Deep Learning-Based Fake-Banknote Detection for the Visually Impaired People Using Visible-Light Images Captured by Smartphone Cameras

Tuyen Danh Pham,Kang Ryoung Park,Chanhum Park,Ganbayar Batchuluun,Dat Tien Nguyen

doi:10.1109/access.2020.2984019

Tuyen Danh Pham, Kang Ryoung Park + Show 3 more

Open Access

https://doi.org/10.1109/access.2020.2984019

Copy DOI

Abstract

Automatic recognition of fake banknotes is an important task in practical banknote handling. Research on this task has mostly involved methods applied to automatic sorting machines with multiple imaging sensors or that use specialized sensors for capturing banknote images in various light wavelengths. These approaches can make use of the security features on banknotes for counterfeit detection. However, they require specialized devices, which are not always available for general users or visually impaired people. Meanwhile, smartphones are becoming more popular and can be useful imaging devices. Moreover, the types of fake banknotes created by imaging devices such as smartphone cameras or scanners are sometimes cannot be recognized by especially the visually impaired people. Addressing these problems, we propose a method for classifying fake and genuine banknotes using visible-light images captured by smartphone cameras based on convolutional neural networks. Experimental results on a self-collected dataset of US dollar, Euro, Korean won, and Jordanian dinar banknotes showed that our method performs better in terms of fake detection than the state-of-the-art methods.

Highlights

Electronic financial transactions are becoming more popular and the use of paper money has been decreasing recently, banknotes still remain in recirculation owing to their reliability and simplicity in usage
Smartphones with cameras are becoming more popular. Considering these issues, we proposed a fake banknote recognition method based on banknote images captured by smartphone cameras in visible-light conditions
Based on an analysis of the advantages and disadvantages of previous methods, we proposed a fake banknote classification method using convolutional neural network (CNN) on banknote images captured by smartphone cameras under visible-light conditions

Summary

Introduction

Electronic financial transactions are becoming more popular and the use of paper money has been decreasing recently, banknotes still remain in recirculation owing to their reliability and simplicity in usage. The problems of the automatic handling of banknotes are still relevant These tasks include the recognition of the banknote type and denomination, counterfeit detection, fitness classification, and serial number recognition, which are mostly conducted on automated transaction facilities, such as counting machines or vending machines, based on image processing techniques [1]. Among these tasks, counterfeit detection plays an important role in ensuring the security of. It is difficult for general users to check for counterfeit banknotes

Methods

Results

Conclusion