Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Fuzzy Hough transform and an MLP with fuzzy input output for character recognition
Autore:
Sural, S; Das, PK;
Indirizzi:
CMC Ltd, Calcutta 700016, W Bengal, India CMC Ltd Calcutta W Bengal India700016 , Calcutta 700016, W Bengal, India Jadavpur Univ, Dept Comp Sci & Engn, Calcutta 700032, W Bengal, India Jadavpur Univ Calcutta W Bengal India 700032 utta 700032, W Bengal, India
Titolo Testata:
FUZZY SETS AND SYSTEMS
fascicolo: 3, volume: 105, anno: 1999,
pagine: 489 - 497
SICI:
0165-0114(19990801)105:3<489:FHTAAM>2.0.ZU;2-J
Fonte:
ISI
Lingua:
ENG
Soggetto:
NEURAL-NETWORK; PERCEPTRON; ALGORITHM;
Keywords:
pattern recognition; fuzzy Hough transform; linguistic sets; multilayer perceptron; character recognition;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
23
Recensione:
Indirizzi per estratti:
Indirizzo: Sural, S 151 Kanungo Pk, Calcutta 700084, W Bengal, India 151 Kanungo Pk Calcutta W Bengal India 700084 4, W Bengal, India
Citazione:
S. Sural e P.K. Das, "Fuzzy Hough transform and an MLP with fuzzy input output for character recognition", FUZ SET SYS, 105(3), 1999, pp. 489-497

Abstract

A neuro-fuzzy system for character recognition using a fuzzy Hough transform technique is presented in this paper. For each character pattern, membership values are determined for a number of fuzzy sets defined on the standard Hough transform accumulator cells. These basic fuzzy sets are combined by t-norms to synthesize additional fuzzy sets whose heights form an n-dimensional feature vector for the pattern. A 3n-dimensional fuzzy linguistic vector is generated from the n-dimensional feature vector by defining three linguistic fuzzy sets, namely, weak, moderate and strong. The linguistic setmembership functions are derived from the Butterworth polynomials and are similar to the gain functions of low-pass, band-pass and high-pass filters,respectively. A multilayer perceptron (MLP) is trained with the fuzzy linguistic vectors by the back propagation of errors. The MLP outputs representfuzzy sets denoting similarity of an input feature vector to a number of character pattern classes. Recognition accuracy of the system is more than 98%, (C) 1999 Elsevier Science B.V. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 16/07/20 alle ore 19:59:05