COUNTERFEIT NOTES DETECTION

A Fake Currency Detection System

By Akshatha Ramesh, Amogh R, Darshan S and Nikhil Subramanya K

Fake currency is impersonation currency created without the lawful authorize of the state or government. Delivering or utilizing fake currency is a type of misrepresentation or fraud. In the course of recent years, because of the immense innovative advances in shading printing, copying and examining, falsifying issues have turned out to be increasingly genuine. Hence the issue of proficiently recognizing fake banknotes from honest to goodness ones by means of programmed Fake currency detection system has turned out to be increasingly vital. Fake currency detection system can be utilized as a part of spots, for example, shops, banks counter and computerized teller machine, auto merchant machines and so on. We have looked into changed fake currency detection systems. The systems are created utilizing diverse techniques and algorithms. The advantages of this examination for the peruser are that this investigation will give data about the distinctive strategies and algorithms utilized for fake currency detection system. They can look at the detection systems. Detection capacity relies upon the currency note characteristics of specific nation and extraction of highlights.

Final Approach: Using k-NN Algorithm, BFM Technique and Tkinter

Using Tkinter we created the web app which consists of 3 buttons i.e. Scan Currency, Start Scanning and Browse & Scan. When Scan Currency is clicked, we can face the currency note to the web cam and the note gets scanned and then start scan button is clicked. The Browse & scan button is used to input the image of currency notes present on the device and then check if the currency note is real or not.

Output 1

Output 2

Output 3

Output 4

Prerequisites

You should have Python3 installed in your system. To install other required libraries, run the following command in the terminal.

pip install -r re.txt

Front-end Approach 1: Development of Web App using Node.js

Node.js is an open-source, cross-platform, back-end JavaScript runtime environment that runs on the V8 engine and executes JavaScript code outside a web browser. Node.js lets developers use JavaScript to write command line tools and for server-side scripting—running scripts server-side to produce dynamic web page content before the page is sent to the user's web browser. The HTML code is used to display 3 buttons on the screen which is used to load image, scan image and upload image buttons. Then using java script, we tried connecting the Front End with the ML model.

Machine Learning Approach 1: FAST Algorithm

Features from Accelerated Segment Test(FAST) is a corner detection method, which could be used to extract feature points and later used to track and map objects in many computer vision tasks. We have tried to implement the FAST Algorithm for processing the features to find whether the scanned image of the currency note is original or not. Credits and Motivation