Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission Images
The fitness classification of a banknote is important as it assesses the quality of banknotes in automated banknote sorting facilities, such as counting or automated teller machines. The popular approaches are primarily based on image processing, with banknote images acquired by various sensors. How...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-09-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | http://www.mdpi.com/2073-8994/10/10/431 |
id |
doaj-4b372ab4f9d0465d9b31d51b9f91d2f9 |
---|---|
record_format |
Article |
spelling |
doaj-4b372ab4f9d0465d9b31d51b9f91d2f92020-11-25T00:16:17ZengMDPI AGSymmetry2073-89942018-09-01101043110.3390/sym10100431sym10100431Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission ImagesTuyen Danh Pham0Dat Tien Nguyen1Jin Kyu Kang2Kang Ryoung Park3Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, KoreaThe fitness classification of a banknote is important as it assesses the quality of banknotes in automated banknote sorting facilities, such as counting or automated teller machines. The popular approaches are primarily based on image processing, with banknote images acquired by various sensors. However, most of these methods assume that the currency type, denomination, and exposed direction of the banknote are known. In other words, not only is a pre-classification of the type of input banknote required, but in some cases, the type of currency is required to be manually selected. To address this problem, we propose a multinational banknote fitness-classification method that simultaneously determines the fitness level of a banknote from multiple countries. This is achieved without the pre-classification of input direction and denomination of the banknote, using visible-light reflection and infrared-light transmission images of banknotes, and a convolutional neural network. The experimental results on the combined banknote image database consisting of the Indian rupee and Korean won with three fitness levels, and the United States dollar with two fitness levels, show that the proposed method achieves better accuracy than other fitness classification methods.http://www.mdpi.com/2073-8994/10/10/431multinational banknote fitness classificationvisible-light reflection imageinfrared-light transmission imageconvolutional neural networkdeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tuyen Danh Pham Dat Tien Nguyen Jin Kyu Kang Kang Ryoung Park |
spellingShingle |
Tuyen Danh Pham Dat Tien Nguyen Jin Kyu Kang Kang Ryoung Park Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission Images Symmetry multinational banknote fitness classification visible-light reflection image infrared-light transmission image convolutional neural network deep learning |
author_facet |
Tuyen Danh Pham Dat Tien Nguyen Jin Kyu Kang Kang Ryoung Park |
author_sort |
Tuyen Danh Pham |
title |
Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission Images |
title_short |
Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission Images |
title_full |
Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission Images |
title_fullStr |
Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission Images |
title_full_unstemmed |
Deep Learning-Based Multinational Banknote Fitness Classification with a Combination of Visible-Light Reflection and Infrared-Light Transmission Images |
title_sort |
deep learning-based multinational banknote fitness classification with a combination of visible-light reflection and infrared-light transmission images |
publisher |
MDPI AG |
series |
Symmetry |
issn |
2073-8994 |
publishDate |
2018-09-01 |
description |
The fitness classification of a banknote is important as it assesses the quality of banknotes in automated banknote sorting facilities, such as counting or automated teller machines. The popular approaches are primarily based on image processing, with banknote images acquired by various sensors. However, most of these methods assume that the currency type, denomination, and exposed direction of the banknote are known. In other words, not only is a pre-classification of the type of input banknote required, but in some cases, the type of currency is required to be manually selected. To address this problem, we propose a multinational banknote fitness-classification method that simultaneously determines the fitness level of a banknote from multiple countries. This is achieved without the pre-classification of input direction and denomination of the banknote, using visible-light reflection and infrared-light transmission images of banknotes, and a convolutional neural network. The experimental results on the combined banknote image database consisting of the Indian rupee and Korean won with three fitness levels, and the United States dollar with two fitness levels, show that the proposed method achieves better accuracy than other fitness classification methods. |
topic |
multinational banknote fitness classification visible-light reflection image infrared-light transmission image convolutional neural network deep learning |
url |
http://www.mdpi.com/2073-8994/10/10/431 |
work_keys_str_mv |
AT tuyendanhpham deeplearningbasedmultinationalbanknotefitnessclassificationwithacombinationofvisiblelightreflectionandinfraredlighttransmissionimages AT dattiennguyen deeplearningbasedmultinationalbanknotefitnessclassificationwithacombinationofvisiblelightreflectionandinfraredlighttransmissionimages AT jinkyukang deeplearningbasedmultinationalbanknotefitnessclassificationwithacombinationofvisiblelightreflectionandinfraredlighttransmissionimages AT kangryoungpark deeplearningbasedmultinationalbanknotefitnessclassificationwithacombinationofvisiblelightreflectionandinfraredlighttransmissionimages |
_version_ |
1725383522333491200 |