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

Autor:	Pinzolas, Miguel, Astrain Escola, José Javier, Villadangos Alonso, Jesús, González de Mendivil, José Ramón
Jazyk:	angličtina
Rok vydání:	2001
Předmět:	ComputingMethodologies_PATTERNRECOGNITION Fuzzy classification T-norms Intel·ligència artificial Neuronal networks T-conorms Hand-written digit recognition Reconeixement de formes (Informàtica) -- Classificació automàtica 68 Computer science::68T Artificial intelligence [Classificació AMS]
Zdroj:	UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) Mathware & soft computing; 2001: Vol.: 8 Núm.: 3
Popis:	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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::419ae44641dff67be73270d66a42827e https://hdl.handle.net/2099/3611 Zobrazit plný text záznamu