Project Report

​On

​Currency Detection using OpenCV

Submitted By

Anoop sharma (170160107059)

Darshana jethavaa (170160107036)
Swarnali sarkar (170160107063)

Guided By:

Asst Prof. Hardik tank

Submitted To,
​Department of Electronic and communication department
 Academic Year
​(2020-2021)

L.D. college of Engineering

Ahmedabad
​

This is to certify that ​Anoop sharma ​Enrollment No.: 170284111002 of​ Semester VII,

Department of E.C. Engineering has satisfactorily completed the work on the topic

​Currency recognition system in ​Project - I (2170002) course within the four walls of the

Institute.

​Internal Guide
Asst. ​Prof. Hardik tank
​Department of E.C.
Head of
Department
​Prof. Mihir Shah
 Academic Year
​(2020-2021)

L.D. college of Engineering

Ahmedabad
​

This is to certify that ​Darshana jethavaa ​Enrollment No.: 170280111029 of​ Semester

VII, ​Department of E.C. Engineering has satisfactorily completed the work on the topic

​Currency recognition system in ​Project - I (2170002) course within the four walls of the

Institute.

​Internal Guide
Asst. ​Prof. Hardik tank
​Department of E.C.
Head of
Department
​Prof. Mihir Shah
 Academic Year
​(2020-2021)

L.D. college of Engineering

Ahmedabad
​

This is to certify that ​Swarnali sarkar ​Enrollment No.: 170280111127 of​ Semester VII,

Department of E.C. Engineering has satisfactorily completed the work on the topic

​Currency recognition system in ​Project - I (2170002) course within the four walls of the

Institute.

​Internal Guide
Asst. ​Prof. Hardik tank
​Department of E.C.
Head of
Department
​Prof. Mihir Shah
Acknowledgement

It Is A Matter Of Great Pleasure For Our To Submit This Project Report On Topic
​CURRENCY RECOGNITION SYSTEM As​ Part Of Curriculum Of ​Project - I Subject
In E.C. Engineering Degree From L.D. COLLEGE OF ENGINEERING,
AHMEDABAD.

Our Deepest Thanks To Asst.​Prof. Hardik tank ,​The Guide Of The Project For
Guiding And Correcting Various Documents Of Our Team With Attention And Care.
He Has Taken Pain To Go Through The Project And Make Necessary Correction As
And When Needed.

We Express Our Hopefully Thanks To The Head Of The E.C. Engineering

Department, ​Prof. Mihir Shah For Extending His Support.

We Would Also Thank My Institution And My Faculty Members Without Whom This
Project Would Have Been A Distant Reality. We Also Extend Our Heartfelt Thanks To
My All Faculty Members.

At Last But Not Least, We Are Thankful To Our Parents, Who Encouraged & Inspired
Us With Their Blessings.
A​bstract

This project is a Currency recognition system which used for denomination

we propose a system for automated currency recognition using image
processing techniques.

The proposed method can be used for recognizing both the country or
origin as well as the denomination or value of a given banknote. ... Our
system is able to accurately and quickly identify test notes
Table Of Contents

Chapter No. Chapter Title Page No.

Title Page 1

Certificates 2-4

Acknowledgement 5

Abstract 6

Table Of Contents 7

List Of Figures 8
Chapter 1 Introduction of Domain 9

Chapter 2 Problem Statement 10

Chapter 3 Project Definition 11

3.1 Project Definition 11

3.2 System Requirements 11

3.2.1 Software Requirements 11

3.2.2 Hardware Requirements 11

Chapter 4 System Analysis 12

Chapter 5 Future Enhancement 18

Chapter 6 Conclusion 19

Appendix 20

20-2
Design Engineering Canvas 3
 24-2
Project Progress Reports 7

27-3
Patent Search And Analysis Reports 2
List of Figures

Fig. 4.1 - Block diagram

Fig. 4.2 - Flow Chart

Fig. 4.3 - Raspberry 3i

Chapter-1 Introduction Of Domain
Paper currency recognition (PCR) is an important area of pattern recognition.  
A system for the recognition of paper currency is one kind of intelligent 
system which is a very important need of the current automation systems in 
the modern world of today. 
It has various potential applications including electronic banking, currency 
monitoring systems, money exchange machines, etc.  
This paper proposes an automatic paper currency recognition system for 
paper currency. 

A method of recognizing paper currencies has been introduced. This is 

based on interesting features and correlation between images. It uses Radial 
Basis Function Network for classification.  
The method uses the case of India paper currency as a model. The method is 
quite reasonable in terms of accuracy.  
The system deals with 110 images, 10 of which are tilted with an angle less 
than 15o.  
The rest of the currency images consist of mixed including noisy and normal 
images 50 each.  
It uses fourth series (1984–2007) of currency issued by India Monetary 
Agency (IMA) as a model currency under consideration. 
The system produces accuracy of recognition as 95.37%, 91.65%, and 
87.5%, for the Normal Non-Tilted Images, Noisy Non-Tilted Images, and 
Tilted Images respectively.  
The overall Average Recognition Rate for the data of 110 images is 
computed as 91.51%. The proposed algorithm is fully automatic and requires 
no human intervention.  
The proposed technique produces quite satisfactory results in terms of 
recognition and efficiency. 
 
 

 
Chapter-2 Problem Statement 

The paper currencies are the center of target to counterfeiters. Counterfeit 

detection is mainly executed based on the Chemical or Physical properties of 
paper currencies.  

The counterfeiters nowadays, can evade the chemical property & physical 
feature based counterfeit paper currency detection system due to technological 
advancement. Moreover, the unavailability, high cost, poor accuracy and lack of 
user-friendliness leads these fake detection tools to a least acceptance 
situation among the end-users.  

That is why, feature based counterfeit detection system is now the focus of 
active research.  

In the proposed work, the methodology of image processing based extraction of 
the existing features of notes will be depicted in detail to demonstrate the 
feasibility of software assisted counterfeit currency detection system.  

 
Chapter-3 Project Definition 

Modernization of the financial system is a milestone in protecting the economic 

prosperity, and maintaining social harmony. The Reserve Bank of India is the 
only one which has the full authority to issue bank notes in India. But some 
unsocial group of people is prone to make these fake currencies. Fake Indian 
Currency of 100, 500 and 1000 seems to have flooded the system and there is 
no proper way to deal with them for a common person. From few years, along 
with the original currency, Fake Currency is also circulating in the society and 
unbalancing the social harmony of the society 

Key Details Of The Recognition system:  

Perspective: ​2
​ .5d

​Platforms: ​​Android, Windows 10, Linux.

​Software Used: ​P
​ ython3 , opencv 3.4.4, node.js .Raspberry library (gpio,i2c)

3.1 Software Requirements

The System Has Different Requirements When Running On Different
Platforms. The Software Requirements For Running The System Are
As Listed For Each Platforms:

​Android: Version​ 7.0 Or Up

Windows And Linux: .​Net Core 4.5

3.2 Hardware Requirements

Raspberry pi 3b/2b

Camera Pi 5M

LCD I2C 16*2

4​​.1 Feasibility Of The Project

During This Semester We Analyzed And Conceptualized What Our

System Was Going To Be. As It Has Been Proved, Currency
Recognition System Of This Size And Scope Can Be Created Well
Within Months.

We Have Come To These Estimates:

Estimated Development Time: 5-6 Months

First 2 Months: Conceptual Phase

Month 3,4 - Production Phase

Final Month - Testing, Polishing.

4.2 Block Diagram

Fig 4.1 block diagram

4.3 Flow Chart

Fig 4.2 Flow chart

C​​hapter-5 Future Enhancements

The Currency Recognition system Might Receive Following Future Enhancements:

1.​ A
​ Graphical interface Upgrade (GUI)

2.​ P
​ erformance Upgrade

3.​ S
​ upport More Platforms

4.​ D
​ lc Pack (​downloadable content​)

5.​ C
​ ontinuation Of Storyline