loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
16th International Conference on Pattern Recognition (ICPR'02) - Volume 4
A String Length Predictor to Control the Level Building of HMMs for Handwritten Numeral Recognition
Quebec City, QC, Canada
August 11-August 15
ISBN: 0-7695-1695-X
ASCII Text
x 
 
Alceu de S. Britto Jr., Robert Sabourin, Flavio Bortolozzi, Ching Y. Suen, "A String Length Predictor to Control the Level Building of HMMs for Handwritten Numeral Recognition," Pattern Recognition, International Conference on, vol. 4, pp. 40031, 16th International Conference on Pattern Recognition (ICPR'02) - Volume 4, 2002.
 
 
BibTex
x
 
@article{ 10.1109/ICPR.2002.1047393,
author = {Alceu de S. Britto Jr. and Robert Sabourin and Flavio Bortolozzi and Ching Y. Suen},
title = {A String Length Predictor to Control the Level Building of HMMs for Handwritten Numeral Recognition},
journal ={Pattern Recognition, International Conference on},
volume = {4},
year = {2002},
issn = {1051-4651},
pages = {40031},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICPR.2002.1047393},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Pattern Recognition, International Conference on
TI - A String Length Predictor to Control the Level Building of HMMs for Handwritten Numeral Recognition
SN - 1051-4651
SP
EP
A1 - Alceu de S. Britto Jr.,
A1 - Robert Sabourin,
A1 - Flavio Bortolozzi,
A1 - Ching Y. Suen,
PY - 2002
KW - null
VL - 4
JA - Pattern Recognition, International Conference on
ER -
 
Alceu de S. Britto Jr., Pontif?cia Universidade Cat?lica do Paran? and Universidade Estadual de Ponta Grossa
Robert Sabourin, ?cole de Technologie Sup?rieure and Centre for Pattern Recognition and Machine Intelligence
Flavio Bortolozzi, Pontif?cia Universidade Cat?lica do Paran?
Ching Y. Suen, Centre for Pattern Recognition and Machine Intelligence
In this paper a two-stage HMM-based method for recognizing handwritten numeral strings is extended to work with handwritten numeral strings of unknown length. We have proposed a Bayesian-based string length predictor (SLP) to estimate the number of digits in a string taking into account its width in pixels. The top 3 decisions of the SLP module are used to control the maximum number of levels to be searched by the Level Building (LB) algorithm. On 12,802 handwritten numeral strings and 2,069 touching digit pairs, this strategy has shown a small loss (0.91%) in terms of recognition performance compared to the results when the string length is considered as known.
Citation:
Alceu de S. Britto Jr., Robert Sabourin, Flavio Bortolozzi, Ching Y. Suen, "A String Length Predictor to Control the Level Building of HMMs for Handwritten Numeral Recognition," icpr, vol. 4, pp.40031, 16th International Conference on Pattern Recognition (ICPR'02) - Volume 4, 2002
Usage of this product signifies your acceptance of the Terms of Use.