A neuro-fuzzy system for isolated hand-written digit recognition using a similarity fuzzy measure is presented. The system is composed of two main blocks: a first block that normalizes the input and compares it with a set of fuzzy patterns, and a second block with a multilayer perceptron to perform a neuronal classification. The comparison with the fuzzy patterns is performed via a fuzzy similarity measure that uses the Yager parametric t-norms and t-conorms. Along this work, several values of the parameters have been studied, in order to obtain the best classification. The simplicity of the method makes it extremely quick and provides a recognition accuracy about 90% in classification of isolated digits, making it an attractive method for practical applications.


    Access

    Download


    Export, share and cite



    Title :

    A neuro-fuzzy system for isolated hand-written digit recognition



    Publication date :

    2001-01-01


    Remarks:

    Mathware & soft computing . 2001 Vol. 8 Núm. 3


    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    006 / 629




    Hand-Written Digit Recognition Using Combination of Neural Network Classifiers

    Khotanzad, A. / Chung, C. / University of Arizona et al. | British Library Conference Proceedings | 1998


    Hand Written Digit Recognition using BKS Combination of Neural Network Classifiers

    Khotanzad, A. / Chung, C. / IEEE et al. | British Library Conference Proceedings | 1994


    Serbian Connected Digit Recognition System

    Stanimirovic, L. | British Library Conference Proceedings | 1997


    Fourier descriptors and handwritten digit recognition

    Lu, Y. / Schlosser, S. / Janeczko, M. | British Library Online Contents | 1993


    Hand-Written Picture Language for Effective Pattern Recognition

    Kawachiya, S. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1996