FAKE CURRENCY DETECTION WITH MACHINE LEARNING ALGORITHM AND IMAGE PROCESSING

Abstract

The topic of determining if a particular sample of cash is counterfeit is addressed in this article. The 
indicated colours, width, and serial numbers are only a few of the classic techniques and approaches 
that may be used to identify counterfeit cash. Image processing has led to the proposal of several 
machine learning algorithms that provide 99.9 percent accuracy for the counterfeit cash in this era of 
improved computer science and high computational approaches. Colour, form, paper width, and 
picture filtering on the note are entities that may be detected and recognised using algorithms. This 
study presents a technique for detecting counterfeit money by using K-Nearest Neighbours in 
conjunction with image processing. The computer vision job is well-suited to KNN because of its 
excellent accuracy for tiny data sets. To ensure accurate data and information about the entities and 
properties associated with money, a banknote authentication dataset has been developed using 
advanced computational and mathematical techniques. In order to achieve the desired outcome with 
precision, data processing and extraction make use of machine learning algorithms in conjunction with 
image processing.