Published by : International Journal of Engineering Research & Technology (IJERT)

http://www.ijert.org ISSN: 2278-0181

Vol. 6 Issue 11, November - 2017

Automatic Indian New Fake Currency Detection

Technique
Mayadevi A.Gaikwad Vaijinath V. Bhosle
Computer Science, Computer Science,
College of Computer Science & Information Technology College of Computer Science & Information Technology
(COCSIT), (COCSIT),
Latur, Maharashtra, India, Latur, Maharashtra, India,

Vaibhav D Patil
Computer Science,
College Of Computer Science & Information Technology (COCSIT),
Latur, Maharashtra, India,

Abstract - In India,’ currency’ is the means of Transaction so Fake currency detection means finding the fake currency
there is more value for currency in our social and economic from the original one. Generally, currency recognition
development. Here, currency exists in the form of coins, system is mostly used in banks, business firms, shopping
banknotes and electronic data. Fake money or counterfeit malls, railway stations, government sector, organizations
notes is the dangerous or acute problem in front of whole etc.[1] But common people do not have any source of
world, and India is also a part of this fake currency. currency detection and they are unable to identify the real
Modernization in the financial system is a milestone in
original currency. That’s why the malpractice of fake
protecting the economic development and now a days Indian
government has become conscious about this so demonetization currency is carried out openly in our economy. [2]
of Rs 1000 and Rs 500 notes is the latest example of it. But Till date, many researchers have given their contribution in
again we have Rs 2000 as a new currency in market. so as the finding the technique of identifying the genuine currency
highest value note there is a chance that corrupt people will try
to make it as a counterfeit. So main objective of this paper is to
notes from the fake notes.
study different key features of new genuine currency and use II. LITERATURE SURVEY
such techniques to detect and verify new currency circulated In 2014, Binod Prasad Yadav, C. S. Patil, R. R. Karhe, P.H
by Reserve Bank Of India. There are Different techniques
Patil [3] presented Detecting fake currency manually it is
which are used to distinguish between counterfeit notes and
genuine one. By using different components of Digital Image
very default or time-consuming. This process is check by
processing such as image processing, image segmentation, using some technique it is batter to human life that is done
characteristics extraction, comparing images etc. we can by using fature extraction with HSV is nice technique to
extract the features of genuine notes. It is a very challenging detect fake currency with his opinion. This process is done
task for detecting fake currency. by using MATLAB.
General Terms - Image Processing, feature extraction, B.Sai Prasanthi , D.Rajesh Setty[4] Automated detecting
detection. fake currency system can be very help full to banking or
Keywords - Segmenting feature of currency, canny, financial other business so many author work on this technology as
system , genuine note. per his opinion fake currency detection is very important
task in human life. India is also one of them. In this article,
I. INTRODUCTION recognition of paper currency with the help of digital image
Economic development of every nation is mostly dependent processing techniques is described. Six characteristics of
on its currency and every person is the part of Economy but Indian paper currency are selected for counterfeit detection
some of the unsocial group of people damage this process included identification mark, security thread, watermark,
and unbalances the social harmony of the nation. For ex. numeral watermark, floral design and micro-lettering. The
Now a days, in process of demonetization, there are long characteristic feature extraction is performed on the image
queues in front of banks and ATM Machines of those of the currency and it is compared with the characteristic
common people who contribute to our economy by paying features of the genuine currency. The decision making is
taxes but on the other hand many corrupted people are done by calculating the black pixels. This article is aimed to
issuing the money directly by evil sources and it is directly design a low cost system and quick decision making system.
effecting on economic status of India. In 2015 Kevya B R, Devendran B [5] they are designing a
As we know, in India, Ministry Of Finance and system that helps in identification of Indian currency notes
RBI(Reserve Bank Of India are authorized to issue currency and to check whether it is a valid or invalid. This is to
notes and coins. But corrupt people take the advantage of differentiate between the counterfeit notes and genuine
high printing and scanning technologies to print fake notes notes. Currency features such as See Througth register, See
by using latest hardware tools and techniques. Through register symbol or Identification mark, Security

IJERTV6IS110028 www.ijert.org 84
(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 6 Issue 11, November - 2017

thread, Governer's signature, Microlettering, year of print. B Front –side features. (These are the obverse features)
This features are segmented using 3x3 grid. This is done by
the use of SIFT technique which helps in efficient matching
of the features.
In 2016 W. K. El Said [6] they Recently, due to the
development in computer software, laser printers and
scanners, counterfeiting has become an urgent issue. As a
result, distinguishing fake currency from genuine one using
new technologies has become more important. This research
paper presents a new feature extraction based system for
detecting the fake Egyptian paper currency. The process of
extracting features is separately performed on both sides of
the original and the sample version of the currency image.
The obtained features are divided into two parts namely;
texture features and shape features. The currency detection
decision for each side is independently acquired by
similarity measurement. Simulation results show that the
Rs 500 denomination bank notes are released in new series
proposed system can be used effectively in financial
with inset letter ‘E’ in both the number panels and it also has
organizations and various commercial applications.
the image of Mahatma Gandhi and signature of Governor
In 2015, Komal Vora, Ami Shah, Jay Mehta [7] they Dr. Urjit R.Patel.
presented The entire system is pre-processed for the optimal
First of all we will discuss the features of Rs 500 notes.
and efficient implementation of two dimensional discrete
wavelet transform (2D DWT) which is used to develop a Color
currency recognition system. A set of coefficient statistical The color of Rs 500 note is stone gray.
moments are then extracted from the approximate efficient
Size
matrix. The extracted features can be used for recognition,
classification and retrieval of currency notes. The The new Rs 500 note is smaller than previous note (size of
classification result will facilitate the recognition of fake at 63mm x 150 mm ).
currency mainly using serial number extraction by
implementing OCR. It is found that the proposed method
gives superior results. Bleed lines
There are seven “bleed lines” on the side of Rs.2000 notes,
III. PROPOSED DESIGN and five lines on Rs 500 notes.
A Flow of fake Currency detection technique
Latent image
Input Image Scanned Device In Rs 500 note there is latent image of the denomination in
RGB numeral.
Denomination numeral in devnagari font.

Convert into Devnagari font is also used on the currency of Rs.500.

Gray Scale Orientation
In previous notes of Rs 500 and current notes there are some
changes in orientation and relative position of Mahatma
Extract Feature Gandhi..
Windowed security thread
Rs.500 notes contain a readable, fully embedded windowed
Identification Match Feature security thread with the inscription “Bharat‟ (in Hindi), and
with Template “RBI‟. Which changes color from green to blue when note
is tilted. Guarantee clause, Governor’s signature with
promise clause and RBI emblem shifted towards right.
Fake Currency is
Portrait
Detected or not
The portrait has been changed in raised manner. The
For example ,we have new Rs 500 and Rs 2000 notes.We orientation and the portrait of Mahatma Gandhi has been
will discuss their feature one by one . changed and we can see the electrotype watermark also.
First image is of Rs500..
Second image is of Rs 2000.

IJERTV6IS110028 www.ijert.org 85
(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 6 Issue 11, November - 2017

Numerals Windowed security thread

In new currency notes numerals are mentioned in the There are three names that are present on the security thread
increasing order of their size from top-left side to bottom- i.e Bharat, RBI and 2000 printed in raised manner with shift
right side. in their colors when held at different angles . Because of this
special feature visually challenged people can easily identify
Ashoka pillar emblem
the notes.
On the right side Ashoka pillar emblem is present. Number panel
Special Features of New Currency Number panel with numerals growing from small to big on
top left and bottom right sides
1. Swachh Bharat slogan with logo.
These are the front side features, now let’s discuss about the
2.At the center there is a language panel. reverse side features.
3.Red fort with Indian tri-color(flag)
Reverse side features
4.At the right side denomination numeral in Devnagri 1) ‘Swachh Bharat logo with slogan ‘ –
Swachh bharat logo is placed on spectacle with
C key features of Rs 2000 notes. slogan “Ek kadam swachhta ki aur” it is the part of
Narendra modi’s “Swachh Bharat Abhiyaan”.

2) The Symbol of Mangalyan-

We have a new feature in this new note that is the
symbol of Mangalyan. It was a rumor in people’s
mind that GPS chip is embedded in this new
currency that can easily find the location of notes.
But GPS chip is not inserted in it. It is the part of
Mar’s mission of India and after that India got
place in interplanetary domain.
3) Orientation of Mahatma Gandhi
Orientation and size of portrait of Gandhiji has
been changed and placed in raised manner.
4) number panel
Due to no of complaints about “counterfeit notes of Rs.2000 In the current note Top left and bottom right side
denomination, common people are worried about its number panel with numerals is there ,which is
circulation.. There are different key features of genuine increasing from smaller to bigger form.
notes. The touch and appearance of it makes it different .It
has geometric patterns aligning with the overall color IV. METHODOLOGY
scheme, both of the obverse and reverse side. Image processing based currency recognition technique
consists of few basic steps like image acquisition, its pre-
Color processing and finally recognition of the currency.
New banknotes of Rs 2000 are color changing notes. Paper
color is magenta. Image processing generally involves three steps:
Size
1. Import an image with an optical scanner or directly
The size of this note is 66mm x 166 mm. through digital photography.
See through register- 2. Manipulate or analyses the image in some way.
In old notes the denomination’s numeral was written in the 3. Output the result. The result might be the image altered in
middle or at the Centre. Whereas in the new currency note it some way or it might be a report based on analysis of the
is mentioned on the left hand side image. The Flowchart of the steps involved in methodology
Latent image is as follows:
On the obverse side of Rs. 2000 and Rs. 500, when the note Fig-1:Flow-chart of methodology
is tilted at 45 degree , latent image of denominational value Image Acquisition (Input Image)
in numerical manner is displayed. When we hold the note In this process first input the image by using optical scanner
at an angel of 450 or When note is held against light the or directly photography. We can read the image by using
numeral 2,000 can be seen very clearly and Color is changed different source it is software based or hardware based
from green to blue. source. When we perform the operation on any verification
Watermarks we should go with image processing technology. Without
We can see the watermark of Mahatma Gandhi and 2,000 image we cannot perform any operation. Extraction and
numeral in the new currency note. .The portrait of Mahatma detection is very important part in any verification.
Gandhiji is displayed in raised manner as compared to the
previous currency notes.

IJERTV6IS110028 www.ijert.org 86
(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 6 Issue 11, November - 2017

Image pre-processing:- V. IMAGE DATABASE

Image pre- processing is used to extract the feature from This paper will generate its own data base that is related
images and perform different operation for any document to new currency of Indian economy.
verification.
Image adjusting:- VI. CONCLUSION
When we produce the image by scanner or any digital At present we are having Rs 2000 as the highest value
devices the image size is so bigger but when we perform currency in India so in upcoming years there is a chance of
operation on image we should reduce the size of image then scamp and duplication of new currency. So we have to
we perform the different operation on image. And this task develop such a module, which can automatically detect the
is perform by using adjust function in MATLAB. It is better original currency and easily we can differentiate between
software to perform the operation on image. counterfeit notes and genuine notes.
Image smoothening:- VII. REFERENCES
In this process we can capture the image by using digital [1] Sagar S. Lawade, Gayatri S. Hedau, Apurva C. Ramgirwar “FAKE
camera or scan the image by using scanner, and then some CURRENCY DETECTION USING IMAGE PROCESSING” in
Proceedings of International Journal of Research In Science &
noise will appear on the image. Firstly we should have to Engineering e-ISSN: 2394-8299 Volume: 1 Special Issue:1
remove that noise. It is very important task for feature p-ISSN: 2394-
extraction and detection in the image processing technology. [2] Mohammad H Alshayeji*, Mohammad Al-Rousan and Dunya T.
Hassoun “Detection Method for Counterfeit Currency Based on Bit-
iii) Median filter:- Plane Slicing Technique” International Journal of Multimedia and
When we process the image we should apply some filtering Ubiquitous Engineering Vol.10, No.11 (2015), pp.225-242
[3] 8280Binod Prasad Yadav, C. S. Patil, R. R. Karhe, P.H Patil, “An
technique. To filter the image so may author is used automatic recognition of fake Indian paper currency note using
different technique to filter the image for the operation. MATLAB” in Proceedings of International Journal of Engineering
Science and Innovative Technology (IJESIT) Volume 3, Issue 4,
Image Binarization July 2014
Document image binarization is usually performed in the [4] B.Sai Prasanthi , D.Rajesh Setty, “Indian Paper Currency
pre-processing stage of different document image Authentication System- A Quick Authentication System”
International Journal of Scientific & Engineering Research, Volume
processing related applications such as optical character 6, Issue 9, September-2015
recognition (OCR) and document image retrieval. A gray- 1249 ISSN 2229-5518
scale document image is converted into a binary document [5] Kavya B R, Devendran B, “INDIAN CURRENCY DETECTION
image and accordingly it facilitates the ensuing tasks such as AND DENOMINATION USING SIFT” International Journal of
Science, Engineering and Technology Research (IJSETR), Volume 4,
document skew estimation and document layout analysis. Issue 6, June 2015
As more and more text documents are scanned, fast and [6] W. K. ElSaid, “Fake Egyptian Currency Detection System using
accurate document image binarization is becoming Texture and Shape Characteristics” International Journal of Computer
increasingly important. Applications (0975 – 8887) Volume 143 – No.2, June 2016.
[7] Komal Vora, Ami Shah, Jay Mehta “A Review Paper on Currency
Image Segmentation Recognition System” in Proceedings of International Journal of
It determines region boundaries in an image. It can explore Computer Applications (0975 – 8887) Volume 115 – No. 20, April
2015.
many different approches to an image sengmentation &
thresholding. Optimal Global Thresholding:
A threshold is said to be globally optimal if the number of
misclassified pixels is minimum
Histogram is bimodal (object and background)
Ground truth is known OR the histograms of the object and
the background are known
Feature Extraction
It is a challenging work in digital image processing. In any
currency recognition system, feature extraction is one of the
most challenging tasks. Here, the aim is to analysis and
identify the unique and distinguishing features of each
denomination under various challenging conditions such as
old notes, worn out notes, also under different illumination
and background. Some of the features of Indian paper
currency are stated as below:- Identification marks[3]:

IJERTV6IS110028 www.ijert.org 87
(This work is licensed under a Creative Commons Attribution 4.0 International License.)