Evaluating the conventional and class-modular architectures feedforward neural network for handwritten word recognition

Author

Kapp, Marcelo N. ; Freitas, C.O.D.A. ; Nievola, Julio C. ; Sabourin, Robert

Author_Institution

Pontificia Univ. Catolica do Parana, Curitiba, Brazil

fYear

2003

fDate

12-15 Oct. 2003

Firstpage

315

Lastpage

319

Abstract

We evaluate the use of the conventional architecture feedforward MLP (multiple layer perception) and class-modular for the handwriting recognition and it also compares the results obtained with previous works in terms of recognition rate. We present a feature set in full detail to work with handwriting recognition. The experiments showed that the class-modular architecture is better than conventional architecture. The obtained average recognition rates were 77.08% using the conventional architecture and 81.75% using the class-modular.

Keywords

feature extraction; feedforward neural nets; handwriting recognition; handwritten character recognition; multilayer perceptrons; MLP; class-modular architectures; conventional architecture; feedforward neural network; handwriting recognition; handwritten word recognition; multiple layer perception; Artificial neural networks; Character recognition; Feature extraction; Feedforward neural networks; Handwriting recognition; Neural networks; Pattern recognition; Power generation; Shape; System performance;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Graphics and Image Processing, 2003. SIBGRAPI 2003. XVI Brazilian Symposium on

ISSN

1530-1834

Print_ISBN

0-7695-2032-4

Type

conf

DOI

10.1109/SIBGRA.2003.1241025

Filename

1241025