loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Eighth International Conference on Document Analysis and Recognition (ICDAR'05)
Multiple Handwritten Text Line Recognition Systems Derived from Specific Integration of a Language Model
Seoul, Korea
August 31-September 01
ISBN: 0-7695-2420-6
ASCII Text
x 
 
Roman Bertolami, Horst Bunke, "Multiple Handwritten Text Line Recognition Systems Derived from Specific Integration of a Language Model," Document Analysis and Recognition, International Conference on, pp. 521-527, Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005.
 
 
BibTex
x
 
@article{ 10.1109/ICDAR.2005.167,
author = {Roman Bertolami and Horst Bunke},
title = {Multiple Handwritten Text Line Recognition Systems Derived from Specific Integration of a Language Model},
journal ={Document Analysis and Recognition, International Conference on},
volume = {0},
year = {2005},
issn = {1520-5263},
pages = {521-527},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.2005.167},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Document Analysis and Recognition, International Conference on
TI - Multiple Handwritten Text Line Recognition Systems Derived from Specific Integration of a Language Model
SN - 1520-5263
SP521
EP527
A1 - Roman Bertolami,
A1 - Horst Bunke,
PY - 2005
KW - null
VL - 0
JA - Document Analysis and Recognition, International Conference on
ER -
 
Roman Bertolami, University of Bern, Switzerland
Horst Bunke, University of Bern, Switzerland
This paper investigates the generation and use of multiple recognition results to improve the performance of an offline handwritten text line recognition system. Multiple recognition results are created by specific integration of a language model in the hidden Markov model based recognition system. The ROVER algorithm is applied to combine the multiple results. Experiments conducted on the IAM database show that the proposed system is able to produce statistically significant improvements in the recognition rate compared to the original system.
Citation:
Roman Bertolami, Horst Bunke, "Multiple Handwritten Text Line Recognition Systems Derived from Specific Integration of a Language Model," icdar, pp.521-527, Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005
Usage of this product signifies your acceptance of the Terms of Use.