NATIONAL INSTITUTE OF TECHNOLOGY DELHI

(An autonomous institute under the aegis of Ministry of HRD Govt. of India)

Narela, Delhi 110040

Project Synopsis:

Fake Currency Detection using Image processing

Team:

Project Member:

Satyendra Kumar Maurya

151220010

ECE 4th Year

Contact:

9417428525

151220010@nitdelhi.ac.in

Project Supervisor:

Dr. Rajiv Tripathi

(Assistant Professor

Department of Electronics and Communication

NIT Delhi)

rajivtripathi@nitdelhi.ac.in
Introduction:
Due to advancement in technology specifically in colour printing technology,
the cases of fake currency generation has risen up. Currency notes are printed in
special print houses called mints authorized by govt. But today with the help of
laser printers these notes can be printed anywhere that too with very high
accuracy. As a result the circulation of fake currency in the market has
increased largely specially in developing countries like India. This leads to the
design of a technology for automated teller machines and automatic goods seller
machines which can automatically detect the currency whether it is fake or not
in a less time and more efficient manner. Many techniques have been proposed
but they does not work accurately if the note is old, dirty or torn. This project
describes an efficient approach to verify Indian currency by extraction of safety
features of the currency notes and analysing then using a proper algorithm.
MATLAB software is used for this method.

Aim:
The project aims at developing a technology for Indian currency notes so that
ATMs and vending machines can automatically detect for a counterfeit
currency. The method is designed by keeping in mind the safety features used
by RBI for Indian currency. The technology of currency recognition basically
aims for identifying and extracting the visible and invisible safety features of
Indian currency notes and analysing them with a simple algorithm which works
efficiently.

Motivation for the project:

Throughout history, currency issuers have faced one common threat, the threat
of counterfeiting. Despite the introduction of electronic currency, banknotes
remain in abundance. The amount of counterfeit currency in circulation at any
moment threatens the confidence in the currency. Confidence influences the
inherent value and stability of the currency. Banknotes hold higher value than
coins making them more susceptible to counterfeiting, and a. higher economical
risk. It is observed throughout history opponent societies have used counterfeit
currency production of their enemies currency as a weapon. The main
motivation behind development of this project was to make a system for easy
and quick detection of genuine and fake Indian currency notes. This is
a MATLAB based system for automatic recognition of security features of
Indian currency. The cost of the system is reasonable, considering its
helpfulness. This project makes use of an effective and efficient image
processing techniques and algorithms to provide accurate and reliable results.
The developed algorithm works for Indian denominations Rs 500, Rs 2000.

Methodology:
The methodology of this system is very simple but effective. The image of the
currency notes is acquired by using digital camera. The following algorithm is
adopted.

1. Acquisition of currency note using digital camera.

2. The image taken is of RGB type then converted to grayscale image.
3. Edge detection of whole image.
4. After that characteristic features of notes will be cropped and segmented.
5. After that characteristics features of notes is extracted.
6. Then intensity of each feature is calculated.
7. If the condition is satisfied then the note is original otherwise fake.

In this method, characteristics of currencies are employed which are used by

common people for differentiating for different banknote denomination. The
characteristics that can be used to check the authentication of currency note are:

A. Security Thread:
It is a 3mm windowed security thread with inscriptions of India in Hindi,
RBI and 2000/500 on banknotes with colour shift. Colour of the thread
changes from green to blue when the note is tilted.
B. Serial Number:
Serial number panel with banknote number growing from small to big on
the top left side and bottom right side.
C. Latent image:
A vertical band on front side of denomination at right hand size. It
contains latent image showing numeral of denomination when banknote
is held horizontally at eye level.
 D. Watermark:
The portrait of Mahatma Gandhi, and multidirectional lines and a mark
showing the denominational numeral appear which can be viewed when
held against light.
E. Identification Mark:
A mark with intaglio print which can be felt by touch, helps blind person
to identify the denomination. In 500 denomination the mark is of five
lines while in 2000 line the mark is of seven lines.

Flow Diagram of proposed method:

Image Grayscale Edge

Acquisition Conversion Detection

Caculation of Characteristics Image

Intensity Extraction Segmentation

Result

Fig: Flow diagram of method

 Start

Display the Intensity

Avg>70 NO

YES
Original Fake

Stop

Fig: Flow chart for decision making

Usefulness of the project:

The project will help in detecting counterfeit currency automatically and will
help in identifying and removing them from the circulation. Thus making the
currency notes more reliable and more trustworthy to use.

This will lead to decrease in fake currency in circulation which will help the
economy as these fake currency are used as weapons by terrorists and other
antisocial groups against a country for their evil desires.