Original vs Counterfeit Indian Currency Detection

Submitted in partial fulfillment of the requirements

For the degree of

Bachelor of Engineering
in
Information Technology
by

Anushka Kulkarni Roll No. 16IT2008

Prachi Kedar Roll No. 16IT1068
Aishwarya Pupala Roll No. 16IT2013

Supervisor

Ms. Priyanka Shingane

Department of Information Technology

Dr. D. Y. Patil Group’s

Ramrao Adik Institute Of Technology

Dr. D. Y. Patil Vidyanagar, Sector 7, Nerul, Navi Mumbai 400706.
(Affiliated to University of Mumbai)

October 2019
Ramrao Adik Institute of Technology
(Affiliated to the University of Mumbai)
Dr. D. Y. Patil Vidyanagar,Sector 7, Nerul, Navi Mumbai 400706.

CERTIFICATE
This is to certify that, the Project-A titled

“Original vs Counterfeit Indian Currency Detection”

is a bonafide work done by

Anushka Kulkarni Roll No. 16IT2008

Prachi Kedar Roll No. 16IT1068
Aishwarya Pupala Roll No. 16IT2013

and is submitted in the partial fulfillment of the requirement for the

degree of

Bachelor of Engineering
in
Information Technology
to the
University of Mumbai

Supervisor
Ms. Priyanka Shingane

Project Co-ordinator Head of Department Principal

(Ms. Reshma Gulwani) (Dr. Ashish Jadhav) (Dr. Mukesh D. Patil)
 Project Report Approval For B.E.

This is to certify that the project entitled ”Original vs Counterfeit Indian Currency Detec-
tion” is a bonafide work done by Anushka Kulkarni,Prachi Kedar and Aishwarya Pupala under
the supervision of Ms. Priyanka Shingane. This project has been approved for the award of
Bachelor’s Degree in Information Technology, University of Mumbai.

Examiners :
1.
2.

Supervisors :
1.
2.

Principal :

Date :
Place :
 Declaration

I declare that this written submission represents my ideas in my own words and
where other’s ideas or words have been included, I have adequately cited and ref-
erenced the original sources. I also declare that I have adhered to all principles of
academic honesty and integrity and have not misrepresented or fabricated or falsi-
fied any idea/data/fact/source in my submission. I understand that any violation of
the above will be cause for disciplinary action by the Institute and can also evoke
penal action from the sources which have thus not been properly cited or from
whom proper permission has not been taken when needed.

Anushka Kulkarni Roll No. 16IT2008

Prachi Kedar Roll No. 16IT1068

Aishwarya Pupala Roll No. 16IT2013

Date :../../....
Abstract

Currency is used to carry out not only business but also for various other transactions to get
access to various services and commodities. There are a total of 7 denominations for the
Indian currency each with unique features to distinguish them from each other and with various
and distinct security features to prevent them from fraudulent copying. However, with the
evolution of technology, there is also an increase in the ways in which fake forms of these
currencies are created. These fake or counterfeit notes have various ill-effect on society. The
proposed system will be used to check the genuine Indian currency notes. Comparative study
for various image processing algorithms was conducted to identify and select the one which
will be able to extract more prominent features, and is also better in terms of processing time,
outlier rejection, efficiency in computation and in feature matching. On the basis of this study
an image processing algorithm is used in a real time system to detect the currency denomination
and to classify the fake currency from real one.

i
Contents

Abstract i

List of Figures iv

List of Tables v

1 Introduction 1
1.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.3 Scope of project . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.4 Relevance and Motivation of Project . . . . . . . . . . . . . . . . . . . . . . . 2
1.5 Organization of the report . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

2 Review of Literature 4

3 Planning and Formulation 6

3.1 Understanding Different Algorithms . . . . . . . . . . . . . . . . . . . . . . . 6
3.2 Feature Matching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.2.1 Brute Force Matcher . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.2.2 FLANN based Matcher . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.3 Limitations of Existing System . . . . . . . . . . . . . . . . . . . . . . . . . . 11

4 Methodology 12
4.1 Proposed System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12

ii
 Original vs Counterfeit Indian Currency Detection

4.2 Proposed Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

4.3 System Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

5 Design of System 15
5.1 System Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
5.2 Data Flow Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

6 Experimental Results and Performance Analysis 17

6.1 Practical Implementation and Analysis of Algorithms . . . . . . . . . . . . . . 17
6.2 Implementation of Real time System . . . . . . . . . . . . . . . . . . . . . . . 20

7 Testing 22

8 Conclusion and Future Scope 23

References 24

Acknowledgement 26

Ramrao Adik Institute of Technology iii

List of Figures

5.1 Real Time Proposed System . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

6.1 SIFT with non crumpled currency . . . . . . . . . . . . . . . . . . . . . . . . 18

6.2 SIFT with crumpled currency . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
6.3 ORB in good lighting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
6.4 Home Page . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
6.5 Real Note Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
6.6 Fake Note Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

iv
List of Tables

3.1 Analysis of Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

3.2 Time Comparison of Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . 9

v
Chapter 1

Introduction

1.1 Introduction
The evolution of technology, has lead to an increase in the ways in which fake forms of cur-
rencies are created and thus the counterfeit currency notes in the Indian market have increased.
These fake or counterfeit notes have various ill-effect on society. They harm the lay man as
there is no definitive way to be absolutely sure if the currency is original or fake.
This report focuses on the comparison and analysis of different image processing algorithms
to find the most efficient algorithm to identify and classify real and counterfeit currency notes.
The comparative study for various image processing algorithms was conducted to identify and
select the one which will be able to extract more prominent features, and is also better in
terms of processing time, outlier rejection, efficiency in computation and in feature matching.
The chosen image processing algorithm can be used to classify the fake currency from real one.

1.2 Problem Definition

With the rapid advancement of technology, there is also an increase in the production of coun-
terfeit currencies, which is also making it difficult to distinguish between the real and the fake
ones. The proposed system will be able to recognize the currencies and classify them as real

1
 Original vs Counterfeit Indian Currency Detection

or fake. In this approach, we will classify the fake notes using an image processing algorithm.
First, we will perform a comparative study of different image processing algorithms, and then
these algorithms will be implemented in the Matlab software. Based on the studies and com-
parison, the best algorithm for feature extraction and feature matching will be selected that
extracts the maximum number of feature points, and will also perform well under different
lighting conditions, and with different scaling and rotations.
After this point the chosen algorithm will be used to create a real time system to detect the
denomination of currency and to check whether the currency is real or fake.

1.3 Scope of project

• To perform a comparative study of different image processing algorithms such as SIFT
,SURF, BRISK, KAZE, ORB.

• To select the optimal algorithm in terms of accuracy, feature matching points, outlier
rejection, scale invariance, and computational cost.

• To create a database of images that will have currencies of all required denominations in
different lighting conditions and with different viewpoints or inclinations

• To select appropriate methodology to classify the currency as original or fake based on

various security features

• To create a real time system to classify currency note as genuine and fake.

1.4 Relevance and Motivation of Project

Currently the major methods used for the classification of currency notes be it Indian or any
other are either neural networks or image processing or a mixture of both.
Different papers have taken various different approaches to do this task and each of these exist-
ing system give us a perspective into the challenges of detecting currency as real or fake. The

Ramrao Adik Institute of Technology 2

 Original vs Counterfeit Indian Currency Detection

many image processing algorithms that have been used each have their merits and demerits but
most are found lacking in terms of it being transformed into a real time application. Most pa-
pers don’t take into account the computational costs or the different processing times of these
algorithms
In our paper we have analysed each of these in more detail so that we may achieve an optimal
process for a real time application to do the task of identification and detection.

1.5 Organization of the report

In this paper we focus on the comparison of the different image processing algorithms, their
features and capabilities to analyse and judge which of them would be the most efficient in
terms of working in a real time environment.
While judging the efficiency of algorithms we take into account their accuracy, computational
cost, feature matching speed, scale invarience and total image matching time.It also analyses
the feasibility of the deployment of the image processing algorithm in a real time environment.
This report focuses on finding the most optimal process for the task of identification of real and
counterfeit currency.And on creating a real time working system for the same.

Ramrao Adik Institute of Technology 3

Chapter 2

Review of Literature

Currently the major methods used for the classification of currency notes be it Indian or any
other are either neural networks or image processing or a mixture of both. Different papers
have taken various different approaches to do this task and each of these existing system give
us a perspective into the challenges of detecting currency as real or fake.
The many image processing algorithms that have been used each have their merits and demer-
its and in our paper we have analysed each of these in more detail so that we may achieve an
optimal process for a real time application to do the task of identification and detection. The
following papers were referred to get background on the system requirements.
The Paper Indian Banknote Recognition using Convolutional Neural Network Shubham Mit-
tal ,Shiva Mittal[1] took a Deep learning based approach for the purpose of identification of
denominations of Indian currency. And while that method worked efficiently in real time it
is to be considered that the Convolutional neural networks used are computationally expen-
sive. Neural Networks require huge amount of training data to train deep learning model from
scratch.
The paper Neural Network Approach for Indian Currency Recognition by Jayant kumar Nayak,
Chaitan Majhi , Apurva Kumar Srivastav, Ajaya Kumar Das - 2015[4] uses Neural networks to
recognize and then count currency notes of different denominations in a bundle for a ROI(Region
of interest). This paper had a drawback that Counterfeit currency detection was not incorpo-
rated.
Identification of Fake Notes and Denomination Recognition a paper by Archana M , Kalpitha

4
 Original vs Counterfeit Indian Currency Detection

C, Prajwal S ,Pratiksha N.[6] explained how notes could be classified based on color ,dimension
and identification marks (mentioned by RBI) using computer vision.However it had certain de-
merits like Lots of pre-processing steps involved and No portable application for smartphones.
Hence each of these papers offer us an insight on the varying approaches and challenges.

Ramrao Adik Institute of Technology 5

Chapter 3

Planning and Formulation

The many image processing algorithms that have been used each have their merits and demerits
but most are found lacking in terms of it being transformed into a real time application.
Most papers don’t take into account the computational costs or the different processing times
of these algorithms. So we have analysed each of these in more detail so that we may achieve
an optimal process for a real time application to do the task of identification and detection

3.1 Understanding Different Algorithms

The major algorithms analysed in our paper are SIFT,SURF,ORB,FAST,BRISK and KAZE.
It is important to understand the basics of the above mentioned algorithms. We need to analyse
these algorithms on the basis of their capabilities in terms of performance, timing, accuracy,
computational cost, scale invarience, outlier rejection and feature matching time.
Listed below are the algorithms studied in this paper.

• SIFT - SIFT stands for Scale Invarient Feature Transform and it is one of the most fore-
most image processing algorithms introduced in the year 1999.
In the SIFT algorithm various points are detected and matched using the Eucledian dis-
tance In SIFT method an image is transformed into a number of feature points. All these

6
 Original vs Counterfeit Indian Currency Detection

points are unvarying to image rotation and scale. Also Key point locations are appropri-
ated as maxima and minima.

• SURF - Speeded up Robust Features or the SURF in an algorithm present in computer

vision that has numerous applications such as recognition, tracking, reconstruction, iden-
tification and extraction of feature points.
It uses a pyramid structure technique to change the image or video capture into a coordi-
nates. It is known for its speed and is quite fast when compared to its alternatives.

• ORB - Oriented FAST and rotated BRIEF (ORB) was introduced in 2011 by Ethan
Rublee. It is an effective algorithm for the process of image processing and also ob-
ject detection.
As the name suggests it is a fusion of the two other algorithms mentioned here. These
are the FAST algorithm and the BRIEF algorithm.

• FAST - Published in the year 2006 by Edward Rosten and Tom Drummond FAST is the
Features from Accelerated segment test.
The FAST image processing algorithm stands out for its speed which tends to be better
than most of its comparative options. It lacks in accuracy.

• BRISK- BRISK which is the Binary Robust Invariant Scalable Keypoints is an algorithm
that stands average in terms of accuracy and timing.
However what it covers up with other points such as scale invarience and better perfor-
mance with rotated images.

• KAZE - KAZE as an feature detection image processing algorithm introduces the possi-
bility of reduction in noise.
The KAZE also seems to have better accuracy for rotated images. While the kaze feature
detector works well with rotated images it has certain deficiencies.
One such drawback is that it tends to have very high computational cost.

Further each of them are compared according to their different features and capabilities. A
table listing these findings is given below:

Ramrao Adik Institute of Technology 7

 Original vs Counterfeit Indian Currency Detection

Table 3.1: Analysis of Algorithms

Analysis of the different algorithms

Features SIFT SURF BRISK KAZE ORB
ACCURACY Most accu- average Not good Better Second to
rate for rotated accuracy sift
image for rotated
image
FEATURE average less than Can be re- longer than least
MATCH- sift duced sift
ING TIME
OUTLIER Approx. Approx. Approx. Approx. Approx.
REJEC- same same same same same
TION
TIME
TOTAL average less than fastest less than fastest
IMAGE sift sift
MATCH-
ING TIME
SCALE best not as good Good for average good
INVARI- as sift certain
ENCE range
COMPUT. half of kaze better than average highest least
COST sift

Ramrao Adik Institute of Technology 8

 Original vs Counterfeit Indian Currency Detection

Table 3.2: Time Comparison of Algorithms

Time Comparison of algorithms

Referred Papers SIFT SURF ORB KAZE FAST BRISK
A comparative Analysis of al- 1.19 0.8 0.4 0.6 - 0.06
gorithms
Comparison of feature extrac- 11 3 2 - - -
tion techniques to recognize
traffic rule violations
An Improved ORB Image - 1.18 0.18 - - -
Feature Matching Algorithm
Based on SURF
Biomedical Images Stitching 8.01 1 0.1 - - -
Using ORB Feature Based
Approach
ORB-Oriented Mismatching 8.8 2.5 0.28 - - -
Feature Points Elimination
Analysis and Comparison of 54 18 - - - -
Feature Detection and Match-
ing Algorithms for Rovers Vi-
sion Navigation
Real Time Image Mosaicing 1.79 0.67 0.14 - 0.05 -
System Based on Feature Ex-
traction Techniques
Image Feature Points Match- 3.23 - 0.031 - - -
ing via Improved ORB
A Tracking Algorithm Based 0.50 0.72 0.032 - - -
on ORB

Ramrao Adik Institute of Technology 9

 Original vs Counterfeit Indian Currency Detection

3.2 Feature Matching

On studying and analysing the six major image processing algorithms we consider the Orb
algorithm to be the most optimal for the task of classifying currency notes.
However the process of classifying notes works in several phases. The Orb algorithm works
as a feature detector on the images to detect feature points. These detected feature points need
to be matched with a set template. For this purpose feature matching is required and as Orb
does not have inbuilt feature matching like its alternatives we need to make use of external
resources.
The most prominent are the Brute Force Matcher and the FLANN based matcher both of which
are further understood below:

3.2.1 Brute Force Matcher

The most basic of the matchers the Brute Force matcher works on two images by taking into
consideration every detected feature point on both the images. Each of these points are com-
pared and the Euclidean distance between each is taken into account. On this basis the images
are evaluated.
As Brute Focre Matcher offers more precision as compared to the FLANN based matcher even
if the time required is more it is chosen as the matcher in this system.

3.2.2 FLANN based Matcher

FLANN stands for Fast Library for Approximate Nearest Neighbours. FLANN works quite
well with larger databases.
Its basis relies on the same technique as the Brute Force with the major difference that instead
of every point it takes into account the approximate nearest neighbours.
This insures that the time required for FLANN is quite low however the accuracy of matching
degrades.

Ramrao Adik Institute of Technology 10

 Original vs Counterfeit Indian Currency Detection

3.3 Limitations of Existing System

From the literature,after studying different papers and reports to see the various mechanisms
and algorithms that are applied for the purpose of detection of real and counterfeit Indian
currency notes have certain discrepancies. The approaches that are used have some problems
as described below:

• The time requirement of the algorithms in real time environment is not taken into con-
sideration.

• No parameters are set to see if the note is original or just a color copy of the original.

• Projects do not work on both the detection of denomination of notes and their genuine-
ness.

• The computational cost and the processing capabilities required are not taken into con-
sideration.

Ramrao Adik Institute of Technology 11

Chapter 4

Methodology

4.1 Proposed System

The process of classification of the notes as original and counterfeit would be done using the
concept of image processing. Here we would compare the characteristics of the note with a
predefined dataset to check if the note is real or fake.
The detection of the note is done using different security features within the note.
These features are:

• Secure thread

• Portrait of Mahatma Gandhi

• Watermark Of Mahatma Gandhi

• See-through register

• Latent image

• Number panel, with numerals growing from small to big size.

• Denominational numeral with Rupee Symbol 2000

• The Ashoka Pillar emblem

12
 Original vs Counterfeit Indian Currency Detection

• Small horizontal rectangle with 2000

• Seven angular bleed lines

4.2 Proposed Methodology

The major and relevant image processing algorithms are studied and understood. Their features
are analysed. First each of the images that are taken go through the same pre processing and
cleaning methods. After this major algorithms are applied to the image in different conditions
such as good lighting, bad lighting and also the quality of the note is changed.
This is done to see how each algorithm reacts to these changes and how it affects the results
with regards to time and number of features detected. After analysing the results the most effi-
cient and optimal process is chosen.
After this an optimal feature matcher is chosen on the basis of our system requirements. The
real time system is created and it works in two phases of feature detection and feature match-
ing to classify currency. The feature detection is done by the Orb algorithm while the phase of
feature matching is done using the Brute Force Matcher.
The project is such that on initialization the user would encounter a home page that would help
them navigate the application. The user would be presented with two options to help classify
the currency.
These options are Detailed Search and Quick Search. In the Detailed Search option the user
can select an image from their device and see the analysis on that image in real time.
The second option is the Quick Search option in which the input by user and the resulting out-
put analysis would be video based.

4.3 System Requirements

The implementation environment used in the project for the analysis of image processing al-
gorithms is MATLAB software . The Matlab software was used to analyze different image
processing algorithms in terms of their efficiency in finding maximum and essential feature

Ramrao Adik Institute of Technology 13

 Original vs Counterfeit Indian Currency Detection

points that will help in the classification of notes.The specification of the pc used are: Intel
Core,8 GB RAM ,3.40 Ghz.
The dataset of images used in the project implementation and for analyzing different image
processing algorithms is created using different denominations of Indian currency with differ-
ent inclinations and lighting conditions to test the capability and efficiency of different feature
identification algorithms.
For creating the real time classifying system we need Python 3 and various of its packages.

Ramrao Adik Institute of Technology 14

Chapter 5

Design of System

5.1 System Design

1. All major and relevant image processing algorithms are studied and understood.

2. First each of the images that are taken go through the same preprocessing and cleaning
methods.

3. After this major algorithms are applied to the image in different conditions such as good
lighting, bad lighting and also the quality of the note is changed. This is done to see how
each algorithm reacts to these changes and how it affects the results with regards to time
and number of features detected.

4. After analysing the results the most efficient and optimal process is chosen.

5. The project is such that on initialization the user would encounter a home page that
would help them navigate the application. The user would be presented with two options
to help classify the currency.

6. These options are Detailed Search and Quick Search. In the Detailed Search option the
user can select an image from their device and see the analysis on that image in real time.

7. The second option is the Quick Search option in which the input by user and the resulting
output analysis would be video based.

15
 Original vs Counterfeit Indian Currency Detection

5.2 Data Flow Diagram

The data flow diagram shows how a real time working system should be if all the optimal steps
are followed. This means that the correct algorithm and matcher must be chosen which re-
sponds best to the real time working environment. The system that the user encounters would
work as shown in the figure below.

Figure 5.1: Real Time Proposed System

Ramrao Adik Institute of Technology 16

Chapter 6

Experimental Results and Performance

Analysis

6.1 Practical Implementation and Analysis of Algorithms

On studying the various image processing algorithms and implementing them on the currency
notes in varying conditions such as good lighting and bad lighting we obtain the following
results in consideration to their time requirement.

Algorithms Handheld (Bad lighting) On Setup (good lighting)

(Time in sec) Crumpled Non Crumpled Crumpled Non Crumpled
SIFT 32.58 26.7 11.42 10.57
ORB 2.73 2.71 1.61 1.58
SURF 1.47 1.57 1.71 1.59
KAZE 1.41 1.89 1.35 1.50
BRISK 1.36 1.51 1.63 1.39
FAST 1.20 1.59 1.50 1.56

Along with time requirement the algorithms are analysed for various other parameters. The
comparative study of different feature detection algorithms for their ability to discover and de-
tect high number and high quality of features is:

17
 Original vs Counterfeit Indian Currency Detection

KAZE <SIFT <SURF <BRISK <ORB

The order of algorithms as per their efficiency in terms of computational cost is:
KAZE <SIFT <SURF <BRISK <ORB

The order of algorithms as per their efficiency in terms of feature matching is:
SIFT <SURF <BRISK <KAZE <ORB
The efficiency of these algorithms in terms of their speed for image matching(detector-descriptor)
is:
SURF <BRISK <SIFT <KAZE <ORB

Figure 6.1: SIFT with non crumpled currency

Ramrao Adik Institute of Technology 18

 Original vs Counterfeit Indian Currency Detection

Figure 6.2: SIFT with crumpled currency

Figure 6.3: ORB in good lighting

Ramrao Adik Institute of Technology 19

 Original vs Counterfeit Indian Currency Detection

6.2 Implementation of Real time System

The real time system that the user encounters has two options the Detailed Search and Quick
Search. In the Detailed Search option the user can select an image from their device and see
the analysis on that image in real time. Here the processing happens to a still image.
The second option is the Quick Search option in which the input by user and the resulting out-
put analysis would be video based. Here the processing takes place on an image frame of the
video and due to this the image quality turns out to be lacking.
Also as the system works on the basis of a Brute Force matcher the continuous video stream
faces the issue of lag due to the slow feature matching.

Figure 6.4: Home Page

Ramrao Adik Institute of Technology 20

 Original vs Counterfeit Indian Currency Detection

Figure 6.5: Real Note Result

Figure 6.6: Fake Note Result

Ramrao Adik Institute of Technology 21

Chapter 7

Testing

The Real time System for the currency detection works to identify the denomination of the
currency note and whether the currency note is counterfeit or genuine.
For the purpose of testing this system we work with 50 images and the resulting analysis is as
follows-

Currency images tested 50

Real notes 30
Fake notes 20
True Positive 28
True Negative 18
False Positive 2
False Negative 2

Accuracy = (TN+TP)/(TN+TP+FN+FP)
= (18+28)/50
= 92

22
Chapter 8

Conclusion and Future Scope

After analyzing different algorithms we have discovered that SURF,SIFT and BRISK works
well with large scale variations. ORB and BRISK are unvarying to affine change. ORB is
efficient algorithm able to detect large number of features. ORB performs image matching at
speed as compared to other algorithms and does not compromise with the accuracy.
On comparison of matchers the Brute Force matcher is considered most efficient for the pur-
pose of a real time system.
The project has two options with regards to classifying the currency. Out of these the Detailed
Search option has better accuracy. With regards to the Future Scope of the project, the real time
system can be made completely video based with the removal of video lag and an improvement
in the accuracy.

23
References

[1] Shubham Mittal ,Shiva Mittal 2018,“Indian Banknote Recognition using Convolutional
Neural Network” IEEE.

[2] Sahana Murthy, Jayanta Kurumathur, B Roja Reddy,2016 ,“Design and Implementation
of Paper Currency Recognition with Counterfeit Detection”, IEEE.

[3] Sonali R. Darade , Prof.G.R.Gidveer , “Automatic Recognition of Fake Indian Currency

Note”,IEEE.

[4] Jayant kumar Nayak, Chaitan Majhi,Apurva Kumar Srivastav, Ajaya Kumar Das, “ Neu-
ral Network Approach for Indian Currency Recognition”,IEEE INDICON.

[5] Xu Wang, Jiabao Zou, Daosheng Shi “An Improved ORB Image Feature Matching Algo-
rithm Based on SURF”,IEEE.

[6] Archana M, Kalpitha C, Prajwal S , Pratiksha N ,“Identification of Fake Notes and De-
nomination Recognition”,IEEE.

[7] Meng Fanqing , You Fucheng , 2013,“A Tracking Algorithm Based on ORB”,IEEE.

[8] Manishkumar Purohit, Arvind R.Yadav,2018, “Comparison of feature extraction tech-

niques to recognize traffic rule violations using low processing embedded system”, IEEE.

[9] Cai-Wei Shu , Xue-Zhong Xiao ,2018,“ORB-Oriented Mismatching Feature Points Elim-
ination”,IEEE.

[10] Xinbei Bai, Xiaolin Ning, Longhua Wang ,2012, “Analysis and Comparison of Feature
Detection and Matching Algorithms for Rovers Vision Navigation”,IEEE.

24
 Original vs Counterfeit Indian Currency Detection

[11] Ebtsam Adel , Mohammed Elmogy , Hazem Elbakry ,2014,“Real Time Image Mosaicing
System Based on Feature Extraction Techniques”,IEEE.

[12] Yanyan Qin , Hongke Xu , Huiru Chen,2014, “Image Feature Points Matching via Im-
proved ORB”,IEEE.

[13] Kyi Pyar Win , Yuttana Kitjaidure ,2018, “Biomedical Images Stitching Using ORB Fea-
ture Based Approach”,IEEE.

Ramrao Adik Institute of Technology 25

Acknowledgement

This acknowledgment is a token of gratitude, I feel towards the people who have helped me
to make this report a rich experience. I am delighted to offer our sincere thanks to my Institute
and my respected Principal Dr. Mukesh D. Patil for enabling me to add a formal project Report
on my BE project work, which has made me acquire tremendous knowledge. I would like to
express profound gratitude to my project guide Ms. Priyanka Shingane and project coordinator
Mrs. Reshma Gulwani of B.E. Program for their invaluable support, encouragement, supervi-
sion and useful suggestions throughout this project work. There moral support and continuous
guidance enabled us to complete my work successfully. I am very grateful for the valuable co-
operation and constant encouragement from Ms. Priyanka Shingane and Head of Department
Dr. Ashish Jadhav. His regular suggestions made my work easy and proficient. Last but not the
least, I am thankful and indebted all those who helped me directly or indirectly in completion
of this project report.

Anushka Kulkarni
Aishwarya Pupala
Prachi Kedar

26