Real-Time Recognition of Series Seven New Zealand Banknotes

Real-Time Recognition of Series Seven New Zealand Banknotes

Yueqiu Ren (Department of Computer Science, Auckland University of Technology, Auckland, New Zealand), Minh Nguyen (Department of Computer Science, Auckland University of Technology, Auckland, New Zealand) and Wei Qi Yan (Department of Computer Science, Auckland University of Technology, Auckland, New Zealand)
Copyright: © 2018 |Pages: 16
DOI: 10.4018/IJDCF.2018070105

Abstract

This article proposes an effective method for real-time banknote recognition, using digital image processing. The new Series 7 New Zealand banknotes are considered, as a case study, for intelligent real-time recognition. The composite feature of a banknote containing the elements of color and texture is extracted, and a three-layer back-propagation neural network is trained for classification. The proposed method has demonstrated excellent recognition results in an indoor environment and is comparatively less time-consuming that makes it suitable for real-time applications. This article fills in the vacancy of real-time recognition of the newly released paper currency. Practically, our proposed approach can be served as the uppermost for the future development of the prototype assisting the blind or the visually impaired in recognizing the new series of New Zealand banknotes.
Article Preview

Introduction

Currency started serving as a medium for exchanging goods and services thousands of years ago to replace the ancient barter system where any objects could be swapped if two traders agreed (Maestro, 1993). Even nowadays, currency, as a measurement unit in pricing a transaction, still plays an indispensable role in modern society. The monetary form has been extended to cash including coins and banknotes, cashless money like bank cheques, and even electronic data representing currency in bank accounts. Banknotes can be traced back to the year 1023 when they officially appeared in China for the first time in history and were later introduced by American colonists for systematic use in the western world (Bender, 2006; Maestro, 1993). In spite of its long history, the worldwide market for banknote printing is still fairly confidential, which is typically justified as the intention of protecting the secure surroundings for the production of this unique product. The printing apparatus and the security inks, as well as the completely automated machinery for excellent accuracy of banknote examination or the highly secure shredding equipment for used notes are not familiar to the general public.

With little revelation of the techniques for the production of banknotes, nevertheless, there is an enormous amount of research starting to reveal the inside story of the banknote, especially in the field of banknote recognition. Nowadays, numerous paper currency recognition systems have been developed through secure analysis, and have had a wide range of applications, such as automated teller machines (ATMs), banknote sorting machines, self-service payment kiosks, and portable devices assisting the visually impaired with recognizing banknotes. Banknotes recognition refers to the process of identifying the value of a banknote particularly when single currency is to be studied (Vishnu & Omman, 2014). In essence, it is the process of classifying the banknote to one of the classes it belongs to (Sargano, Sarfraz, & Haq, 2014). Unlike coins minted by heavy metals, almost all the banknotes worldwide are produced to be as thin as ordinary paper (Tarnoff, 2011). If weighing coins could be a straightforward way to distinguish different denominations of coins, then apparently, weighing banknotes is not a feasible way to distinguish different denominations of banknotes, due to the intrinsic lightweight property of their raw material. The newly released Series 7 New Zealand banknotes are a typical example. They are printed on paper polymer, which is a type of polypropylene plastic, enabling them to be lightweight (Langwasser, 2014).

After reviewing the literature about banknote recognition, it appears that there is little research on New Zealand banknote recognition, and no system found or method implemented or proposed for the newly released Series 7 New Zealand banknotes. Thus, the main purpose of this article is to seek out a forensic-based solution for recognizing the new Series 7 New Zealand banknotes, or more specifically, banknote denomination recognition.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2019): Forthcoming, Available for Pre-Order
Volume 10: 4 Issues (2018): 3 Released, 1 Forthcoming
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing