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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Comparison of normalization methods for character recognition


    Contributors:


    Publication date :

    1995-01-01


    Size :

    465922 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    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


    Wavelet-Based Illumination Normalization for Face Recognition

    Du, S. / Ward, R. | British Library Conference Proceedings | 2005