection down to 13%.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Confidence modeling for verification post-processing for handwriting recognition


    Beteiligte:
    Pitrelli, J.F. (Autor:in) / Perrone, M.P. (Autor:in)


    Erscheinungsdatum :

    2002-01-01


    Format / Umfang :

    444479 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Confidence Modeling for Verification Post-Processing for Handwriting Recognition

    Pitrelli, J. F. / Perrone, M. P. | British Library Conference Proceedings | 2002


    Confidence-Scoring Post-Processing for Off-Line Handwritten-Character Recognition Verification

    Pitrelli, J. / Perrone, M. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003




    Bigram-Based Post-Processing for On-Line Handwriting Recognition Using Correctness Evaluation

    Nakamura, A. / Kawajiri, H. | British Library Conference Proceedings | 2002