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

Pinzolas, Miguel, et al. "A neuro-fuzzy system for isolated hand-written digit recognition.." Mathware and Soft Computing 8.3 (2001): 291-301. <http://eudml.org/doc/39227>.

@article{Pinzolas2001,
abstract = {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.},
author = {Pinzolas, Miguel, Astrain, José Javier, Villadangos, Jesús, González de Mendívil, José Ramón},
journal = {Mathware and Soft Computing},
keywords = {Lógica difusa; Redes neuronales; Reconocimiento de caracteres; neuro-fuzzy system; hand-written digit recognition},
language = {eng},
number = {3},
pages = {291-301},
title = {A neuro-fuzzy system for isolated hand-written digit recognition.},
url = {http://eudml.org/doc/39227},
volume = {8},
year = {2001},
}

TY - JOUR
AU - Pinzolas, Miguel
AU - Astrain, José Javier
AU - Villadangos, Jesús
AU - González de Mendívil, José Ramón
TI - A neuro-fuzzy system for isolated hand-written digit recognition.
JO - Mathware and Soft Computing
PY - 2001
VL - 8
IS - 3
SP - 291
EP - 301
AB - 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.
LA - eng
KW - Lógica difusa; Redes neuronales; Reconocimiento de caracteres; neuro-fuzzy system; hand-written digit recognition
UR - http://eudml.org/doc/39227
ER -