Efficient multi-currency classification of CIS banknotes

Sungwook Youn, Euisun Choi, Yoonkil Baek, Chul Hee Lee

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

In this paper, we propose a fast and efficient algorithm to classify multi-national banknote images using size information and multi-template correlation matching. Since different banknotes have different sizes, this information was considered to be an important characteristic. Using the size information, we generated a size map to group the banknotes. Then, we determined the discriminant areas of each banknote that have high correlations among the same kind of banknote and low correlations with different kinds of banknotes. Post-processing was applied to handle degradations such as writing, aging, etc. The algorithm was tested using 55 banknotes of 30 different denominations from five countries: KRW, USD, EUR, CNY, and RUB. The experimental results showed 100% classification accuracy for unsoiled banknotes and 99.8% classification accuracy for soiled banknotes. The average processing time was about 4.83. ms per banknote.

Original languageEnglish
Pages (from-to)22-32
Number of pages11
JournalNeurocomputing
Volume156
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

Processing
Aging of materials
Degradation

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Cognitive Neuroscience

Cite this

Youn, Sungwook ; Choi, Euisun ; Baek, Yoonkil ; Lee, Chul Hee. / Efficient multi-currency classification of CIS banknotes. In: Neurocomputing. 2015 ; Vol. 156. pp. 22-32.
@article{2ac0339494cd4dc0b0e4cb024b0f23c2,
title = "Efficient multi-currency classification of CIS banknotes",
abstract = "In this paper, we propose a fast and efficient algorithm to classify multi-national banknote images using size information and multi-template correlation matching. Since different banknotes have different sizes, this information was considered to be an important characteristic. Using the size information, we generated a size map to group the banknotes. Then, we determined the discriminant areas of each banknote that have high correlations among the same kind of banknote and low correlations with different kinds of banknotes. Post-processing was applied to handle degradations such as writing, aging, etc. The algorithm was tested using 55 banknotes of 30 different denominations from five countries: KRW, USD, EUR, CNY, and RUB. The experimental results showed 100{\%} classification accuracy for unsoiled banknotes and 99.8{\%} classification accuracy for soiled banknotes. The average processing time was about 4.83. ms per banknote.",
author = "Sungwook Youn and Euisun Choi and Yoonkil Baek and Lee, {Chul Hee}",
year = "2015",
month = "1",
day = "1",
doi = "10.1016/j.neucom.2015.01.014",
language = "English",
volume = "156",
pages = "22--32",
journal = "Review of Economic Dynamics",
issn = "1094-2025",
publisher = "Academic Press Inc.",

}

Efficient multi-currency classification of CIS banknotes. / Youn, Sungwook; Choi, Euisun; Baek, Yoonkil; Lee, Chul Hee.

In: Neurocomputing, Vol. 156, 01.01.2015, p. 22-32.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Efficient multi-currency classification of CIS banknotes

AU - Youn, Sungwook

AU - Choi, Euisun

AU - Baek, Yoonkil

AU - Lee, Chul Hee

PY - 2015/1/1

Y1 - 2015/1/1

N2 - In this paper, we propose a fast and efficient algorithm to classify multi-national banknote images using size information and multi-template correlation matching. Since different banknotes have different sizes, this information was considered to be an important characteristic. Using the size information, we generated a size map to group the banknotes. Then, we determined the discriminant areas of each banknote that have high correlations among the same kind of banknote and low correlations with different kinds of banknotes. Post-processing was applied to handle degradations such as writing, aging, etc. The algorithm was tested using 55 banknotes of 30 different denominations from five countries: KRW, USD, EUR, CNY, and RUB. The experimental results showed 100% classification accuracy for unsoiled banknotes and 99.8% classification accuracy for soiled banknotes. The average processing time was about 4.83. ms per banknote.

AB - In this paper, we propose a fast and efficient algorithm to classify multi-national banknote images using size information and multi-template correlation matching. Since different banknotes have different sizes, this information was considered to be an important characteristic. Using the size information, we generated a size map to group the banknotes. Then, we determined the discriminant areas of each banknote that have high correlations among the same kind of banknote and low correlations with different kinds of banknotes. Post-processing was applied to handle degradations such as writing, aging, etc. The algorithm was tested using 55 banknotes of 30 different denominations from five countries: KRW, USD, EUR, CNY, and RUB. The experimental results showed 100% classification accuracy for unsoiled banknotes and 99.8% classification accuracy for soiled banknotes. The average processing time was about 4.83. ms per banknote.

UR - http://www.scopus.com/inward/record.url?scp=84923573721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923573721&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2015.01.014

DO - 10.1016/j.neucom.2015.01.014

M3 - Article

AN - SCOPUS:84923573721

VL - 156

SP - 22

EP - 32

JO - Review of Economic Dynamics

JF - Review of Economic Dynamics

SN - 1094-2025

ER -