Detection of counterfeit banknotes using multispectral images

Sangwook Baek, Euisun Choi, Yoonkil Baek, Chul Hee Lee

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper, we propose counterfeit banknote detection algorithms using low resolution multispectral images. It has become increasingly difficult to detect professionally produced counterfeit banknotes, so more sophisticated features have had to be implemented in banknotes. However, sensors that are capable of reading these counter-fake features are rather expensive. On the other hand, multispectral images can be used to tackle the counterfeit banknote problem. Recently, multispectral sensors have been developed for ATM applications. We developed efficient counterfeit banknote detection algorithms and the proposed algorithms were tested using 20 different denominations of European Euro (EUR), Indian rupee (INR), and US Dollars (USD). The experimental results show that the proposed methods provided 99.8% classification accuracy for genuine banknotes and 100% detection accuracy for counterfeit banknotes.

Original languageEnglish
Pages (from-to)294-304
Number of pages11
JournalDigital Signal Processing: A Review Journal
Volume78
DOIs
Publication statusPublished - 2018 Jul 1

Fingerprint

Sensors
Automatic teller machines

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Baek, Sangwook ; Choi, Euisun ; Baek, Yoonkil ; Lee, Chul Hee. / Detection of counterfeit banknotes using multispectral images. In: Digital Signal Processing: A Review Journal. 2018 ; Vol. 78. pp. 294-304.
@article{5e23a56f451d49d983cada1179f0c2f1,
title = "Detection of counterfeit banknotes using multispectral images",
abstract = "In this paper, we propose counterfeit banknote detection algorithms using low resolution multispectral images. It has become increasingly difficult to detect professionally produced counterfeit banknotes, so more sophisticated features have had to be implemented in banknotes. However, sensors that are capable of reading these counter-fake features are rather expensive. On the other hand, multispectral images can be used to tackle the counterfeit banknote problem. Recently, multispectral sensors have been developed for ATM applications. We developed efficient counterfeit banknote detection algorithms and the proposed algorithms were tested using 20 different denominations of European Euro (EUR), Indian rupee (INR), and US Dollars (USD). The experimental results show that the proposed methods provided 99.8{\%} classification accuracy for genuine banknotes and 100{\%} detection accuracy for counterfeit banknotes.",
author = "Sangwook Baek and Euisun Choi and Yoonkil Baek and Lee, {Chul Hee}",
year = "2018",
month = "7",
day = "1",
doi = "10.1016/j.dsp.2018.03.015",
language = "English",
volume = "78",
pages = "294--304",
journal = "Digital Signal Processing: A Review Journal",
issn = "1051-2004",
publisher = "Elsevier Inc.",

}

Detection of counterfeit banknotes using multispectral images. / Baek, Sangwook; Choi, Euisun; Baek, Yoonkil; Lee, Chul Hee.

In: Digital Signal Processing: A Review Journal, Vol. 78, 01.07.2018, p. 294-304.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detection of counterfeit banknotes using multispectral images

AU - Baek, Sangwook

AU - Choi, Euisun

AU - Baek, Yoonkil

AU - Lee, Chul Hee

PY - 2018/7/1

Y1 - 2018/7/1

N2 - In this paper, we propose counterfeit banknote detection algorithms using low resolution multispectral images. It has become increasingly difficult to detect professionally produced counterfeit banknotes, so more sophisticated features have had to be implemented in banknotes. However, sensors that are capable of reading these counter-fake features are rather expensive. On the other hand, multispectral images can be used to tackle the counterfeit banknote problem. Recently, multispectral sensors have been developed for ATM applications. We developed efficient counterfeit banknote detection algorithms and the proposed algorithms were tested using 20 different denominations of European Euro (EUR), Indian rupee (INR), and US Dollars (USD). The experimental results show that the proposed methods provided 99.8% classification accuracy for genuine banknotes and 100% detection accuracy for counterfeit banknotes.

AB - In this paper, we propose counterfeit banknote detection algorithms using low resolution multispectral images. It has become increasingly difficult to detect professionally produced counterfeit banknotes, so more sophisticated features have had to be implemented in banknotes. However, sensors that are capable of reading these counter-fake features are rather expensive. On the other hand, multispectral images can be used to tackle the counterfeit banknote problem. Recently, multispectral sensors have been developed for ATM applications. We developed efficient counterfeit banknote detection algorithms and the proposed algorithms were tested using 20 different denominations of European Euro (EUR), Indian rupee (INR), and US Dollars (USD). The experimental results show that the proposed methods provided 99.8% classification accuracy for genuine banknotes and 100% detection accuracy for counterfeit banknotes.

UR - http://www.scopus.com/inward/record.url?scp=85044918160&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044918160&partnerID=8YFLogxK

U2 - 10.1016/j.dsp.2018.03.015

DO - 10.1016/j.dsp.2018.03.015

M3 - Article

VL - 78

SP - 294

EP - 304

JO - Digital Signal Processing: A Review Journal

JF - Digital Signal Processing: A Review Journal

SN - 1051-2004

ER -