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

Título inglés	A neuro-fuzzy system for isolated hand-written digit recognition.
Título español	Un sistema neuro-difuso para reconocimiento de dígitos aislados escritos a mano.
Autor/es	Pinzolas, Miguel ; Astrain, José Javier ; Villadangos, Jesús ; González de Mendívil, José Ramón
Organización	Dep. Ing. Sist. Autom. Univ. Politéc. Cartagena, Cartagena (Murcia), España;Dep. Mat. Inform. Univ. Públ. Navarra, Pamplona, España;Dep. Autom. Comput. Univ. Públ. Navarra, Pamplona, España
Revista	1134-5632
Publicación	2001, 8 (3): 291-301, 10 Ref.
Tipo de documento	articulo
Idioma	Inglés
Resumen inglés	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.
Clasificación UNESCO	110208 ; 330405
Palabras clave español	Lógica difusa ; Redes neuronales ; Reconocimiento de caracteres
Código Z-Math	Zbl 0996.68179
Acceso al artículo completo