This paper validates a recognition system via multiwavelet neural network as feature extractor and classifier. It investigates the relevance of each sub-band image in the recognition process. An experiment to verify the efficiency of the multiwavelet was performed omitting the feature extraction step. Results show that information about the relevant image features are evenly distributed in all sub-band images of multiwavelet coefficients and that multiwavelet neural network are promising feature extractors and classifiers. Numerals from the NIST database were used for evaluation of the system tested.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Performance Analysis of Handwritten Numerals Recognition Based on Multiwavelet Neural Network


    Beteiligte:
    Huang, Tong-cheng (Autor:in) / Ding, You-dong (Autor:in) / Yin, Li-ping (Autor:in)


    Erscheinungsdatum :

    01.05.2008


    Format / Umfang :

    440434 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch






    Evaluation of Codes and Primitives: Recognition of Unconstrained Handwritten Numerals

    Feray, N. / De Brucq, D. / Romeo-Pakker, K. et al. | British Library Conference Proceedings | 1995


    A Multi-Layer Classifier for Recognition of Unconstrained Handwritten Numerals

    Wang, G.-E. / Wang, J.-F. | British Library Conference Proceedings | 1995