loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Fourth International Conference Document Analysis and Recognition (ICDAR'97)
Handwritten ZIP Code Recognition
Ulm, GERMANY
August 18-August 20
ISBN: 0-8186-7898-4
ASCII Text
x 
 
Gregory Dzuba, Alexander Filatov, Alexander Volgunin, "Handwritten ZIP Code Recognition," Document Analysis and Recognition, International Conference on, pp. 766, Fourth International Conference Document Analysis and Recognition (ICDAR'97), 1997.
 
 
BibTex
x
 
@article{ 10.1109/ICDAR.1997.620613,
author = {Gregory Dzuba and Alexander Filatov and Alexander Volgunin},
title = {Handwritten ZIP Code Recognition},
journal ={Document Analysis and Recognition, International Conference on},
volume = {0},
year = {1997},
isbn = {0-8186-7898-4},
pages = {766},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.1997.620613},
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 - Handwritten ZIP Code Recognition
SN - 0-8186-7898-4
SP
EP
A1 - Gregory Dzuba,
A1 - Alexander Filatov,
A1 - Alexander Volgunin,
PY - 1997
KW - Handwriting recognition
KW - address recognition
KW - field localization
KW - confidence level
KW - cross validation
KW - feature extraction
VL - 0
JA - Document Analysis and Recognition, International Conference on
ER -
 
Gregory Dzuba, Parascript, LLC, 1035 Pearl Street, Suite 206, Boulder, CO 80302 USA
Alexander Filatov, Parascript, LLC, 1035 Pearl Street, Suite 206, Boulder, CO 80302 USA
Alexander Volgunin, Parascript, LLC, 1035 Pearl Street, Suite 206, Boulder, CO 80302 USA
The encoding of delivery point code (DPC) for handwritten address is one of the most complex problems of the US mail delivery automation. This paper describes a real-time system intended to recognize the 5-digit ZIP code part of DPC. To increase the system performance the results of ZIP code recognition are cross-validated with those of city and state names recognition. Main principles of the handwritten word recognizer which is the core of the system are explained. The system throughput is 40.000 address blocks per hour. Experimental results on live mail pieces are presented. ZIP code recognition rate is 73% with 1% error rate.
Index Terms:
Handwriting recognition, address recognition, field localization, confidence level, cross validation, feature extraction
Citation:
Gregory Dzuba, Alexander Filatov, Alexander Volgunin, "Handwritten ZIP Code Recognition," icdar, pp.766, Fourth International Conference Document Analysis and Recognition (ICDAR'97), 1997
Usage of this product signifies your acceptance of the Terms of Use.