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.
A neuro-fuzzy system for isolated hand-written digit recognition
2001-01-01
Mathware & soft computing . 2001 Vol. 8 Núm. 3
Article (Journal)
Electronic Resource
English
Hand-Written Digit Recognition Using Combination of Neural Network Classifiers
British Library Conference Proceedings | 1998
|Hand Written Digit Recognition using BKS Combination of Neural Network Classifiers
British Library Conference Proceedings | 1994
|Serbian Connected Digit Recognition System
British Library Conference Proceedings | 1997
|Fourier descriptors and handwritten digit recognition
British Library Online Contents | 1993
|Hand-Written Picture Language for Effective Pattern Recognition
British Library Conference Proceedings | 1996
|