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

• Autores: Miguel Pinzolas, José Javier Astrain Escola, Jesús Villadangos Alonso, José Ramón González de Mendívil
• Localización: Mathware & soft computing: The Magazine of the European Society for Fuzzy Logic and Technology, ISSN-e 1134-5632, Vol. 8, Nº. 3, 2001, págs. 291-301
• Idioma: inglés
• Títulos paralelos:
  • Un sistema neuro-difuso para reconocimiento de dígitos aislados escritos a mano
• Enlaces
  • Texto completo (pdf)
• Resumen

  • 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.