Sei sulla pagina 1di 24














This is to certify that Project Report entitled


Submitted by

Mr. Shubham Patil (Exam No.)

Mr. Krunal Vedpathak (Exam No.)
Mr. Abhijeet Jamdar (Exam No.)

is the record of bonafide work carried out by them in partial fulfillment of the
requirement for the award of the Degree of Bachelor of Engineering (Electronics
and Telecommunication), as prescribed by the Savitribai Phule Pune University in
the Academic Year 2018-2019.(14-Times new Roman)
This project report has not been earlier submitted to any other Institute or University
for the award of any degree or diploma.(12/ sentence case)

<<Name >> Dr.M.P.Sardey

Internal Guide Head of Department

Department of E&TC Engg. Department of E&TC Engg.

<<Name >> Dr.P.B.Mane

External Examiner Principal
AISSMS Institute Of Information Technology,
Date : .
(It has to be on the letter head of the Company)

It is my great pleasure in expressing sincere and deep gratitude towards my

guide Mrs/Mr S.B.Pokharkar ,Assistant Professor Electronics &
Telecommunication Engineering Department for her/his valuable guidance and
constant support throughout this work and help to peruse additional studies in
IOT(domain of project).

We take this opportunity to thank Head of the Department Dr.M.P.Sardey and

Project coordinator Mrs/Mr S.S.Nikam and all staff members of department of
Electronics &Telecommunication Engineering AISSMS IOIT, Pune, for cooperation
provided by them in many ways.
The motivation factor for this work was the inspiration given by our honorable
principal Dr. P.B.Mane.

Lastly I am thankful to those who have directly or indirectly supported for our

Sign Sign Sign

Shubham Patil Krunal Vedpathak Abhijeet Jamdar

Automated Teller Machine (ATM) transactions are found safe, reliable

and inevitable these days for fulfilling our financial commitments.
Traditional approach for using ATM mandates involvement of Debit card.
But however, people do experience times when their account lacks
balance amount or they forget to carry card and struggle to complete
transaction. With the growing sector of banking, everyone is using ATM
machines as these machines are located in different places and the
customer can access his Account anytime anywhere. A customer holding
a bank Account can access the Account from ATM systems by getting a
PIN or password confidentially from bank. By scratching the ATM card
into the machine and entering PIN number, one can easily perform
transaction, transfer money, etc. PIN number is a crucial aspect used to
secure information of customer’s Account, thus should not be shared with
others. In this regard, an intuitive approach is to introduce biometric
authentication technique in ATM systems, Although various biometric
technique like- fingerprint, eye recognition, retina and iris recognition,
etc. have been devised as an authentication method for ATM machines,
still there is need to enhance the security in ATM systems to overcome
various challenges.
We know that, parallel to ATM usage, mobile phones’ usage has also been
an inevitable trend. Establishing a connection between these e-gadgets
has ignited a simple and effective approach to withdraw cash without the
involvement of debit card which can be referred to as card less cash
withdrawal. When OTP and Fingerprint are matched then customer’s
account will open in ATM machine.
This project focuses on developing a cardless cash access using biometric
atm security system using fingerprint and OTP. Fingerprint and One-Time
Password (OTP) are used for the enhancement of security of accounts and
privacy of users.

Keywords: Biometric identification, Card less ATM, One-Time Password






List Of Tables
List Of Figures
List Of Abbreviations
1.1 Information about the system
1.2Overview of the target for the final system
1.3 Overview of the technical area
1.4 Summary of the system functionality
1.5 Overview of report
2.1 Summary of Litarature Survey
5 Specifications of the system
5.1 Functionality provided by system
5.2 System interfaces, inputs and outputs
5.3 Expected outcomes
5.4 system requirements
6.1 System architecture diagram
6.2 Working of the system
7.1 Rapsberry pi
7.2 Keypad
7.4 Fingerprint Module

1.1.1 Information about the system

ATM is an electronic device which provides the user to perform

transactions without the need of cashier, bank teller. ATM services are
popular because of their easiness for banking systems. In modern ATMs,
the customer account can be identified by inserting a plastic card with
magnetic strip that contains his or her account number. The customer then
verifies his or her identity by entering a pass code (i.e.) personal
identification number (PIN) of four digits. If the number is entered
incorrectly several times consequently (usually the, most ATMs will
retain the card as security precaution to prevent an authorized user from
assuming the PIN by guesswork and so on. Moreover, the customer has to
pay transaction fees. In the proposed system, the person with the card
needs to swipe the card first and then ATM asks for the fingerprint
authentication. ATM requires user authentication for any transaction.
Currently customers use’s smartcard for the transaction which can be lost,
duplicated, stolen or impersonated with accuracy. In traditional ATM
system, customer recognition only based on smartcards, passwords, and
some identity verification methods which are not genuine. By unique
feature or characteristic biometric system provides automatic
authentication for any customer.
start Input Select
card language
1.1.2 Overview of the target for the final system
Safety plays a major role in today’s world. In modern world, numerous of
people are dependent on computers for keeping major record of data.
Data are transferred in a cost-effective manner across wide area. ATM
was invented by John Shepphard baren on June 1967 at United Kingdom.
It first came in India in 1968. Today, many people have PIN’s and
password for operating multiple devices like car, mobile, ATM machines;
herein using PIN’s without safety results in a major difficulty faced by
customers like usability, memorability and security. Some people used to
write their PIN on some diary which is not at all secure. As, it can be
easily attacked and hacked by someone, resulting the account holder can
suffer. In this regard, an intuitive approach is to introduce biometric
authentication technique in ATM systems, i.e. face recognition and OTP.

1.1.3 Overview of the technical area

This project helps to overcome the problem of complexity and provides
easiest way to secure the ATM transaction. We are designing a cardless
ATM system, that uses biometric identification technique namely, face
recognition and OTP system to verify the user. Camera is used to capture
image of the user. The user swipes his/her ATM card. Camera captures
the user image and an OTP will be sent to the user. If the image and OTP
matches, the transaction will be proceeded or else transaction will, be
1.1.4 Summary of the system functionality

Fingerprint is used for authentication of user. The user will swipe the
ATM card. If it matches, an OTP will be sent to the corresponding
registered mobile number. This randomly generated code has to be
entered by the user in the textbox. If the user correctly enters the OTP, the
transaction can proceed.

1.1.5 Overview of report

We are developing a cardless cash access using biometric atm security
system using face recognition and OTP.
Features like fingerprint and One-Time Password (OTP) are used for the
enhancement of security of accounts and privacy of users. Fingerprint
technology helps the machine to identify each and every user uniquely.
This completely eliminates the chances of fraud due to theft and duplicity
of the ATM cards. Moreover, the randomly generated OTP frees the user
from remembering PINs as it itself acts as a PIN.


Manual banking is based on paper and time-consuming. A customer has

to go to branch physically, do cash withdrawal using a check or ask the
teller to inform him about his balance which is very much annoying
sometimes. ATM is invented to remove this hassle as it is self-servicing,
no teller is needed. Customers can use this machine 24/7 basis. They can
access it whenever they want whatever the time of day is. Life becomes
very easy with the advent of ATM. People can access their bank account
through balance inquiry, withdraw cash, transfer fund etc using ATM. It
makes all these transactions paperless.
The existing ATM system authenticates transactions via the card and PIN-
based system. Thereafter, it grants access to bank customers to several
services such as cash withdrawal and deposits, account to account
transfers, balance enquiry, top-up purchases and utility bills payment. The
ATM system compares the PIN entered against the stored authorization
PIN for every ATM users. If there is a match, the system authenticates the
user and grants access to all the services available via the ATM. If there is
a mismatch on the other hand, the user authentication process fails and
the user is given two more opportunities to enter a correct PIN. If an
incorrect PIN is entered for the third time, the card gets blocked and
retained by the ATM.

To avail the above facilities, the bank provides a plastic card to

customers. But the plastic card has some disadvantages. It can be lost,
damaged, expired or skimmed. To overcome these disadvantages, Imran
et al [1] proposed a new model for the cardless transaction which uses
BPIN and OTP for secure authentication. The BPIN is used to identify
issuer institution; customer type and category of facilities are enrolled for
that customer.

Automatic Teller Machines (ATMs) transactions are an important role for

obtaining money using credit or debit cards; hence they need to be secure
and trustworthy. Shoulder-surfing or observation attacks, including card
skimming and video recording with hidden cameras while users perform
transactions at point-of-service terminals is one of the common threats for
common users. In system proposed in [2], a secure authentication
protocol for performing transaction in Automatic Teller Machines
(ATMs) using mobile application is developed. This approach protects the
user from illegal use of credit/debit cards and partial observation attacks,
and is also against to relay, replay, and intermediate transaction attacks in
the transaction process. Users use an mobile application installed in their
personal mobile device for scanning a Quick Response (QR) code on the
screen to initiate the transaction and obtain a secure One-Time-Password
(OTP) for authentication. By using this proposed system, the security is
enhanced while providing less complexity on the user side.

The current ATM (Automated Teller Machine) system uses ATM card and
PIN (Pin Identification Number) for authentication. This system is likely
to be harmed by many security issues such as theft of ATM card,
skimming, Lebanese loop etc. So in this paper, we propose a system that
uses fingerprint and face recognition authentication (not ATM cards) for
accessing user account along with PIN which is more secure and reliable
than the existing system. Here we are using the CNN model for face
recognition and Minutiae feature extraction for fingerprint recognition
Research presented in [4] looked into the development of a system that
integrates facial recognition technology into the identity verification
process used in ATMs. An ATM model that is more reliable in providing
security by using facial recognition software is proposed. The
development of such a system would serve to protect consumers and
financial institutions alike from intruders and identity thieves. This paper
proposes an automatic teller machine security model that would combine
a physical access card, a PIN, and electronic facial recognition that will
go as far as withholding the fraudster’s card. If this technology becomes
widely used, faces would be protected as well as PINs. However, it
obvious that man’s biometric features cannot be replicated, this proposal
will go a long way to solve the problem of Account safety making it
possible for the actual account owner alone have access to his accounts.
The combined biometric features approach is to serve the purpose both
the identification and authentication that card and PIN do.


Authentication is the process of determining whether a person is who he
or she claims to be. This process can occur in one of two ways.
Verification asks “Is this the person who he or she claims?” and consists
of a single comparison. Identification makes a one-to-N comparison and
tries to determine if the person is one of the N people. Several factors,
such as what you know, what you have, or what you are can be used for
authentication, with all three options having strengths and weaknesses.
For improved security, it is advisable to use more than one factor, if
Biometric authentication is a “what you are” factor and is based on
unique individual characteristics.
Advantages of biometric systems:
 Improved security
 Improved customer experience
 Cannot be forgotten or lost
 Reduced operational costs
Biometric Authentication with OTP Password is a stronger method of
authentication and verification as it is uniquely bound to individuals. It is
a viable approach, as it is easy to maintain and operate with lower cost. In
this project, a technique for ATM system is introduced for secure
transaction with OTP Password or biometric to do the transaction. This
Technique is more secure in comparison to the atm biometric system. In
biometric we can access the account but when OTP password option is
included at the time of transaction then one security point is increased. At
the time of transaction if OTP password does not match, then the
customer cannot access the account.

3. AIM

As the number of ATM units increase, the machines are prone to hacker
attacks, fraud, robberies and security breaches. In the past, the main
purpose of ATMs was to deliver cash in the form of bank notes, and to
debit a corresponding bank account. However, ATMs are becoming more
complicated, and they serve numerous functions, thus becoming a high
priority target to robbers and hackers.
Identification and verification of a person today is a common thing;
which may include door-lock system, safe box and vehicle control or
even at accessing bank accounts via ATM, etc which is necessary for
securing personal information. The conventional methods like ID card
verification or signature does not provide perfection and reliability. The
systems employed at these places must be fast enough and robust too.
Use of the ATM (Automatic Teller Machine) which provides customers
with the convenient banknote trading is facing a new challenge to carry
on the valid identity to the customer. Since, in conventional identification
methods with ATM, criminal cases are increasing making financial losses
to customers. The best choice in today’s world is to choose biometric
authentication technique. One of the main motive of biometric card ATM
machine is to prevent unauthorized access means everyone cannot access
the ATM means user should present then the access the ATM otherwise
not to access the Account.
Hence, we are designing a cardless ATM system wherein the user will be
able to make the transaction if and only if he successfully goes through
two step verification process. The first is face recognition where the
camera will capture the image of user and second, where the system will
send OTP to the user. If the image and entered OTP by the user matches,
only then the user will be able to proceed with his/her transaction.

1. To study the existing security systems used in ATM’s.
2. To study the biometric authentication process using face
3. To study image processing.
4. Make a note of hardware and software requirements.
5. Interface keypad, GSM with the controller.
6. Implement the image processing and OTP part.
7. Test the working of the system.


5.1 Functionality provided by the system
The system has two step verification process. First as the user swipes the ATM card,
camera will capture the image of the user. Next an OTP will be sent to the users
mobile number. User has to correctly enter this OTP in the system. Once the image
and OTP are matched, the user can proceed with their required transaction.
5.2 System interfaces, inputs, and outputs
Finger scaned by fingerprint sensor.
OTP to be entered by user.
Depending on the matching of image and OTP, the system will decide whether to
proceed further to make a transaction or decline it.
Camera and the image processing section is interfaced to Raspberry Pi controller.
Keypad and GSM are also interfaced to raspberry Pi controller.

5.3 Expected Outcomes

 Camera should clearly capture the image of the user.
 The decision for captured image, compared along with the data in database
should be accurately decided and sent to controller.
 OTP should be sent to the registered mobile number.
 The received OTP should be entered into the system before system timeout.

5.4 System Requirement

i. Hardware Requirement
 Camera
 Raspberry Pi
 Keypad.

ii. Software requirement

 Open CV
 SD card formatter
 Disk imager
 Raspbian OS
6.1 System Architecture Diagram
System consists of fingerprint sensor, keypad and GSM interfaced with Raspberry Pi.
It consists of image processing part for further processing of captured image.
Following is the block diagram of the proposed system.

Power supply

Finger Print (Raspbery pi)

Fig : Block diagram of proposed system

6.2 Working of the System

Above figure represents the block diagram of the proposed system.

Camera is used for authentication of user. We are using Keypad and
camera of PC/laptop. First, the user will swipe the ATM card. A live
image is captured automatically through a webcam installed on the ATM,
which is compared with the image stored in the database. If it matches,
an OTP will be sent to the corresponding registered mobile number. This
randomly generated code has to be entered by the user in the textbox. If
the user correctly enters the OTP, the transaction can proceed. Therefore,
the combination of face recognition algorithm and an OTP drastically
reduces the chances of fraud plus frees a user from an extra burden of
remembering complex passwords.

Image processing: Input to the system is image captured by camera. Pre-

processing images commonly involves removing low-frequency
background noise, normalizing the intensity of the individual particle’s
images, removing reflections, and masking portions of images. Image
pre-processing is the technique of enhancing data images prior to
computational processing. Feature extraction involves reducing the
amount of resources required to describe a large set of data. When
performing analysis of complex data one of the major problems stems
from the number of variables involved. Feature extraction is a general
term for methods of constructing combinations of the variables to get
around these problems while still describing the data with sufficient
accuracy. Image classification refers to the task of extracting information
classes from a multiband raster image. The resulting raster from image
classification can be used to create thematic maps. Depending on the
interaction between the analyst and the computer during classification,
there are two types of classification: supervised and unsupervised.


7.1 Raspberry Pi:

RASPBERRY PI is a development board in PI series. It can be considered as a single

board computer that works on LINUX operating system. The board not only has tons
of features it also has terrific processing speed making it suitable for advanced
applications. PI board is specifically designed for hobbyist and engineers who are
interested in LINUX systems and IOT (Internet of Things).
Fig: Raspberry Pi.
 Hardware
• Low cost
• Low power
• High availability
• High reliability – Tested over millions of Raspberry Pis Produced to date –
Module IO pins have 35u hard gold plating.
 Peripherals
• 48x GPIO
• 2x I2C
• 2x SPI
• 2x UART
• 2x SD/SDIO
• 1x HDMI 1.3a
• 1x DPI (Parallel RGB Display)
• 1x NAND interface (SMI)
• 1x 4-lane CSI Camera Interface (up to 1Gbps per lane)
• 1x 2-lane CSI Camera Interface (up to 1Gbps per lane)
• 1x 4-lane DSI Display Interface (up to 1Gbps per lane)
• 1x 2-lane DSI Display Interface (up to 1Gbps per lane).
 Software
• ARMv6 (CM1) or ARMv7 (CM3, CM3L) Instruction Set
• Mature and stable Linux software stack
– Latest Linux Kernel support
– Many drivers upstreamed
– Stable and well supported userland
– Full availability of GPU functions using standard APIs.

7.2 Keypad:
A keypad is a set of buttons arranged in a block or "pad" which bear digits, symbols
or alphabetical letters. Pads mostly containing numbers are called a numeric keypad.
Numeric keypads are found on alphanumeric keyboards and on other devices which
require mainly numeric input such as calculators, push-button telephones, vending
machines, ATMs, Point of Sale devices, combination locks, and digital door locks.

Fig: Keypad
Many devices follow the E.161 standard for their arrangement. 4X4 keypad
MODULES are available in different sizes and shapes. But they all have same pin
configuration. It is easy to make 4X4 keypad by arranging 16 buttons in matrix
formation. In them four are rows of matrix and four are columns of matrix. These 8
PINS are driven out from 16 buttons present in the MODULE.
7.3 GSM:
A GSM module or a GPRS module is a chip or circuit that will be used to establish
communication between a mobile device or a computing machine and
a GSM or GPRS system. GSM (Global System for Mobile Communications), is a
standard developed by the European Telecommunications Standards Institute (ETSI).
It was created to describe the protocols for second-generation (2G) digital cellular
networks used by mobile phones and is now the default global standard for mobile
communications – with over 90% market share, operating in over 219 countries and

Fig: GSM Module

A GSM module or a GPRS module is a chip or circuit that will be used to establish
communication between a mobile device or a computing machine and a
GSM or GPRS system. The modem (modulator-demodulator) is a critical part here.
These modules consist of a GSM module or GPRS modem powered by a power
supply circuit and communication interfaces (like RS-232, USB 2.0, and others) for
computer. A GSM modem can be a dedicated modem device with a serial, USB
or Bluetooth connection, or it can be a mobile phone that provides GSM modem
8.1 Modules in the project
8.2 Diagram
i. Entity relationship diagram
ii. Data flow diagram
iii. UML diagram

a) Use case diagram

b) Class Diagram
c) Package diagram
d) Sequence diagram
e) Communication diagram
f) Activity diagram
g) State machine diagram
h) Component diagram
i) Deployment diagram
8.3 Mathematical Concept Used (Regarding all algorithms used to
Implement system)
8.4 Feasibility Study
8.5 Software Development Life Cycle Phases
9.1 It must include the tables and graphs that shows the quantitative result
(Should cover comparison analytical or statistical result from literature survey and
expected result for proposed system)
Conclusion must relate with the abstract and the project. (Maximum 600 words). The
conclusion must include your concluded quantitative result.


[1] Md. Al Imran M.F. Mridha Md. Kamruddin Nur “OTP Based Cardless
Transction using ATM”, DOI: 10.1109/ICREST.2019.8644248 Conference:
2019 International Conference on Robotics,Electrical and Signal Processing
Techniques (ICREST)
[2] Bharathiraja N, Ravindhar N.V, Loganathan V, “Secure PIN Authentication for
ATM Transaction using Mobile Application”, International Journal of Soft
Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-6 Issue-2, May
[3] Ayusha Mohite1, Shruti Gamare2, Karan More3, Nita Patil “Deep Learning
based Card-Less Atm using Fingerprint and Face Recognition Techniques”,
International Research Journal of Engineering and Technology (IRJET) e-
ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 p-ISSN:
2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008
Certified Journal | Page 3504
[4] American Journal of Engineering Research (AJER) e-ISSN : 2320-0847 p-
ISSN : 2320-0936 Volume-02, Issue-05, pp-188-193 Research
Paper Open Access Facial Verification Technology for Use In Atm Transactions
Aru, Okereke Eze, Ihekweaba Gozie

Attach the List of Certificates.
Hard copy of papers presented at National/International conferences/journals
and Project Competitions.
Also attach the CD at the end of report. (Including Presentation, Report,
Literature Survey papers, Video of working of the project.)