International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056

Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072

Currency Recognition System Using Image Processing

Prof. Sagar S.Rajebhosale, Devang S.Gujarathi, Sushil V.Nikam, Prathmesh P.Gogte,

Nilesh M.Bahiram

Guided By Prof. S.S Rajebhosale, Dept. Information Technology, Pune Vidyarthi Grihas College of Engineering,
Nasik, Maharashtra, India

---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The Reserve Bank is the one which issue bank technique named optical, mechanical and electronic
notes in India. Reserve Bank, changes the design of bank notes integration, integrated with calculation, pattern
from time to time. Reserve bank uses several techniques to recognition(high speed image processing). It is accurate and
detect fake currency. Common people faces many problems for highly-efficient. But for most staffs,they have to keep a lot of
the fake currency circulation and also difficult to detect fake different features and anti-fakes label for different
currency, suppose that a common people went to a bank to commonly-used currency in their mind.
deposit money in bank but only to see that some of the notes
are fake, in this case he has to take the blame. As banks will 1.1 Relevance
not help that person. Some of the effects that fake currency has
on society include a reduction in the value of real money; and The relevance of a project shows how efficient the output of
inflation due to more fake currency getting circulated in the the project which is to be specified by the evaluation or by
society or market which disturbs our economy and growth - an using the project which were being submitted. That means
some illegal authorities an artificial increase in the money the relevance of a project is always to be related to some goal
supply,a decrease in the acceptability of paper money and and , for general research projects, such goal is mostly
losses. Our aim is to help common man to recognize currency increase of our scientific knowledge, although it is
for originality. Proposed system is based on image processing sometimes also related to more direct social environmental
and makes the process automatic and robust. Shape benefits for our society. In this proposed system, our
information are used in our algorithm. Original Note relevance is to focus on detection of fake currencies which is
Detection Systems are present in banks but are very costly. We spreaded in Indian market also our main goal is to use image
are developing an image processing algorithm which will processing technique and recognize original
extract the currency features and compare it with features of currency[1].Relevance of our project is similar to currency
original note image. This system is cheaper and can provide recognition system using neural networks . That paper
accuracy on the basics of visual contents of note. So, as an identifies, and extracts robust features from banknotes. Now
output, people will get information provided the note image is a days many ways are found for currency recognition also
original or duplicate. most of the people manually recognizes currency which is
sometimes mistakenly not recognize by some people to build
Key Words: Currency detection, Fake currency, a system so the system can recognize all kind of currencies
Image processing, Template matching, Counterfeit which is useful to common man[4].
note.
1.2 System Background
1.INTRODUCTION
The proposed web portal will help common people for
There are 50 currencies all over the world, with each of them currency recognition anywhere anytime. Automatic method
looking totally different. For e.g. the size of the paper may for detection of fake currency note is very important in every
vary, and also color and pattern may different. People have country. In this approach system extract the general
to remember the features of each currency. This may cause attributes of the paper currency like various dominant parts
some problems (e.g.wrong recognition), so people need an of image of currency note (like identification marks, latent
efficient and exact system to help their work. The aim of our image, etc). [6] The identification marks helps to know the
proposed system is to help people who need to recognize denomination of currency. These marks of currency helps to
their currency, and work with convenience and efficiency. detect fake or genuine. The system will be developed to
For bank staffs, there is a Currency Sorting Machine which is check different currency notes of 100, 500 and 1000 rupees.
an electronic device which helps them to recognize The Web Application will display currency denomination
currencies. The main working processes of Currency Sorting and either currency is genuine or fake. The system simply
Machine are image acquisition and recognitions. It has an extracts feature of currency which were match with original
currency features and immediately displays result with
2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 2559
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072

accuracy. The features which were considered for currency 4. SYSTEM ARCHITECTURE
recognition are as follows :

Latent image
Currency Value Area (100,500 & old 1000)
Intaglio printing
Identification mark
See through register
Satyamev Jayate logo at left corner
Reserve Bank of India at top of currency note
Reserve Bank of India logo at right corner

2. LITERATURE SURVEY

Main purpose of the system is to provide fake currency

detection facility. There are lots of machines are available 4.1 SYSTEM DESCRIPTION
that helps the people to recognize different features of
currencies. But for most working staffs in money exchange Input(Image Acquisition) : A digital camera or
have to keep a lot of different features and anti-fakes label scanner or phone is used for image preprocessing.
for different commonly-used currencies. However, everyone The starting step of the paper currency recognition
has a handbook that about the features and anti-fakes labels system would be image segmentation that means
of come commonly-used currencies. No one can ever be 100 separating the note image from the background.
percent confident about the manual recognition. So, our
purpose is to detect currency with accurate results without Browsing : Proposed System browse these images
any interference also our proposed system will save time to file in the system and these image will be given for
recognize currency by detecting fake currency in less time feature segmentation and template matching.
[3].
Image processing : - It is method to convert an
Existing systems uses optoelectronic device to produce the image into digital form and perform some
signal from the light refracted by the banknote. There are operations on picture or image, in order to
many currency recognition machines are available in current obtaining an enhanced image or to extract some
market through which currency can be recognize whether by useful information from image or picture. Here, We
using image processing technique or neural networks[3]. use Template matching for finding small parts of
Existing currency recognition systems are mainly based on image.
processing of image using image processing techniques and
neural networks. Some system uses Gaussian function in Template matching : - It is a technique in digital
hidden layer and output layer of NN in the place of sigmoid image processing for finding small parts of an
function. System shown that the Gaussian function is more image which match a template image. It can be
effective than sigmoid function for the recognition of known used in manufacturing as a part of quality control, a
features and rejection of unknown patterns [5]. way to navigate a mobile robot, or as a way to
detect edges in images.
3.OBJECTIVES OF APPLICATION
Finally, we get output which shows the whether
To identify original currency note using Image currency is Original or Duplicate. After applying
processing techniques. Template matching Algorithm, so person can know
System compare images of currency note to the whether note is real or fake.
stored images of original currency note images.
To provide Cheaper and Accurate system to the user
which can easily accessible and gives accurate
recognition of currency notes.
To develop user friendly web application of
currency recognition system.
To make available to common people quickly
and easily so they can utilize anywhere and at
any time.

2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 2560
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072

5.RESULT REFERENCES

[1] Rubeena Mirza,Vinti Nanda,Paper Currency

verification System Based On characteristic
Extraction Using Image Processing, IJEAT,
Vol.1,Issue 03, pp.68-71, February 2012.
[2] Sanjana, Manoj Diwakar, Anand Sharma, "An
Automated recognition of Fake or Destroyed Indian
currency notes in Machine vision", IJC-SMS, Vol. 12,
Issue 02, pp. 53-60, April 2012.
[3] R. Bhavani, A. Karthikeyan, A Novel Method for
Counterfeit Banknote Detection, IJCSE, Vol.2, Issue 4,
pp 165-167, April 2014.
[4] Harish Agarwal, Padam Kumar, Indian Currency Note
Denomination Recognition in Color Image, Int.
Journal on Advanced Computer Eng. And
Communication Tech.Vol.1.
[5] A.Ms.Trupti Pathrabe and B.Dr. N.G.Bawane, Paper
Currency Recognition System Using Characteristics
Fig. Uploading Image Extraction and Negativity Correlated NN
Ensemble,2010, Int. Journal of Latest Trends in
Computing.
[6] Vipin Kumar Jain, Dr. Ritu Vijay, Indian Currency
Denomination Identification Using Image Processing
Technique IJCSIT, Vol.4, issue 1,pp.126-128, January
2013.

Fig.2 Template Matching

3. CONCLUSIONS

In this technique, the authentication of currency is described

by applying image processing. Basically some features are
extracted including various domination parts of note (like
identification marks of the currency).The features are
extracted using image based segmentation using template
matching and works well in the whole process with less
computation time.
The complete methodology works for 100, 500 and 1000
currency notes. The method is very simple and easy to
implement. This technique is very adaptive to implement in
real time world. The process begins from image acquisition
and end at comparison of features. This project will be
helpful to those people who dont have any knowledge about
currency , so basically this project will be developed by
taking common man issues of currency related problem.

2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 2561