loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
33rd Applied Imagery Pattern Recognition Workshop (AIPR'04)
An Efficient Selected Feature Set for the Middle Age Persian Character Recognition
Cosmos Club, Washington, DC
October 13-October 15
ISBN: 0-7695-2250-5
ASCII Text
x 
 
S. Alirezaee, H. Aghaeinia, M. Ahmadi, K. Faez, "An Efficient Selected Feature Set for the Middle Age Persian Character Recognition," Applied Image Pattern Recognition Workshop,, pp. 246-250, 33rd Applied Imagery Pattern Recognition Workshop (AIPR'04), 2004.
 
 
BibTex
x
 
@article{ 10.1109/AIPR.2004.12,
author = {S. Alirezaee and H. Aghaeinia and M. Ahmadi and K. Faez},
title = {An Efficient Selected Feature Set for the Middle Age Persian Character Recognition},
journal ={Applied Image Pattern Recognition Workshop,},
volume = {0},
year = {2004},
issn = {1550-5219},
pages = {246-250},
doi = {http://doi.ieeecomputersociety.org/10.1109/AIPR.2004.12},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Applied Image Pattern Recognition Workshop,
TI - An Efficient Selected Feature Set for the Middle Age Persian Character Recognition
SN - 1550-5219
SP246
EP250
A1 - S. Alirezaee,
A1 - H. Aghaeinia,
A1 - M. Ahmadi,
A1 - K. Faez,
PY - 2004
KW - null
VL - 0
JA - Applied Image Pattern Recognition Workshop,
ER -
 
S. Alirezaee, Amirkabir Univ. of Tech., & Iran Telecommunication Research Center, Tehran, Iran; University of Windsor, Canada
H. Aghaeinia, Amirkabir Univ. of Tech., & Iran Telecommunication Research Center, Tehran, Iran
M. Ahmadi, University of Windsor, Canada
K. Faez, Amirkabir Univ. of Tech., & Iran Telecommunication Research Center, Tehran, Iran
In this paper, a morphological based method for recognition of handwritten middle Persian characters is presented. After pre-processing and noise cancellation, Morphological erosion operator with many structure elements is applied. The structure elements are with variable length lines at directions 0, 45, 90, 135 degrees. A five element feature set has been defined so: (1) relative energy of eroded version with respect to the original image energy (REL_ENG), (2) displacement of the center of mass (CM_DIS), (3) minimum eigenvalue (EIG_MIN), (4) maximum eigenvalue (EIG_MAX) and (5) its direction (EIG-DIR). These features are used to design a feedforward neural network with one hidden layer. The best classification error is about 2.39% (97.61% recognition rate), and is achieved with 150 neurons for the hidden layer.
Citation:
S. Alirezaee, H. Aghaeinia, M. Ahmadi, K. Faez, "An Efficient Selected Feature Set for the Middle Age Persian Character Recognition," aipr, pp.246-250, 33rd Applied Imagery Pattern Recognition Workshop (AIPR'04), 2004
Usage of this product signifies your acceptance of the Terms of Use.