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

Miguel Pinzolas; José Javier Astrain; Jesús Villadangos; José Ramón González de Mendívil

Mathware and Soft Computing (2001)

  • Volume: 8, Issue: 3, page 291-301
  • ISSN: 1134-5632

Abstract

top
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.

How to cite

top

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 -

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.