A PRELIMENERY REPORT ON

“Authentication for ATM Machine”

SUBMITTED TO THE SAVITRIBAI PHULE PUNE UNIVERSITY,
PUNE
IN THE PARTIAL FULFILLMENT OF THE REQUIREMENTS

IN
COMPUTER ENGINEERING
BY
Om Raosaheb Sadaphal

Seat no:—————-

UNDER THE GUIDANCE OF

Prof. Tejashree Patil

DEPARTMENT OF COMPUTER ENGINEERING

Dr. D.Y.Patil Institute Of Technology Pimpri,Pune
SAVITRIBAI PHULE PUNE UNIVERSITY
2022-23

1
————————————————————————————————

This is to certify that the Seminar report entitles

” Authentication for ATM Machine”

Submitted By

Om Raosaheb Sadaphal

is a bonafide student of this institute and the work has been carried out by
him under the supervision of Prof. Tejashree Patil and it is approved for
the partial fulfillment of the requirement of Savitribai Phule Pune
University(COMPUTER ENGINEERING).

Prof. Tejashree Patil Dr.S.V.chobe

Internal Guide Head Of Department
Dept. of Computer Engineering Dept. Computer Engineering

Dr.L.K.Wadhwa
External Examiner Principal
DYPIET, PUNE
Place :
Date :

Department of Computer Engineering 2022-23 0

I
 Acknowledgments

It gives me great pleasure in presenting the seminar report on ’ Authentication

for ATM Machine.’
I would like to take this opportunity to thank my internal guide Prof.
Tejashree Patil for giving me all the help and guidance that I needed. I
am really Greatful to them for their kind support. Their valuable
suggestions were very useful.
I am also greatful to Dr.S.V.chobe, Head of Computer Engineering Department,
DYPIET Pimpri Pune for his indispensable support and suggestions.

Om Raosaheb Sadaphal
(TE Computer Engg.)

II
Abstract

“A biometric factor is something physiologically unique

about an individual, such as a fingerprint, facial image, iris, voice
pattern, and handwriting. When an individual wants logical or
physical access (depending on the implementation), a sample is
taken of the authenticates biometric data for example a finger print.
Then the authenticator using a previously enrolled version of the
same biometric template can match the sample against the stored
template to verify the individual’s identity”.
“Biometrics are not secret, as everyone leaves fingerprints
everywhere they go, faces and eyes can be photographed, voices can
be recorded, and handwriting samples can be obtained. The security
of the fingerprint authentication system therefore relies on the
integrity and authenticity of the biometric information”, therefore
careful evaluation must be done for the selection of the fingerprint
authentication and Good practices should be followed during the
implementation, enrollment and administration of the fingerprint
authentication system.

III
Contents
Acknowledgment . . . . . . . . . . . . . . . . . . . . . . . . . . . II

1 INTRODUCTION IX
1.1 Overview…………………………………………………………..VI
1.2 Problem Statement……………………………………………VII
1.3 Research Objectives…………………………………..VII
1.4 Significance of Study…………………………………………..VII

2 LITERATURE SURVEY VIII

3 Software Requirement Specification IX

3.1 System Requirements…………………………………………XI
3.1.1 Software Requirements………………………….. IX
3.1.2 Hardware Requirements…………………………..IX

4 Technology X
4.1 Biometric Authentication…………………………………… XI
4.2 Fingerprint Authentication………………………………… XII
4.2.1 What is Fingerprint Authetication……………..XII
4.2.2 How Fingerprint Authentication works……..XIII
4.3 Iris Authentication …………………………………………...XIII
4.3.1 What is Iris Authentication……………………….XIII

IV
 4.3.2 How Iris Authentication works …………………………………….. XIV
5 System Design XV
5.1 Required Architectures/Flow Diagrams …………………………………… XV
5.1.1 Fingerprint Biometric Authentication………………………………XVI
5.1.2 Iris Biometric Authentication…………………………………………..
XVII
5.1.3 Overall Biometric ATM Machine Architecture ………………….
XVII

6 Chapter 6 XVIII

6.1 Advantages OF Biometric ATM Machine XVIII

6.2 Disadvantages OF Biometric ATM Machine XIX

s7 Conclusion XXI
8 References XXI

List of Figures

1. Types of Biometric Authentications …………………………XI

2. Fingerprint Authentication Architecture ………………….XVI
3. Iris Authentication Architecture ………………………………XVII
4. Overall Biometric Atm Machine Architecture…………….XVIII

List of Tables

No Table

V
 Chapter 1

INTRODUCTION

1.1 Overview
In existing ATM system, most often only personal
identification number (PIN) is used to verify authentic user
which is not secured enough as it is very easy to copy.
Sometimes thieves have a very strong way to steal account
information, that’s why bio-metric verification system can be a
firm solution. The objective of this paper, is to provide a more
secured method using bio-metric features and message
authentication technique. In our proposed method, PIN
verification is combined with fingerprint recognition, to
identify a customer during ATM transaction. Fingerprint is
verified using efficient minutiae feature extraction algorithm.
To assure the security while doing transaction through swipe
machine, the client will confirm the transaction by an approval
message through GSM technology. In both cases, location will
be identified through GPS. If any illegitimate person tries to
use the card it will automatically be blocked by the system and
detail information will be sent to the customer through the
message. Hence, the proposed method will provide more
security by identifying and reducing the frauds.

Keywords- ATM, Bio-metric, Fingerprint, GSM, GPS, PIN

1.2 Problem Statement :

 The issue of people’s accounts being emptied by fraudsters
when they are able to hack into their cards to know their PIN.

1.3 Research Objectives :

To proffer solution to ATM fraud in the Banking Industry.To
stop the vice of people impersonating others to withdraw money on their behalf
from the ATM.

1.4 Significance of the Study:

Once this study is carried out the issue of fraudsters
making away with customers’ money will be a thing of the past.

Chapter 2

VII
 LITERATURE SURVEY
Analysis Literature Survey:

1. The author Ahmad Tasnim Siddiqui in his paper he discussed regarding the
ATM Scams going on now days . To caome up this problem the author had
discuss the idea of biometric technology . According to him the Biometric
Technology can stop this.

2. The authors Christiawan1, Bayu Aji Sahar2, Azel Fayyad Rahardian3, Elvayandri
Muchtar4 they have discuss about fingerprint authentication technology in
the paper they think that fingerprint authentication is better for security
purpose of ATM.

3. The authors Alfi Zuhriya Khoirunnisaa, Lutfi Hakim , Adhi Dharma Wibawa
They have discuss regarding the Iris authentication technology in the
paper
they think that Iris authentication is better for security purpose of ATM.

VIII
 Chapter 3
Software Requirement
Specification

3.1 Software Requirement :

1. Operating system - Windows 10
2. Database system - Microsoft SQL Server 2019
3. Front End - Visual Studio
4. Framework - .NET Framework 4.8

3.2 Hardware requirement :

1. Processor - Intel Core i5
2. Hard Disk - 10 GB
3. RAM - 4GB
4. Sensor - Fingerprint Recognizer

IX
Chapter 4
Technology

4.1 Biometric Authentication :

Biometric authentication is a security process

that relies on the unique biological characteristics of individuals to verify they are who
they say they are. Biometric authentication systems compare physical or behavioral
traits to stored, confirmed, authentic data in a database. If both samples of the
biometric data match, authentication is confirmed. Typically, biometric authentication
is used to manage access to physical and digital resources, such as buildings, rooms
and computing devices.

Biometric identification uses biometrics, such as fingerprints or retina scans, to

identify a person, whereas biometric authentication is the use of biometrics to verify
people are who they claim to be.

X
XI
4.2 Fingerprint Authentication :

Fingerprints have been accepted as the

most common form of biometrics authentication today. The strong
point about using fingerprint biometrics are that giving fingerprints
is more widely accepted, convenient and reliable than other forms of
physical identification, especially when using technology. In fact, it is
considered that fingerprint identification is the least intrusive of all
biometric technologies when privacy is the concern. Every human
beings fingerprint is unique. Each fingerprint has a unique
characteristic and pattern that is made up of lines and spaces. The
lines are called ridges while the spaces between the ridges are called
valleys. These patterns of ridges and valleys are used to match the
fingerprint for verification and authentication.

How fingerprint biometrics work

Fingerprint biometrics uses some form of a scanner to obtain an image of your
fingerprint. Methods include the following:

 Optical scanner: This takes a digital image of your fingerprint by lighting

up the finger through a prism and reading the way the ridges and valleys
reflect the light. This information is then converted into an image.  
 Capacitive scanner: This generates a small electric charge through
miniature built-in capacitors that store electricity. The capacitors are
discharged when the finger touches the scanner.

A higher level of discharge is created by fingerprint ridges, which have a greater

contact surface, and less by the valleys, which create gaps in the skin. The difference
between these is measured to determine a pattern.  

 Ultrasound scanner: An ultrasound signal is used to record the echo the

fingerprint creates, as ridges and valleys create different echoes. This
scanner does not need to be in direct contact with the finger to get a
reading and also has the benefit of reading in a more three-dimensional
manner.  

XII
  Thermal scanner: This uses heat to measure the temperature difference
between the ridges and valleys of the fingerprint. It creates the image of
the fingerprint based on the contrast between the two.

After fingerprints are scanned, they can then be matched based by pattern matching,
which compares two images looking for similarities. More commonly, minutiae-based
matching is used, which looks more closely at the direction and location of the points.

The unique data and specific characteristics of the fingerprint are filtered and then
saved as a mathematical representation (algorithm) or as an encrypted biometric key.
The fingerprint image itself is not saved, only the binary code (or series of numbers) is
retained and used for verification purposes. This algorithm cannot be reverse
engineered to recapture the image of the fingerprint and thus cannot be duplicated. 

Fingerprint data is generally stored on the device itself and not in the cloud.

4.3 Iris Biometric :

Iris Recognition is a biometric method of identifying people

based on unique patterns within the ring-shaped region surrounding the pupil of
the eye. Every iris is unique to an individual, making it an ideal form of biometric
verification.

Whilst Iris Recognition remains a niche form of biometric identification, we can

expect it to become more prevalent over the coming years. Immigration control is
one area expected to push forward with wider use of Iris Recognition as a safety
measure and a response to the threat of terrorism around the world.

One of the reasons Iris Recognition is such a sought after method of identifying
individuals, especially in sectors such as law enforcement and border control, is
that iris is a very strong biometric, highly resistant to false matches and the high
search speed against large databases. Iris Recognition is an extremely reliable
and strong method to accurately identify individuals.

XIII
 How Iris Recognition works 
The process of Iris Recognition involves the use of a specialised digital camera. The
camera will use both visible and near-infrared light to take a clear, high contrast
picture of a person’s iris. With Iris Recognition, the camera focusses in on your eye
and locates the centre of the pupil, edge of the pupil, edge of the iris and your eyelids
and eyelashes. This information is then fed through Iris Recognition software where
the unique pattern of the iris is analysed and translated to and iris template 

Iris Recognition is compatible with contact lenses and even eyeglasses and can be used
by blind people, as long as they have an iris. This makes it an extremely versatile
technology when it comes to securely identification. 

Five benefits of Iris Recognition 

The characteristics of an iris are unique for each individual and even between eyes –
your right and left eye both have unique iris patterns. Being a highly accurate way of
identifying people, there are many advantages of the technology: 

 Accuracy – Iris Recognition is one of the most accurate forms of biometric

authentication and here at NEC, our Iris Recognition technology has been
identified as the most accurate, achieving the highest matching accuracy
evaluation in the Iris Exchange (IREX) IX evaluations performed by the U.S.
National Institute of Standards and Technology (NIST). 
 Contactless – whilst proximity to the iris scanner is necessary, Iris
Recognition provides a contactless solution which makes it hygienic to use
and less intrusive to the end user. 
 Flexible and Scalable – Iris recognition is extremely flexible. The use of
an infrared camera means scanners can be used at night or in the dark. 
Because of its flexibility, Iris Recognition is also highly scalable and has
been deployed by government and other agencies worldwide. 
 Liveness Detection – one area which NEC is pioneering is Liveness
Detection. The technology in the iris scanner detects movement of the iris
which identifies the liveness of the individual, reducing the risk of forged
access through high quality static images. 
 Fast Matching – if an individual is already enrolled in the biometric
system, Iris Recognition is one of the fastest forms of biometric
identification. 

XIV
Chapter 5
Architectures/Flow Diagrams

XV
XVI
XVII
Chapter 6
4.1 Advanatages of Biometric ATM Machine
1. Quicker Authentication

Traditionally, businesses used to opt for the ‘pen and paper’ method, where an
employee would sign in by penning his signature on an ‘attendance sheet.’ The
manual process would be time-consuming; however, the biometric system eliminates
the need for physical attendance. Employees can just use the retina or fingerprint
scanner to sign in to record their attendance.

2. Improves the Security System

Passwords, pins, security codes are hard to remember for some people. The
biometric system eliminates the need to remember passwords. It offers different
modes like retina recognition, fingerprint, or face scanner.

Additionally, the system can be used to protect sensitive data, because fingerprints
can’t be forged, while passwords and pins can be stolen.

3.Complete Data Accuracy

The data provided by a company biometric is 100% authentic and reliable. The
biometric system only allows access to authorized personnel and keeps out intruders.
Data security is guaranteed once a physical trait is logged onto the system by
restricting outside access.

4. Scalability

The biometric system is one system per organization deal. The technology can be
used for more than one aspect of the organization, whether it’s a new department or
a special project. It is the most scalable security solution for big and small businesses
today.

XVIII
For example, banks are investing in affordable mobile app development and
biometric where users can sign using the fingerprint on their smartphones!

5. Flexible

The biometric system offers users the flexibility of using physical traits and
eliminating the need for remembering passwords or pins. Most smartphones, in the
present day, have fingerprint scanners that allow the user quick access to the files on
their phones. Likewise, apps like WhatsApp also offer finger identification, that helps
users keep their data protected from unwanted theft.

4.2 Disadvantages of Biometric ATM

Machine

1. Physical Disabilities

The authentication system only recognizes traits that were entered and fail to
recognize the user if their physical traits change even the slightest. Here are a few
reasons why traits might change:

A burnt or damaged finger

A retina transplants

Tattooed hands

If the user is wearing lenses (and usually doesn’t) or vice versa

In such situations, the authentication method needs to be changed to grant

authorized user access, which can be inconvenient.

XIX
2. Expensive on the Pocket

While the system is reliable and handy, the cost is not easy on the pocket. The
biometric system is yet to be mainstream, which is why the setup, integration,
and hardware can be costly, especially for small businesses.

3. Physical Traits Can’t Be Altered

Like any other system, the biometric system is not perfect. The system is still
changing to become better. That means users can’t rely on the safety of their data.
If the data were stolen, they can’t try to ‘change’ their identification traits like
they can change passwords during a security breach.

4. Scanner Issues

Some biometric systems can face scanning issues if there is even a slight change,
especially if the company is using retina scanning. Iris scanning is still not 100%
reliable because the system will fail if the user has long eyelashes, different eye
color, or a reflection in the cornea.

5. No Remote Access

In a crisis, like a security breach, HR professionals cannot access the system

‘remotely’ to try and eliminate sensitive data, which is a major disadvantage for
the system.

XX
 Chapter 7

Conclusion
Thus, we are looking forward to an ATM model
that is more reliable in providing security by using Biometric Authentication . By
keeping the time elapsed in the verification process to a negligible amount we
even try to maintain the efficiency of this ATM system to a greater degree.
Furthermore, since nearly all ATMs videotape customers engaging in
transactions, it is no broad leap to realize that banks already build an archive of
their customer images, even if they are not necessarily grouped with account
information.

Chapter 8

REFERENCES
1. A. Z. Khoirunnisaa, L. Hakim and A. D. Wibawa, "The Biometrics
System Based on Iris Image Processing: A Review," 2019 2nd
International Conference of Computer and Informatics
Engineering (IC2IE), 2019, pp. 164-169, doi:
10.1109/IC2IE47452.2019.8940832.

https://ieeexplore.ieee.org/stamp/stamp.jsp?
tp=&arnumber=8940832&isn umber=8940810

XXI
2. Christiawan, B. A. Sahar, A. F. Rahardian and E. Muchtar,
"Fingershield ATM – ATM Security System using Fingerprint
Authentication," 2018 International Symposium on Electronics
and Smart Devices (ISESD), 2018, pp. 1-6, doi:
10.1109/ISESD.2018.8605473.

https://ieeexplore.ieee.org/stamp/stamp.jsp?
tp=&arnumber=8605473&isn umber=8605438

3. Biometrics to Control ATM Scams: A Study

Ahmad Tasnim Siddiqui
College of Computers & Information Technology
Taif University
[email protected]
Kingdom of Saudi Arabia

https://ieeexplore.ieee.org/stamp/stamp.jsp?
tp=&arnumber=8940832&isn umber=8940810

XXII