AWERProcedia
Information Technology
&
Computer Science
1 (2012) 1151-1160
2
nd
World Conference on Information Technology (WCIT-2011)
EigenCoin: sassanid coins classification based on Bhattacharyya
distance
Rahele Allahverdi
a
*, Mohammad Mahdi Dehshibi
a
, Azam Bastanfard
b
, Daryoosh
Akbarzadeh
c
a
Department of Electrical, Computer and IT, Islamic Azad University, Qazvin Branch, Iran
b
Department of Computer Engineering, Islamic Azad University, Karaj Branch, Iran
c
National Museum of Iran, Tehran, Iran
Abstract
Solving pattern recognition problems using imbalanced databases is a hot topic, which entices researchers to bring it into
focus. Therefore, we consider this problem in the application of Sassanid coins classification. Our focus is not only on
proposing EigenCoin manifold with Bhattacharyya distance for the classification task, but also on testing the influence of the
holistic and feature-based approaches. EigenCoin consists of three main steps namely manifold construction, mapping test
data, and classification. Conducted experiments show EigenCoin outperformed other observed algorithms and achieved the
accuracy from 9.45% up to 21.75%, while it has the capability of handling the over-fitting problem.
Keywords: EigenCoin, Sassanid Coin Classification, Bhattacharyya distance, Over-fitting;
©2012 Academic World Education & Research Center. All rights reserved.
1. Introduction
In recent years, much research has been devoted to make the pattern recognition algorithms applicable and
solve the real world problems. Many desired applications such as biometric data analysis, medical image
processing, quantifying industrial products, and optical/handwritten character recognition are highly demanded
by this requirement. However, cultural heritage studies have been less taken into consideration due to several
*ADDRESS FOR CORRESPONDENCE:
Rahele, Allahverdi, Department of Electrical, Computer and IT, Islamic Azad University, Qazvin Branch,
E-Mail: mohammad.dehshibi@ieee.org
Selection and peer review under responsibility of Prof. Dr. Hafize Keser.
Iran