Fingerprint Authentication for ATM

Fingerprint
Authentication
for ATM
BY:-
Parul Varshney - 0919213069
Paras Garg - 0919213067
Upendra N. Giri - 0919213121G. L. Bajaj Institute of Technology, Gr
Noida

1. PROBLEM STATEMENT
2. OBJECTIVE
3. INTRODUCTION
4. APPROACHES / PROCEDURE
5. SOFTWARE REQUIREMENT AND SPECIFICATION
6. FLOW CHART
7. USE CASE DIAGRAM
8. E-R DIAGRAM
9. SEQUENCE DIAGRAM
10. ACTIVITY DIAGRAM
11. CLASS DIAGRAM
12. DFD
13. SNAPSHOTS
14. ADVANTAGES / DISADVANTAGES
15. CONCLUSION
CONTENT

PROBLEM STATEMENT
 In present scenario, traditional ATM system accepts only on the
PIN CODE security system, enabling the other person rather
than the owner to access the account very easily.
 This ensures that the traditional ATM system is not fully secured.

 The objective of our project is to provide biometric security
through fingerprint authentication in ATM application.
 The underlying principle is the phenomenon of biometrics
“AUTHENTICATION”, in this project we propose a method for
fingerprint matching based on matching algorithms.
OBJECTIVE

 The fingerprint is a person’s most unique physical characteristic.
 This software can pick only authentic
fingerprint out of crowd, extract that
fingerprint is compared from rest of
which those are stored in database.
 Fingerprint recognition software is based
on the ability to first recognize fingerprint,
in this technological fingerprint measure the
various features of each fingerprint.
INTRODUCTION

What Fingerprint Is?
 A fingerprint is the feature pattern of fingers (Figure 1), and each
fingerprint is unique, and every person has unique fingerprints. So
fingerprints have being used for identification.
 A fingerprint is composed of many ridges and furrows, fingerprints are
not distinguished by their ridges And furrows, but by Minutiae, which
are some abnormal points on the ridges (Figure 2).
 Two types of minutiae are called termination, which is the immediate
ending of a ridge and the other called bifurcation, which is the point
on the ridge from which two branches derive.
Figure 1 Figure 2

What is Fingerprint Authentication?
 The fingerprint authentication problem can be grouped into two sub-
domains i.e. fingerprint verification and fingerprint identification.
 Fingerprint verification is to verify the authenticity of one person by his
fingerprint and PIN Code and Fingerprint identification is by matching
the information of user such as PIN Code and Fingerprint matching.
Figure 2.2. Verification vs. Identification

Approaches For Fingerprint Recognition
 The first approach, which is minutiae-based, represents the fingerprint
by its local features, like terminations and bifurcations. This approach
has been intensively studied, also is the backbone of the current
available fingerprint recognition products.
 The second approach, which uses image-based methods, tries to do
matching based on the global features of a whole fingerprint image. It is
an advanced approach. And it is useful to solve some intractable
problems of the first approach.

SOFTWARE REQUIREMENT
SPECIFICATION (SRS)

INTRODUCTION
 Purpose
This Software Requirements Specification provides a complete description
of all the functions and specifications of the ATM system of bank. The
purpose is to provide extra security to the ATM systems
 Scope
The ATM system is designed to run for 24 hours and to allow bank clients
to carry out transactions in a secured way. The data will be held in a bank
database. The system is connected to the bank database using a modem.
 Document Overview
The remainder of this document is two chapters, the first providing a full
description of the project for the bank’s ATM with fingerprint security. This
SRS gives the details about the various requirements & about the various
hardware & software interfaces.

OVERALL DESCRIPTION
The ATM system encompasses various GUI menus including the SENSOR,
to provide high security. It provides secure access to the account of a
customer. The ATM must be able to provide the following services to the
customer:
Enter Pin: A customer is allowed to enter the PIN Code for his/her Account.
Change Pin: A customer must be able to change the pin linked to the card.
Enroll Finger: A customer is allowed to enroll the fingerprint impression
which has been used to provide security to the Account
Change Fingerprint: A customer is allowed to change the fingerprint
impression.

Functional Requirements Definition
The software to be designed will control a simulated automated teller
machine (ATM) having :
 A sensor to enroll and detect fingerprint.
 A customer console (keyboard and display) for interaction with the
customer.(for entering PIN Code)

 Facility of Aborting transaction
A customer must be able to abort a transaction in progress by pressing the
Cancel key instead of responding to a request from the machine.
 PIN Code format
Pin should be of exactly 4 digit.
 Facility of PIN Re-entering
If the customer's PIN is invalid, the customer will be required to re-enter
the PIN before a transaction can proceed.
 Denial of service, if PIN goes wrong.
If the customer is unable to successfully enter the PIN after three tries, the
service would be denied for particular card.

 Enroll finger
Enroll your finger from first joint to the tip.
 Facility of Re-enrolling the finger
If the customer's Fingerprint is invalid, the customer will be required to re-
enroll the Fingerprint before a transaction can proceed.
 Denial of service, if fingerprint goes wrong
If the customer is unable to successfully enroll fingerprint after three tries,
the service would be denied for that particular card.
 Explanation of problem
If a transaction fails for any reason other than an invalid PIN and
fingerprint, the ATM will display an explanation of the problem.

NON FUNCTIONAL REQUIREMENT
There are requirements that are not functional in nature. Specifically,
these are the constraints the system must follow. They are often called
qualities of a system. Other terms for non-functional requirements are
“constraints”,” quality attributes”,” quality goals”,” quality of service
requirements” and “non-behavioral requirements”.
 Scope: The scope of this project is to allow the user to get access to
their account through the ATM using fingerprinting functionality.
 Functionality: One customer at a time can process their account in the
ATM machine.
 Usability: The desktop user interface shall be Windows 95/98/2000/XP/7
complaint.
 Reliability: The ATM machine must be able to scan or read the card and
the fingerprint properly and identify the customer account.

 Performance: The ATM machine support only one customer at a time.
The speed and accurate transaction decides the performance factor.
The screen must be clearly visible to the user.
 Security: The pin number and the fingerprint in the card guarantee the
security of a customer’s account. The ATM system must not store any
of this data in its database. The customer with a pin number and a valid
card with valid fingerprint impression is allowed to do all transactions.

For developing the front – end interface, we have decided to use
ASP.NET platform, with C# as the programming language, due to the
following reasons:-
 Easy to use and flexible interface.
 A number of options for customizability.
 Proven to provide good performance and high reliability.
 Attractive and visually pleasing interface.
For developing the database (back – end), we have decided to use
MS-SQL Server 2008 database, due to the following reasons:-
 Native support and full compatibility with ASP.NET platform .
 Flexible, scalable and robust database architecture.
 Used by market-leading companies worldwide.
 Strong data protection and ease of management.
FRONT END DESCRIPTION
BACK END DESCRIPTION

Tools Used:
 Database - MS SQL Server 2008 R2
 Processor - Pentium 4
 Hard Disk - 5 GB
 RAM - 256 MB
 Sensor - Fingerprint Recognizer
 Operating System - Windows 7
 Database System - MS SQL Server 2008 R2
 Front End - Visual Studio 2010
 Framework - .NET Framework 4.0
DATABASE DESCRIPTION
HARDWARE REQUIREMENT
SOFTWARE REQUIREMENT

Fingerprint Authentication for ATM

1. Very high accuracy and security
• Identification (Do I know who you are?)
• Verification (Are you who you claim to be?)
2. Is the most economical biometric PC user authentication
technique.
3. It is one of the most developed biometrics.
4. Easy to use.
5. Small storage space required for the biometric template, reducing
the size of the database memory required.
6. It is standardized.
7. Enhance traditional methods (PINs, Passwords).
ADVANTAGES

 General Limitations
1. Misidentification
 False Acceptance
 False Rejection
2. Privacy
3. Image captured at 500 dots per inch(dpi). Resolution: 8 bits per pixel.
A 500 dpi fingerprint image at 8 bits per pixel demands a large
memory space, 240 KB approximately  Compression required ( a
factor of 10 approximately).
 Limitations for individual
1. Dry, wet or dirty hands.
2. For some people it is very intrusive, because it is still related to
criminal identification.
DISADVANTAGES

 A smartcard based ATM fingerprint authentication scheme has been
proposed. The possession (smartcard) together with the claimed user’s
Biometrics (fingerprint) is required in a transaction. The smartcard is used for
the first layer of mutual authentication when a user requests transaction.
Biometric authentication is the second layer. The fingerprint image is
encrypted via 3D map as soon as it is captured, and then is transmitted to
the central server via symmetric algorithm. The encryption keys are extracted
from the random pixels distribution in a raw image of fingerprint.
 The stable features of the fingerprint image need not to be transmitted, it can
be extracted from the templates at the central server directly.
 After this, the minutiae matching is performed at the central server. The
successful minutiae matching at last verifies the claimed user. Future work
will focus on the study of stable features (as part of encryption key) of
fingerprint image, which may help to set up a fingerprint matching dictionary
so that to narrow down the workload of fingerprint matching in a large
database.
CONCLUSION

REFERENCES
 Bhanu Bir, Tan Xuejun, Computational Algorithms for
Fingerprint Recognition
 Kluwer Academic Publishers, 20 Das, K. Design and
Implementation of an Efficient Thinning Algorithm
 Bachelor of Technology thesis, Department of
Computer Science and Engineering, Indian Institute of
Technology, Kanpur
 Hong, L., Wan, Y. and Jain, A. Fingerprint Image
Enhancement: Algorithm and Performance Evaluation.
 IEEE Transactions on Pattern Analysis and Machine
Intelligence,1998

Fingerprint Authentication for ATM

More Related Content

What's hot (20)

Viewers also liked (18)

Similar to Fingerprint Authentication for ATM (20)

Recently uploaded (20)

Fingerprint Authentication for ATM