Image size normalization is a crucial preprocessing stage in the development of robust object recognizers. A new method of image size normalization based on multirate filter theory is proposed. Comparisons with ratio-based normalization and simple scaling are made. The effect of each normalization method on handwritten digit recognition is evaluated. Recognition incorporates global and local features extracted from normalized digit images and used with a neural network and K-nearest neighbor classifier performance evaluation is based on recognition accuracy, reject versus error graph, figure of merit and processing time required by each method. Multirate-based normalization yields better recognition performance at the cost of increased computation, whereas ratio-based normalization and simple scaling method require less processing time with reduced recognition performance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Comparison of normalization methods for character recognition


    Beteiligte:
    Srikantan, G. (Autor:in) / Dar-Shyang Lee (Autor:in) / Favata, J.T. (Autor:in)


    Erscheinungsdatum :

    01.01.1995


    Format / Umfang :

    465922 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Comparison of Normalization Methods for Character Recognition

    Srikantan, G. / Lee, D.-S. / Favata, J. T. | British Library Conference Proceedings | 1995


    Handwritten Chinese Character Recognition: Alternatives to Nonlinear Normalization

    Liu, C. / Sako, H. / Fujisawa, H. et al. | British Library Conference Proceedings | 2003



    Image normalization for pattern recognition

    Pei, S.-C. / Lin, C.-N. | British Library Online Contents | 1995


    Illumination Modeling and Normalization for Face Recognition

    Wang, H. / Li, S. / Wang, Y. et al. | British Library Conference Proceedings | 2003