A SEMINAR REPORT ON

SECURE ATM BY IMAGE PROCESSING

Submitted in partial fulfillment of the requirements for the
award of the degree of

BACHELOR OF TECHNOLOGY

In

COMPUTER SCIENCE AND ENGINEERING

Submitted by

Buyyakar Vinay Raj – 18841A05D1

DEPARTMENT OF COMPUTER SCIENCE ENGINEERING

AURORA’S TECHNOLOGICAL AND RESEARCH INSTITUTE

PARVATHAPUR, UPPAL - 500039
NOVEMBER,2021

1
 AURORA’S TECHNOLOGICLA AND RESEARCH INSTITUTE
PARVATHAPUR, UPPAL – 500039

DEPARTMENT OF COMPUTER SCIENCE ENGINEERING

CERTIFICATE

Certified that seminar work entitled “SECURE ATM BY IMAGE PROCESSING” is a bonafide
work carried out in the fourth year by Buyyakar Vinay Raj-18841A05D1 in partial fulfillment for the
award of degree of Bachelor of Technology in Computer Science Engineering from JNTU Hyderabad
during the academic year 2021-22.

SEMINAR COORDINATORHEAD OF THE DEPARTMENT

Ms. D. Subashini Ms. A. Durga Pavani
Associate Professor Department of CSE
Department of CSE ATRI
ATRI
GUIDE
(Ms. A. Durga Pavani)

2
 ACKNOWLEDEMENT

I express my sincere thanks to Ms. A. Durga Pavani (Head of the Department,

Computer Science and Engineering), Ms. A. Durga Pavani (Staff in charge), my seminar guide
for their kind co-operation for presenting the seminar. I also extend my sincere thanks to all
other members of the faculty of Computer Science and Engineering Department and my friends
for their co-operation and encouragement.

Buyyakar Vinay Raj

3
 ABSTRACT

Every biometric system has its limitations. Therefore, identification based on multiple biometrics is an
emerging trend as multimodel biometrics can provide a more balanced solution to the security
multimodel systems involve the use of more than one biometric system.

Our contribution to the above subject is that we have developed an algorithm on banking security. For
this we have considered a bank using biometric technology for its security purpose. The security is
assured by using finger scan, voice scan, hand geometry scan and by requesting the password given by
the bank for a particular user when necessary.

Biometrics technology allows determination and verification of ones identity through physical
characteristics. To put it simply, it turns your body in to your password. We discussed various biometric
techniques like finger scan, retina scan, facial scan, hand scan etc. Two algorithms have been proposed
by taking biometric techniques to authenticate an ATM account holder , enabling a secure ATM by
image processing. Biometrics is now applied in various public and private sectors..

4
 TABLE OF CONTENTS
CHAPTER NO PARTICULARS Page
1 Introduction
2 Importance Of Security In ATM
3 Digital Image Processing
4 Biometrics
5 Proposed Work
6 Reliability And Advantages
7 Benefits
8 Conclusion
9 Bibliography

5
 1. INTRODUCTION

Nowadays people don't even think twice about using ATMs. But how many people actually think about
the security risks involved in using them? How many people think about the potentials for fraud and
crime that ATMs introduce? The answer is probably not many, since these transactions are so common
now. But as the use of ATMs is on the rise, so is the number of crimes involving ATMs.
1.1 PROBLEMS FACED

More recently and even more to the point is another story that was written about in the Reno
GazetteJournal on November 6, 1990. The headline reads "Reno bank job nets $740,000". The
criminals in this story involved one insider who worked for Wells Fargo Armored and ATM Repair
Service and four other people. The insider was newly hired by Wells Fargo and was part of a team
that delivered the $740,000 to the ATM for storage on October 24, 1990. Later that day, the alarm
for the ATM was triggered. But when the police came, they didn't see any signs of entry and they
left. The alarm was reset by the bank, and the next morning the money was discovered missing. A
specific key and combination was needed to gain entry, so the investigation focused on Wells Fargo
employees. In the end, the FBI was able to recover little less than half of the money, but there was
still $350,000 missing.
Since both a specific key and a combination was needed, how did one employee have access to
both? What happened to dual access control? Did it fail in this instance? Or was it never in place?
Or is dual access control a result of crimes like these? Because ATMs are a part of our daily lives by
allowing us access to cash and other financial information, it's important that we understand the
security risks and the measures in place to protect our money. Along the same lines, it's important
that we understand the security measures around tellers.
Afterall, they are the ones who have access to all the account information in the database and access
to a potentially large sum of paper money. They have financial histories at their fingertips. They
enter in transactions for the customers. Is there some way fraudulent transactions could be entered?
Is there any way that money could be skimmed? What measures are in place to protect us from the
tellers who are behind the counters? Not only do we have to consider security from the tellers, but
security of the tellers. Precisely because they do have access to large sums of cash and financial

6
 information, what danger does that put them in? What measures are in place to protect the tellers
from bank robbers? These are some of the questions that I would like to address in this paper.

2. IMPORTANCE OF SECURITY IN ATM

There ATMs make life easy. You can get cash in less than a minute from almost anywhere.

However, attacking ATMs is "more lucrative than drugs" according to Diebold's Chuck Somers, who
summarizes the three major ATM threats for BankInfoSecurity.com:
 Physical, or stealing the cash from an ATM
 Logical, or the installation of malicious software,
 And Fraud, or using fake cards and stealing card
 Details in skimming scams

The threat of getting your card skimmed is the greatest one and continues to increase -- scammers get
easy access to cash, and the stakes are low if they get caught.
As skimming devices get harder and harder to detect, it's more and more important to bank at ATMs
you trust. Machines at bank branches can be attacked, but they're less risky than machines out on the
street. If you're cavalier about where you use the ATM, be sure that you regularly check your accounts
for unusual activity.

2.1 Present measures taken for security

Considering the volume of transactions being processed by several branches of a commercial bank,
proper control in
Form the identification and authentication should be in place. Several control measures have been
put in place to ensure interests of all concerned parties such as issuers, acquirers, third party
7
 processors, switching companies and cardholders are protected. Some of the controls in place
include:
2.1.1 About ATM
 Well lit up to discourage shady deeds at night
 Fortified with camera for footage
 Keypad protector against key logger and shoulder surfing
 Dual control of physical access to the machine
 Default password disabled to avoid unauthorized access .
 Timely reconciliation of cash loading with ATM Till account
 Surveillance through physical monitoring and CCTV cameras
2.1.2 About Cards
 Strong algorithms are used in generating PANs
 Storage of card details is done on protected systems
 Card details (such as PAN, expiry date) are jealously guarded.
 While communicating, PAN is masked. Strong Encryption is used when transferring files
especially, between TPP and Issuer
 Magnetic stripe type is outlawed in some countries to avoid card cloning.
 Some restrictions are placed on cards in terms of allowable transactions and withdrawal limit
2.1.3 About PIN
 Where PIN mailers are used, they are not dispatched at the same time with the cards and
usually through a different medium.
 PIN selectable options are used to prevent insider compromise
 PINs are masked during usage against shoulder surfing.

3. DIGITAL IMAGE PROCESSING:

An image may be defined as a two-dimensional function, f(x, y), where x and y are spatial
(plane) coordinates, and the amplitude of at any pair of coordinates (x, y) is called the intensity or gray
level of the image at that point. When x, y, and the amplitude values of f are all finite, discrete
quantities, we call the image a digital image. The field of digital image processing refers to processing
digital images by means of a digital computer. Note that a digital image is composed of a finite number
8
of elements, each of which has a particular location and value. These elements are referred to as picture
elements, image elements, pels, and pixels. Pixel is the term most widely used to denote the elements of
a digital image. Vision is the most advanced of our senses, so it is not surprising that images play the
single most important role in human perception.

However, unlike humans, who are limited to the visual band of the electromagnetic (EM) spectrum,
imaging machines cover almost the entire EM spectrum, ranging from gamma to radio waves. They can
operate on images generated by sources that humans are not accustomed to associating with images.
These include ultra-sound, electron microscopy, and computer-generated images. Thus, digital image
processing encompasses a wide and varied field of applications. There is no general agreement among
authors regarding where image processing stops and other related areas, such as image analysis and
computer vision, start. Sometimes a distinction is made by defining image processing as a discipline in
which both the input and output of a process are images. We believe this to be a limiting and somewhat
artificial boundary

9
 How is facial recognition making a difference?

While controversy has emerged over how law enforcement authorities use facial recognition,
many police officials have argued that the technology helps them to flight crime, and it can also be used
to identify missing persons and the victims of human trafficking.
Meanwhile, as a contactless biometric solution that’s easy to deploy in consumer devices, face
recognition is showing the public just how convenient strong authentication can be.
Facial recognition doesn’t just deal with hard identities, but also has the ability to gather
demographic data on crowds. This has made face biometrics solutions increasingly sought after in the
retail marketing industry.

10
.

4. BIOMETRICS:

The Biometrics are automated methods of recognizing a person based on a physiological or

behavioral characteristic. Among the features measured are face, fingerprints, hand geometry,
handwriting, iris, retinal, vein, and voice. Biometric technologies are becoming the foundation of an
extensive array of highly secure identification and personal verification solutions. As the level of
security breaches and transaction fraud increases, the need for highly secure identification and personal
verification technologies is becoming apparent. Biometric-based solutions are able to provide for
confidential financial transactions and personal data privacy. The need for biometrics can be found in
federal, state and local governments, in the military, and in commercial applications. Enterprise-wide
network security infrastructures, government IDs, secure electronic banking, investing and other
financial transactions, retail sales, law enforcement, and health and social services are already benefiting
from these technologies.
A. How Biometric System Works?
In biometrics a series of steps are followed to get the aimed goal, the steps are as shown in
the figure below : Sensor : A sensor collects data and converts the information to a digital
format. Signal processing algorithms : This is where quality control activities and
development of the template takes place. Data Storage : Keeps information that new
biometric templates will be compared to. Matching algorithm : Compares the new template
to other templates in the data storage. Decision process: Uses the results from the matching
component to make a system level decision.
B. Types of Biometrics
1) Finger scan: Finger-scan biometrics is based on the distinctive characteristics of the human
fingerprint. Fingerprints are used in forensic applications: large- scale, one-tomany searches on
databases of up to millions of fingerprints
2) Retina scan: Retina scan requires the user to situate his or her eye with ½ inch of the capture
device and hold still while the reader ascertains the patterns. Retina scan is designed to use in military
facilities, logical security applications such as network access or PC logic
3) Iris scan : The iris has colored streaks and lines that radiate out from the pupil of the eye. The
iris provides the most comprehensive biometric data after DNA. The iris has more unique information
11
than this.
4) Hand Geometry :This is one of the first successful commercial biometric products .A person
places their hand on a device and the system takes a picture of the hand using mirrors ,then measures
digits of the hand and compares to those collected at enrollment

C.. Facial Scan

Masked The first and most important step of this project will be to locate a powerful open-
source facial recognition program that uses local feature analysis and that is targeted at facial
verification. This program should be compliable on multiple systems, including Linux and Windows
variants, and should be customizable to the extent of allowing for variations in processing power of the
machines onto which it would be deployed. We will then need to familiarize ourselves with the internal
workings of the program so that we can learn its strengths and limitations. Simple testing of this
program will also need to occur so that we could evaluate its effectiveness. Several sample images will
be taken of several individuals to be used as test cases – one each for “account” images, and several
each for “live” images, each of which would vary pose, lighting conditions, and expressions. Once a
final program is chosen, we will develop a simple ATM black box program. This program will serve as
the theoretical ATM with which the facial recognition software will interact. It will take in a name and
password, and then look in a folder for an image that is associated with that name. It will then take in an
image from a separate folder of “live” images and use the facial recognition program to generate a
match level between the two. Finally it will use the match level to decide whether or not to allow
“access”, at which point it will terminate. All of this will be necessary, of course, because we will not
have access to an actual ATM or its software. Both pieces of software will be compiled and run on a
Windows XP and a Linux system. Once they are both functioning properly, they will be tweaked as
much as possible to increase performance (decreasing the time spent matching) and to decrease memory
footprint.

5. PROPOSED WORK :

Locate a powerful open-source facial recognition program that uses local feature analysis and
that is targeted at facial verification. (should be compliable on multiple systems, including Linux and
Windows variants, and should be customizable to the extent of allowing for variations in processing
12
power of the machines onto which it would be deployed) then we need to familiarize ourselves with the
internal workings of the program so that we can learn its strengths and limitations. Simple testing of this
program will also need to occur so that we could evaluate its effectiveness. Once a final program
ischosen, we will develop a simple ATM black box program.
1) DATA ACQUISITION:
Several sample images will be taken of several individuals to be used as test cases – one
each for “account” images, and several each for “live” images, each of which would vary
pose, lighting conditions, and expressions.

2) INPUT :
It will take in a name and password, and then look in a folder for an image that is associated
with that name. It will then take in an image from a separate folder of “live” images and use
the facial recognition program to generate a match level between the two.
3) FACE IMAGE CLASSIFICATION :
Finally it will use the match level to decide whether or not to allow “access”, at which point
it will terminate.

13
 A. DATA ACQUISITION
The input can be recorded video of the speaker or a still image. A sample of 1 sec duration
consists of a 25 frame video sequence. More than one camera can be used to produce a 3D
representation of the face and to protect against the usage of photographs to gain
unauthorized access
B. INPUT PROCESSING
A pre-processing module locates the eye position and takes care of the surrounding lighting
condition and colour variance. First the presence of faces or face in a scene must be detected.
Once the face is detected, it must be localized and Normalization process may be required to
bring the dimensions of the live facial sample in alignment with the one on the template.

14
 C. FACE IMAGE CLASSIFICATION
The appearance of the face can change considerably during speech and due to facial
expressions. In particular the mouth is subjected to fundamental changes but is also very
important source for discriminating faces. So an approach to person’s recognition is
developed based on patiotemporal modeling of features extracted from talking face. Models
are trained specific to a person’s speech articulate and the way that the person speaks .
D. DECISION MAKING
Face recognition starts with a picture, attempting to find a person in the image.The face
recognition system locates the head and finally the eyes of the individual. A matrix is then
developed based on the characteristics of the Individual’s face. The method of defining the
matrix varies according to the algorithm This matrix is then compared to matrices that are in
a database and a similarity score is generated for each comparison

6. RELIABILITY AND ADVANTAGES:

6.1 RELIABILITY
It requires no physical interaction on behalf of the user. It is accurate and allows for high
enrollment and verification rates. It does not require an expert to interpret the comparison
result. It can use your existing hardware infrastructure, existing cameras and image capture
Devices will work with no problems It is the only biometric that allow you to perform
passive identification.

6.2ADVANTAGES
The advantages are as follows
1) Deliver a practical and workable solution that addresses the requirements of the
regulatory authorities.
2) Limit the financial risks given that they were forced to take responsibility for
financial loss [rather than being allowed to pass this on to the account-holder]

3) Provide a framework that still allowed for high withdrawal limits to cater for the

15
 demands of a cashfocused customer base
4) Take societal responsibility to reduce rising levels of crime that were associated with
cash-card transactions
5) Increase customer satisfaction
6) Different charges for transactions given that the transaction takes place in a more
secure manner
7) Higher withdrawal and transaction limits
8) Peace of mind given the higher level of security applied to the account.

16
 7. BENEFITS

Biometrics technology permits determination and verification of one’s identity through physical
characteristics and it turns your body in to your password. This is just like biometric techniques like
finger scan, facial scan, retina scan, hand scan etc. Two algorithms are proposed by taking biometric
techniques to authenticate an ATM account holder, enabling a secure ATM by image processing.
Biometrics is currently applied in various private and public sectors.

17
 8. CONCLUSION

We thus develop an ATM model that is more reliable in providing security by using facial
recognition software. 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. Biometrics as means of
identifying and authenticating account owners at the Automated Teller Machines gives the needed and
much anticipated solution to the problem of illegal transactions. In this paper, we have tried to proffer a
solution to the much dreaded issue of fraudulent transactions through Automated Teller Machine by
biometrics that can be made possible only when the account holder is physically present. Thus, it
eliminates cases of illegal transactions at the ATM points without the knowledge of the authentic owner.
Using a biometric feature for identification is strong and it is further fortified when another is used at
authentication level .

18
 9. BIBLIOGRAPHY

 https://www.ijraset.com/fileserve.php?FID=12912
 https://findbiometrics.com/solutions/facialrecognition/
 http://www.oasis-open.org/cover/wap-wml.html
 https://www.explainthatstuff.com

19