loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2
Context-Sensitive Error Correction: Using Topic Models to Improve OCR
Curitiba, Parana, Brazil
September 23-September 26
ISBN: 0-7695-2822-8
ASCII Text
x 
 
M. Wick, M. Ross, E. Learned-Miller, "Context-Sensitive Error Correction: Using Topic Models to Improve OCR," Document Analysis and Recognition, International Conference on, vol. 2, pp. 1168-1172, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2, 2007.
 
 
BibTex
x
 
@article{ 10.1109/ICDAR.2007.91,
author = {M. Wick and M. Ross and E. Learned-Miller},
title = {Context-Sensitive Error Correction: Using Topic Models to Improve OCR},
journal ={Document Analysis and Recognition, International Conference on},
volume = {2},
year = {2007},
issn = {1520-5363},
pages = {1168-1172},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.2007.91},
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 - Context-Sensitive Error Correction: Using Topic Models to Improve OCR
SN - 1520-5363
SP1168
EP1172
A1 - M. Wick,
A1 - M. Ross,
A1 - E. Learned-Miller,
PY - 2007
VL - 2
JA - Document Analysis and Recognition, International Conference on
ER -
 
M. Wick, University of Massachusetts Amherst
M. Ross, University of Massachusetts Amherst
E. Learned-Miller, University of Massachusetts Amherst
Modern optical character recognition software relies on human interaction to correct misrecognized charac- ters. Even though the software often reliably identifies low-confidence output, the simple language and vocabu- lary models employed are insufficient to automatically cor- rect mistakes. This paper demonstrates that topic models, which automatically detect and represent an article's se- mantic context, reduces error by 7% over a global word distribution in a simulated OCR correction task. Detecting and leveraging context in this manner is an important step towards improving OCR.
Citation:
M. Wick, M. Ross, E. Learned-Miller, "Context-Sensitive Error Correction: Using Topic Models to Improve OCR," icdar, vol. 2, pp.1168-1172, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2, 2007
Usage of this product signifies your acceptance of the Terms of Use.