Abstract
Fitness classification is a technique to assess the quality of banknotes in order to determine whether they are usable. Banknote classification techniques are useful in preventing problems that arise from the circulation of substandard banknotes (such as recognition failures, or bill jams in automated teller machines (ATMs) or bank counting machines). By and large, fitness classification continues to be carried out by humans, and this can cause the problem of varying fitness classifications for the same bill by different evaluators, and requires a lot of time. To address these problems, this study proposes a fuzzy system-based method that can reduce the processing time needed for fitness classification, and can determine the fitness of banknotes through an objective, systematic method rather than subjective judgment. Our algorithm was an implementation to actual banknote counting machine. Based on the results of tests on 3856 banknotes in United States currency (USD), 3956 in Korean currency (KRW), and 2300 banknotes in Indian currency (INR) using visible light reflection (VR) and near-infrared light transmission (NIRT) imaging, the proposed method was found to yield higher accuracy than prevalent banknote fitness classification methods. Moreover, it was confirmed that the proposed algorithm can operate in real time, not only in a normal PC environment, but also in an embedded system environment of a banknote counting machine.
Highlights
Problems occur when banknotes used in such devices as automated teller machines (ATMs) and vending machines cannot be recognized due to higher-than-normal levels of soilage
To solve problems in prevalent technologies for banknote fitness classification, this study proposes a method that uses a fuzzy system to achieve accurate fitness classification results from visible light and infrared images using rules determined
The banknote area is detected such that the background is excluded from the captured banknote image, and regions of interest (ROI) within this area are selected from each visible light reflection (VR) image and near-infrared light transmission (NIRT) image according to denomination
Summary
Problems occur when banknotes used in such devices as automated teller machines (ATMs) and vending machines cannot be recognized due to higher-than-normal levels of soilage. This research involved a classification part, which used a three-layered perceptron, and a verification part, which used a radial-based function (RBF) network to reject partial unfit data He et al performed research that classified the fitness of Chinese (Renminbi (RMB)) banknotes using a neural network [7]. In this technique, the gray level histogram of the image of a banknote was used as an input feature, and the classifier was designed based on a neural network that used a sine basis function [7]. To solve problems in prevalent technologies for banknote fitness classification, this study proposes a method that uses a fuzzy system to achieve accurate fitness classification results from visible light and infrared images using rules determined. 2016, 16, 863 the results of experimental performance analyses of the algorithm, and Section 4 summarizes the of 18 conclusions of this study as well as plans for future research in the area
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
