loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
XVI Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'03)
Evaluating the Conventional and Class-Modular Architectures Feedforward Neural Network for Handwritten Word Recognition
S?o Carlos, Brazil
October 12-October 15
ISBN: 0-7695-2032-4
ASCII Text
x 
 
Marcelo N. Kapp, Cinthia O. De A. Freitas, Júlio C. Nievola, Robert Sabourin, "Evaluating the Conventional and Class-Modular Architectures Feedforward Neural Network for Handwritten Word Recognition," Graphics, Patterns and Images, SIBGRAPI Conference on, pp. 315, XVI Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'03), 2003.
 
 
BibTex
x
 
@article{ 10.1109/SIBGRA.2003.1241025,
author = {Marcelo N. Kapp and Cinthia O. De A. Freitas and Júlio C. Nievola and Robert Sabourin},
title = {Evaluating the Conventional and Class-Modular Architectures Feedforward Neural Network for Handwritten Word Recognition},
journal ={Graphics, Patterns and Images, SIBGRAPI Conference on},
volume = {0},
year = {2003},
issn = {1530-1834},
pages = {315},
doi = {http://doi.ieeecomputersociety.org/10.1109/SIBGRA.2003.1241025},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Graphics, Patterns and Images, SIBGRAPI Conference on
TI - Evaluating the Conventional and Class-Modular Architectures Feedforward Neural Network for Handwritten Word Recognition
SN - 1530-1834
SP
EP
A1 - Marcelo N. Kapp,
A1 - Cinthia O. De A. Freitas,
A1 - Júlio C. Nievola,
A1 - Robert Sabourin,
PY - 2003
KW - null
VL - 0
JA - Graphics, Patterns and Images, SIBGRAPI Conference on
ER -
 
Marcelo N. Kapp, Pontif?cia Universidade Cat?lica do Paran?
Cinthia O. De A. Freitas, Pontif?cia Universidade Cat?lica do Paran?
Júlio C. Nievola, Pontif?cia Universidade Cat?lica do Paran?
Robert Sabourin, ?cole de Technologie Sup?rieure
This paper evaluates the use of the conventional architecture feedforward MLP (multiple layer perceptron) and class-modular for the handwriting recognition and it also compares the results obtained with previous works in terms of recognition rate. This work presents 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.
Citation:
Marcelo N. Kapp, Cinthia O. De A. Freitas, Júlio C. Nievola, Robert Sabourin, "Evaluating the Conventional and Class-Modular Architectures Feedforward Neural Network for Handwritten Word Recognition," sibgrapi, pp.315, XVI Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'03), 2003
Usage of this product signifies your acceptance of the Terms of Use.