A MINI-PROJECT REPORT ON

FINGERPRINT BASED ON ATM SYSTEM.

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

MASTER OF COMPUTER APPLICATIONS

Submitted by:

GAJULAPALLI NAGA VYSHNAVI.

(22091F0029)

Under the Guidance of

Mr. V. V. NAGENDRA KUMAR, M. Tech, (Ph. D)
Asst. Professor in Dept. of MCA

DEPARTMENT OF MASTER OF COMPUTER APPLICATIONS

RAJEEV GANDHI MEMORIAL COLLEGE OF ENGINEERING & TECHNOLOGY
(AUTONOMOUS)
AFFILIATED TO J.N.T UNIVERSITY ANANTAPUR. ACCREDITED BY NBA (TIER-1) &
NAAC OF UGC. NEW DELHI, WITH A+ GRADE
RECOGNIZED UGC-DDU KAUSHAL KENDRA
NANDYAL-518501, (Estd-1995)
YEAR: 2023-2024
 Rajeev Gandhi Memorial College of Engineering &Technology
(AUTONOMOUS)
AFFILIATED TO J.N.T UNIVERSITY ANANTAPUR. ACCREDITED BY NBA (TIER-1) &
NAAC OF UGC. NEW DELHI, WITH A+ GRADE
RECOGNIZED UGC-DDU KAUSHAL KENDRA
NANDYAL-518501, (Estd-1995)

(ESTD – 1995)

DEPARTMENT OF MASTER OF COMPUTER APPLICATIONS

CERTIFICATE
This is to certify that GAJULAPALLI NAGA VYSHNAVI (22091F0029), of MCA III-
semester, has carried out the mini-project work entitled “FINGERPRINT BASED ON ATM
SYSTEM” under the supervision and guidance of Mr. V. V. NAGENDRA KUMAR, Assistant.
Professor, MCA Department, in partial fulfillment of the requirements for the award of Degree of
Master of Computer Applications from Rajeev Gandhi Memorial College of Engineering &
Technology (Autonomous), Nandyal is a bonafied record of the work done by her during 2023-
2024.

Project Guide Head of the Department

Mr. V.V. NAGENDRA KUMAR Dr. K. Subba Reddy MTech, Ph.D.

M. Tech, (Ph.D).
Professor, Dept. of CSE
Assistant Professor,

Dept. of MCA

Place: Nandyal External Examiner

Date:
 ACKNOWLEDGEMENT

I manifest my heartier thankfulness pertaining to your contentment over my project guide

Mr. V.V. NAGENDRA KUMAR, Asst. Prof, M. Tech, (Ph.D) in Department of MCA with whose
adroit concomitance the excellence has been exemplified in bringing out this project to work with
artistry.

I express my gratitude to Dr. K. Subba Reddy garu, Head of the Department of Computer
Science Engineering & MCA departments, all teaching and non-teaching staff of the Computer
Science Engineering department of Rajeev Gandhi memorial College of Engineering and
Technology for providing continuous encouragement and cooperation at various steps of my
project.

Involuntarily, I am perspicuous to divulge my sincere gratefulness to our Principal, Dr.

T. Jaya Chandra Prasad garu, who has been observed posing virtue in abundance towards my
individuality to acknowledge my project work tangentially.

At the outset I thank to honorable Chairman Dr. M. SanthiRamudu garu, for providing us
with exceptional faculty and moral support throughout the course.

Finally, I extend my sincere thanks to all the Staff Members of MCA & CSE Departments
who have co-operated and encouraged us in making my project successful.

Whatever one does, whatever one achieves, the first credit goes to the Parents be it not for
their love and affection, nothing would have been responsible. I have seen every good that happens
to us their love and blessings.

BY
GAJULAPALLI NAGA VYSHNAVI (22091F0029)
 CONTENTS
CHAPTER PAGE NO.

1. INTRODUCTION 1

1.1. Purpose 1

1.2. Scope 1

1.3. Need for system. 2

2. LITERATURE SURVEY 3

2.1. Literature review 1 3

2.2. Literature review 2 3

2.3. Literature review 3 3

2.4. Existing System 4

2.4.1. Disadvantages 4

2.5. Proposed System 4

2.5.1. Advantages 4

3. SYSTEM MODEL / DESIGN 5

3.1 System Narration 5

3.1.1 Algorithms 5

3.1.1.1 Linear Regression 6

3.1.1.2 Decision Tree 6

3.2 Modules 7

3.3 Software development life cycle (SDLC) 8

3.4 Spiral Model 9

3.5 Feasibility Study 10

3.5.1 Economic Feasibility 10

3.5.2 Specialized Feasibility 10

3.5.3 Social Feasibility 11

3.6 Functional Requirements 11

3.7 Non-Functional Requirements 11

 3.8 Visual Modelling 12
3.8.1 UML Diagrams 13

3.8.1.1 Use case Diagram 14

3.8.1.2 Class Diagram 15

3.8.1.3 Sequence Diagram 16

3.8.1.4 Activity Diagram 17

3.8.1.5 Component Diagram 18

3.8.1.6 Deployment Diagram 19

3.9 Hardware & Software Requirements 19

3.9.1 Software Requirements 19

3.9.2 Hardware Requirements 19

4. IMPLEMENTATION 20

4.Programming Language 20

4.1 Overview of python 20

4.2 Python Features 21

4.2.1 Advantages of python 22

4.2.2 Disadvantages of python 23

4.2.3 Overview of machine learning 26

4.2.4 Categories of machine learning 26

4.2.5 Need for machine learning 27

4.2.6 Advantages of machine learning 27

4.2.7 Disadvantages of machine learning 28

4.3 Features used in project 29

4.4 Normalization 30

4.4.1 First Normal Form(1NF) 31

4.4.2 Second Normal Form(2NF) 31

4.4.3 Third Normal Form(3NF) 32

4.4.4 Fourth Normal Form(4NF) 32

5.TESTING 34

5.1 Testing Methodologies 34

5.1.1 Unit Testing 34

5.1.2 Co-ordination Testing 34

5.1.3 Integration Testing 34

5.1.4 User acceptance Testing 35

5.1.5 Output Testing 35

5.1.6 Test Case Results 36

6.FUTURE ENHANCEMENT 37

7.CONCLUSION 38
Appendix: Screenshots 39

Bibliography 44
 LIST OF FIGURES

FIG NO. NAME OF THE FIGURE PAGE NO.

Fig: 1 System Architecture 5

Fig: 2 Linear Regression Graph 6

Fig: 3 Decision Tree 7

Fig: 4 Software Development Life Cycle (SDLC) 9

Fig: 5 Spiral Model 10

Fig: 6 Use-case Diagram 14

Fig:7 Class Diagram 15

Fig: 8 Sequence Diagram 16

Fig: 9 Activity Diagram 17

Fig:10 Component Diagram 18

Fig:11 Deployment Diagram 19

TABLES PAGE NO.

1. Data dictionary 25

2. Data table 25

3. 1NF 31

4. 2NF 31

5. User details 32

6. User details 32

7. Test Case Results 36

 ABSTRACT
The main aim of this project to provide secure banking system, by taking fingerprints as
authorized identity at ATM/banks. The purpose of the project is to provide a secured and
reliable environment to the customers for their banking transactions by providing a unique
identity to every user using the FINGER PRINT identification technology. 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, which is
necessary for securing personal information. The conventional methods like ID card
verification or signaturedoes not provide perfection and reliable. The systems employed at
these places must be fast enough and robust too. Use of the ATM (Automatic Teller
Machine) which provides customerswith the convenient banknote trading is facing a new
challenge to carry on the valid identity tothe customer. Since, in conventional identification
methods with ATM, criminal cases are increasing making financial losses to customers.
Fingerprint Based ATM is a desktop application where fingerprint of the user is used as a
authentication. The finger print minutiae features are different for each human being so the
user can be identified uniquely. Instead of using ATM card Fingerprint based ATM is safer
and secure. There is no worry of losing ATM card and no need to carry ATM card in your
wallet.
FINGERPRINT BASED ATM SYSTEM

CHAPTER-I
INTRODUCTION
1.1 Purpose

Biometrics is the art of science and technology of measuring and analyzing biological data. If
biometrics refers to technologies that measure and analysis human body characteristics, such
as DNA, fingerprinting, eye retina and irises, voice pattern, facial pattern and measurement for
authentication purposes. Biometrics identifier method provides several advantages over the
traditional method and current method used in our daily life. Basically concentrate on two
function one is for identification and other verification. A modern ATM is typically made up
of the devices like CPU to control the user interface and devices related to transaction, magnetic
or chip card reader to identify the customer, Pin pad, secure crypto-processor generally within
a secure cover.

Display to be used by the customer for performing the transaction, function key button, record
printer to provide the customer with a record of their transaction, to store the parts of the
machinery requiring restricted access- vault, housing for aesthetics, sensors and indicators. In
this modern era there are many people using ATM. Fast development of banking has various
advantages and disadvantages.

1.2 Scope

The main objective of this system is to develop an embedded system, which is used for ATM
security applications. In these system Bankers will collect the customer fingerprints while
opening the accounts then customer will only access ATM machine. The working of these
ATM machine is when customer place finger on the finger print module it displays the name
of the customer on the LCD connected to the micro controller. If the user does not have a
account activated by a fingerprint initially it does not allow the user to do transactions.
Nowadays, using the ATM (Automatic Teller Machine) which provides customers with the
convenient banknote trading is very common. However, the financial crime case rises
repeatedly in recent years; a lot of criminal tampers with the ATM terminal and steal user's
credit card and password by illegal means. Once user's bank card is lost and the password is
stolen, the criminal will draw all cash in the shortest time, which will bring enormous financial
losses to customer. How to carry on the valid identity to the customer becomes the focus in
current financial circle.

DEPT. OF MCA, RGMCET, NANDYAL 1 page

FINGERPRINT BASED ATM SYSTEM

1.3 Need For System

We are using ATMs in our country for all our banking activities. An automated teller machine
(ATM) is an electronic telecommunications device that enables customers of financial
institutions to perform financial transactions, such as cash withdrawals, deposits, transfer
funds, or obtaining account information, at any time and without the need for direct interaction
with bank staff. On most modern ATMs, customers are identified by inserting a plastic ATM
card (or some other acceptable payment card) into the ATM, with authentication being by the
customer entering a personal identification number (PIN), which must match the PIN stored in
the chip on the card (if the card is so equipped), or in the issuing financial institution's database.

Using an ATM, customers can access their bank deposit or credit accounts in order to make a
variety of financial transactions such as cash withdrawals, check balances, or credit mobile
phones. ATMs can be used to withdraw cash in a foreign country. If the currency being
withdrawn from the ATM is different from that in which the bank account is denominated, the
money will be converted at the financial institution's exchange.

Most biometric technology systems use the same basic principles of operation. First, a person
must be registered, or enrolled, on the biometric system.

DEPT. OF MCA, RGMCET, NANDYAL 2 page

FINGERPRINT BASED ATM SYSTEM

CHAPTER -II

LITERATURE REVIEW
2.1 A Review on Securing ATM System Using Fingerprint:

AUTHOR: Saima Rafat Bhandari.

Biometric systems have overtime served as robust security mechanisms in various domains.
Fingerprints are the newest and most widely used form of biometric identification. The use of
fingerprint for identification has been employed in law enforcement for about a century. A
much broader application of fingerprint is for personal authentication, for instance to access a
computer, a network, an ATM machine, a car or a home. The method uses 3D analysis of the
finger for tracking and identification purposes.This recorded biostatistics information is then
stored for future use. Companies have used this type of biometrics for attendance tracking and
accessing secure entrances.

2.2 A Survey on Cardless Cash Access Using Biometric ATM Security

System:
AUTHOR: Vijayraj A
All the biometrics, fingerprint recognition is one of the most reliable and promising personal
identification technologies. Fingerprints are plays an important role in biometric system. In
existing system the algorithms used fingerprint are (FRAMEN) fingerprint recognition
algorithms for matching ad enhancement and minutiae cylinder-code (MCC). Fingerprint
authentication has been in use for the longest time and bears more advantages than other
biometric technologies do. Fingerprints are the most widely used biometric feature for person
identification and verification. But in this project we proposed Linear Regression and Decision
tree that fingerprint verification of ATM (Automatic Teller Machine) security system using the
biometric with hybridization. The fingerprint trait is chosen, because of its availability,
reliability and high accuracy.

2.3 ATM Security Using Fingerprint Biometric Identifier:

AUTHOR: Moses Okechukwu Onyesolu, Ignatius M. Ezeani
The fingerprint based biometric system can be implemented easily for secure the ATM
machine. In this system the working of these ATM machine is when the customer place on the
fingerprint module when it access the ATM for draw the cash then, the machine wants to

DEPT. OF MCA, RGMCET, NANDYAL 3 page

FINGERPRINT BASED ATM SYSTEM

fingerprint of that users which use the machine. Using biometric, it verify/identify fingerprint
and gives accurate result that if it valid or not valid. In this way we can try to control the crime
circle of ATM and do secure it. In this scheme, a fingerprint biometric technique is fused with
the ATM for person authentication to ameliorate the security level.

2.4 The Existing System:

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 die 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.

2.4.1 Disadvantages:

• Less Authentication

• Users should carry cards.

• Cyber threat of cloning cards.

2.5 The Proposed System:

The proposed system is an improvement of the existing system, and it does not require card
and PIN to operate. The proposed system work with biometric fingerprint only, the customer
uses fingerprint at ATM and if matched correctly, then all banks of the customer have account
with appears Customer will now choose or select the bank he wants to withdraw money from
and specify if the account is Current or Savings, this is a means of securing ATM transaction
using biometric fingerprint. This proposed system has a lot of advantages over the existing
Card and PIN method as stated follows.

2.5.1 Advantages:

 High level of Security

 Convenient to use
 Non-transferable
 Cost effective

DEPT. OF MCA, RGMCET, NANDYAL 4 page

FINGERPRINT BASED ATM SYSTEM

CHAPTER-III

SYSTEM DESIGN
3.1 System Narration:

 The current banking system is very popular with the feature of offering customers high quality
service 24hours a day, but with a low quality security for the transaction

 The traditional method of personal identification number (PIN) at the ATM has stood the
test of time, mainly due to its speed and storage, but with greater risk to customers and the bank

 ATM security has often been compromised, hence the need to ensure the operation of ATM
transactions using the biometric fingerprint.

 This research proposes to secure transactions at ATMs using a biometric fingerprint. The
proposed system is an improvement of the existing system through the use of a biometric
fingerprint and a BVN to secure transactions at ATMs.

 The proposed new system will also be profitable as it is based on the existing system.

Fig-1:System Architecture.

3.1.1 Algorithms:

In this project Fingerprint Based ATM System, we use two algorithms:

1. Linear Regression.

2. Decision tree.

DEPT. OF MCA, RGMCET, NANDYAL 5 page

FINGERPRINT BASED ATM SYSTEM

3.1.1.1 Linear Regression

Linear Regression is a supervised machine learning algorithm where the predicted output is
continuous and has a constant slope. It's used to predict values within a continuous range, (ex:
Patients, Medicines, Lab Tests) rather than trying to classify them into categories.

Fig-2:Linear Regression graph.

3.1.1.2 Decision Tree:

Decision trees are non-parametric supervised learning Method used for classification and
regression. The goal is to create a model that predicts the value of a target variable by learning
simple decision rules inferred from the data features.

A decision tree is drawn upside down with its root at the top. In the image on the left, the bold
text in black represents a condition/internal node, based on which the tree splits into branches/
edges. The end of the branch that doesn’t split anymore is the decision/leaf, in this case,
whether the passenger died or survived, represented as red and green text respectively.

DEPT. OF MCA, RGMCET, NANDYAL 6 page

FINGERPRINT BASED ATM SYSTEM

Block Diagram for Decision Tree Algorithm:

Fig-3:Decision tree.

Root Node: It represents the entire population or sample and this further gets divided into two
or more homogeneous sets.

Splitting: It is a process of dividing a node into two or more sub-nodes.

Decision Node: When a sub-node splits into further sub-nodes, then it is called the decision
node.

Leaf / Terminal Node: Nodes do not split is called Leaf or Terminal node.

Pruning: When we remove sub-nodes of a decision node, this process is called pruning. You
can say the opposite process of splitting.

Branch / Sub-Tree: A subsection of the entire tree is called branch or sub-tree.

3.2 Modules
Most biometric technology systems use the same basic principles of operation. First, a person
must be registered, or enrolled, on the biometric system.

1. Enrollment:

The process by which a user's biometric data is initially acquired, accessed, processed, and
stored in the form of a template for ongoing use in a biometric system is called enrollment.
Subsequent verification and identification attempts are conducted against the template(s)
generated during enrollment.

DEPT. OF MCA, RGMCET, NANDYAL 7 page

FINGERPRINT BASED ATM SYSTEM

2. Presentation:

Presentation is a process by which user provides biometric data to an acquisition device-the

hardware used to collect biometric data. Depending on the biometric system, presentation may
require looking in the direction of a camera, placing a finger on a platen, or reciting pass
phrase.

3. Biometric data:

The biometric data users provide in an unprocessed image or recording of a characteristic. The
unprocessed data is also referred to as raw biometric data or as a biometric sample. Raw
biometric data cannot be used to perform biometric matches. Instead, biometric data provided
by the user during enrollment and verification is used to generate biometric templates, and in
almost every system is discarded thereafter. Thus Biometric systems do not store biometric
data-systems use data for template creation. Enrollment requires the creation of an identifier
such as a username or ID. This identifier is normally generated by the user or administrator
during entry of personal data. When the user returns to verify, he or she enters the identifier,
and then provides biometric data. Once biometric data has been acquired, biometric templates
can be created by a process of feature extraction.

4. Feature extraction:

The automated process of locating and encoding distinctive characteristics from biometric
data in order to generate a template as called feature extraction. Feature extraction takes place
during enrollment and verification-any time a template is created. The feature extraction
process includes filtering and optimization of images and data in order to accurately locate
features. For example, voice-scan technologies generally filter certain frequencies and
patterns, and finger-scan technologies often thin ridges present in a fingerprint image to the
width of a single pixel. Since quality of feature extraction directly affects a system's ability to
generate templates, it is extremely important to the performance of a biometric system.

3.3 Software Development Life Cycle:

SDLC stands for software development life cycle. It is a process followed for software building
within a software organization. SDLC consists of a precise plan that describes how to develop,
maintain, replace, and enhance specific software. The life cycle defines a method for
improving the quality of software and the all-around development process.

DEPT. OF MCA, RGMCET, NANDYAL 8 page

FINGERPRINT BASED ATM SYSTEM

SDLC is the cost-effective and time-efficient process that development teams use to design and
build high-quality software.

Fig-4:Software development life cycle.

3.4 Spiral Model

It is joining parts of both arrangement and prototyping-in-stages, with a ultimate objective to
merge advantages of progressive and base up thoughts. This model of headway joins the features
of the prototyping model and the fountain model. The winding model is leaned toward for
tremendous, exorbitant, and tangled projects. This model purposes enormous quantities of
comparable stages as the outpouring model, in fundamentally a comparative solicitation,
disconnected by orchestrating, risk assessment, and the construction of models and
entertainments.

DEPT. OF MCA, RGMCET, NANDYAL 9 page

FINGERPRINT BASED ATM SYSTEM

Fig-5:Spiral model

3.5 Feasibility Study:

The presence of mind of the undertaking is reviewed to sort out and crucial comprehension is
advanced with an inconceivably sweeping approach for the task and two or three explanations.
During system appraisal the trustworthiness evaluation of the proposed structure is to be
finished. This is to guarantee that the proposed framework isn't a heap to the affiliation. For
possibility evaluation, some enthusiasm for the immense necessities for the design is critical.

Three key examinations related with the possibility appraisal are

1. Economical Feasibility
2. Specialized Feasibility
3. Social Feasibility

3.5.1 Economical Feasibility:

This study is finished to check the monetary impact that the system will have on the affiliation.
How much asset that the affiliation can fill the creative work of the framework is restricted.
The usages should be legitimized. In this way, the made structure likewise in all actuality
reasonable and this was achieved in light of the way that a gigantic piece of the upgrades used
are uninhibitedly open. Basically, the changed things ought to be bought.

3.5.2 Specialized Feasibility:

This study is finished to actually look at the particular feasibility, or if nothing else, the specific
necessities of the system. Any construction made shouldn't have an appeal on the open specific

DEPT. OF MCA, RGMCET, NANDYAL 10 page

FINGERPRINT BASED ATM SYSTEM

assets. This will induce high requests on the open explicit assets. This will incite high demands
being placed on the client. The made construction should have an unassuming need, as
irrelevant or invalid changes are typical for finishing this framework.

3.5.3 Social Feasibility:

The piece of study is to examine the degree of certification of the framework by the client in
actuality. This integrates the most well-known approach to setting up the client to use the
structure gainfully. The client shouldn't feel compromised by the system, rather ought to
recognize it as a need. The level of affirmation by the clients solely depends on the methods
that are used to show the client the plan and to make him familiar with it. His level of assurance
ought to be raised with the goal that he is in like manner prepared to make some supportive
examination, which is welcomed, as he is the last client of the structure. Social feasibility is a
detailed study on how one interacts with others within a system or an organization. Social
impact analysis is an exercise aimed at identifying and analyzing such impacts in order to
understand the scale and reach of the project's social impacts. But cost-benefit analysis (CBA)
is only one aspect of economic evaluation. The evaluation should ask broader questions to
address socio-economic impacts overall.

3.6 Functional Requirements:

Functional requirements describe what the system should do. The functional requirements can
be further categorized as follows:

The input design is the link between the information system and the user. It comprises the
developing specification and procedures for data preparation and the steps are necessary to put
transaction data in to a usable form for processing that can be achieved by inspecting the
computer to read data from a written or printed document or it can occur by having people
keying the data directly into the system. The design of input focuses on controlling the amount
of input required, controlling the errors, avoiding delay, avoiding extra steps and keeping the
process simple. The input is designed in such a way so that it provides security and ease of use
with retaining the privacy.

3.7 Non-functional Requirements:

Coming up next are the chief kinds of non-useful necessities:

Non-Functional Requirements address principal issues of huge worth for programming

DEPT. OF MCA, RGMCET, NANDYAL 11 page

FINGERPRINT BASED ATM SYSTEM

structures. If NFRs not tended to true to form, the results can include:

• Clients, clients, and creators are unsatisfied.

• Clashing programming.
• Time and cost overpower to fix what which was prepared without reviewing NFRs.

Types of Non-functional Requirements:

1. Scalability

2. Reliability

3. Regulatory

4. Maintainability

5. Serviceability

6. Utility

7. Availability

8. Usability

9. Interoperability

10. Environmental

3.8 Visual Modelling:

Fingerprint Icon:

Visualization: Start with an image or icon representing a fingerprint to symbolize the

biometric authentication step.

Modeling: Describe how the fingerprint is captured and processed for verification.

Database Interaction:

Visualization: Use an image of a database or server to indicate where fingerprint data is

stored.

Modeling: Explain the interaction between the fingerprint scanner and the database for
matching fingerprints.

DEPT. OF MCA, RGMCET, NANDYAL 12 page

FINGERPRINT BASED ATM SYSTEM

Authorization Status:

Visualization: Incorporate visual cues like a green checkmark for successful authentication
and a red cross for unsuccessful attempts.

Modeling: Outline the logic behind determining and displaying the authorization status
based on fingerprint matching.

Transaction Process:

Visualization: Include images or representations of ATM components like card slots and
cash dispensers.

Modeling: Detail the steps involved in a typical ATM transaction, emphasizing the role of
fingerprint authentication in securing transactions.

Security Measures:

Visualization: Integrate security symbols such as locks or shields to convey the secure
nature of the fingerprint authentication process.

Modeling: Explain the use of encryption and secure protocols in communication between
the fingerprint scanner and the ATM system to ensure data security.

User Feedback:

Visualization: Display feedback messages on the ATM screen to inform users of the
authentication status.

Modeling: Describe how the system provides response messages based on the success or
failure of each fingerprint authentication step.

3.8.1 Uml Diagrams

The UML diagrams are arranged into fundamental charts, social frameworks, and besides
correspondence frame graphs. The diagrams are logically organized in the going with figure:

DEPT. OF MCA, RGMCET, NANDYAL 13 page

FINGERPRINT BASED ATM SYSTEM

3.8.1.1 Use case Diagram:

A use case outline in the Unified Modeling Language (UML) is a kind of lead outline depicted
by and conveyed utilizing a Use-case examination. Its motivation is to introduce a graphical
chart of the worth given by a design regarding performers, their targets (tended to as utilize
cases), and any circumstances between those usage cases. The key inspiration driving a usage
case frame is to show what system limits are performed for which performer. Occupations of
the performers in the system can be depicted.

Fig-6:Use Case Diagram.

DEPT. OF MCA, RGMCET, NANDYAL 14 page

FINGERPRINT BASED ATM SYSTEM

3.8.1.2 Class Diagram:

In PC programming, a class diagram in the Unified Modelling Language (UML) is a kind of

static plan outline that depicts the development of a system by showing the structure's classes,
their properties, activities (or techniques), and the relationship among the classes. It figures
out which class contains information.

Fig-7:Class Diagram

DEPT. OF MCA, RGMCET, NANDYAL 15 page

FINGERPRINT BASED ATM SYSTEM

3.8.1.3 Sequence Diagram:

A movement outline in Unified displaying Language (UML) is a sort of correspondence

diagram that shows how cycles work with each other and in what request. It is a make of a
Message Sequence Chart. Progression frames are a portion of the times called event diagrams,
event circumstances, and timing graphs.

Fig-8:Sequence Diagram.

DEPT. OF MCA, RGMCET, NANDYAL 16 page

FINGERPRINT BASED ATM SYSTEM

3.8.1.4 Activity Diagram:

Activity diagrams describe the activities of a class. They are similar to state transition diagrams
and use similar conventions, but activity diagrams describe the behavior/states of a class in
response to internal processing rather than external events.

Fig-9:Component Diagram.

DEPT. OF MCA, RGMCET, NANDYAL 17 page

FINGERPRINT BASED ATM SYSTEM

3.8.1.5 Component Diagram:

A part chart is utilized to separate a huge item situated framework into the more modest parts,
in order to make them more sensible. It displays the actual perspective on a framework, for
example, executables, documents, libraries, and so forth that wells inside the hub.

It pictures the connections as well as the association between the parts present in the
framework. It helps in framing an executable framework. A part is a solitary unit of the
framework, which is replaceable and executable. The execution subtleties of a part are covered
up, and it requires a point of interaction to execute a capacity. It resembles a black box whose
conduct is made sense of by the gate and required interfaces.

Fig-10:Component Diagram.

DEPT. OF MCA, RGMCET, NANDYAL 18 page

FINGERPRINT BASED ATM SYSTEM

3.8.1.6 Deployment Diagram:

The organization outline pictures the actual equipment on which the product will be conveyed.
It depicts the static arrangement perspective on a framework. It includes the hubs and their
connections.

It discovers how programming is sent on the equipment. It maps the product engineering made
in plan to the actual framework design, where the product will be executed as a hub. Since it
includes numerous hubs, the relationship is shown by using correspondence ways.

Fig-11:Deployment diagram.

3.9 Specific Requirements

3.9.1. Software Requirements:

 Operating system : Windows 7 Ultimate.

 Coding Language : Python.
 Front-End : Python.
 Back-End : Django

3.9.2. Hardware Requirements:

 Processor : Intel i3 processor

 RAM : 4 GB (min)
 Hard Disk : 500 GB

DEPT. OF MCA, RGMCET, NANDYAL 19 page

FINGERPRINT BASED ATM SYSTEM

CHAPTER-IV

OVERVIEW OF TECHNOLOGIES
4 Programming Language:

4.1. Overview of Python:

Python is currently the most widely used multi-purpose, high-level programming language.
Python allows programming in Object-Oriented and Procedural paradigms. Python
programs generally are smaller than other programming languages like Java. Programmers
have to type relatively less and indentation requirement of the language, makes them
readable all the time. Python language is being used by almost all tech-giant companies like
– Google, Amazon, Facebook, Instagram, Dropbox, Uber… etc.

Python thoughts

If are not motivated by the how's and whys of Python, feel free to leap to the accompanying
segment. It will endeavor to clear up for the scrutinize why It think Python is most likely the
best language open and why it's an uncommon one to start programming with. Open-source
broadly useful language.

 Object Oriented, Procedural, Functional

 Simple to connect with C/Object/Java/Fortran
 Simple is to connect with C++ (by means of SWIG)
 Incredible intuitive climate

Python is a gigantic level, loosened up, shrewd and object-coordinated arranging language.
Python should be in a general sense reasonable. It utilizes English articulations much of the
time however different tongues use supplement, and it has less phonetic progressions than
different vernaculars.

Python is Interpreted − Python is overseen at runtime by the translator. It doesn't have to

assemble program going before executing it. This is like PERL and PHP.

Python is Interactive − It can truly sit at a Python brief and talk with the center individual
straightforwardly to make endeavor’s.

Python is Object-Oriented − Python stays mindful of Object-Oriented style or strategy for

programming that typifies code inside objects.

DEPT. OF MCA, RGMCET, NANDYAL 20 page

FINGERPRINT BASED ATM SYSTEM

Python is a Beginner's Language − Python is an immense language for the youthful grown-
up developers and supports the headway of a wide degree of utilizations from clear text figuring
out how to WWW endeavor’s to games.

History of Python.

Python was made by Guido van Possum in the last piece of the eighties and mid-nineties at the
National Research Institute for Mathematics and Computer Science in the Netherlands.

Python is gotten from different tongues, including ABC, Modula-3, C, C++, Algol-68,
Smalltalk, and UNIX shell and other setting up vernaculars.

Python is protected. Like Perl, Python source code is after a short time accessible under the
GNU General Public License (GPL).

Python is as of now remained mindful of by a middle improvement pack at the foundation,

disregarding the way that Guido van Possum genuinely holds a major occupation in
straightening out its reassuring.

4.2. Python Features:

1. Easy to-learn − Python has not many watchwords, crucial arrangement, and a plainly
depicted language structure. This permits the understudy to rapidly get the language.
2. Simple to-explore − Python code is in a general sense all the more plainly portrayed
and clear to the eyes.
3. Simple to-remain mindful of − Python's source code is genuinely simple to-remained
mindful of.
4. A wide standard library − Python's more prominent piece of the library is absolutely
significant and cross-stage sensible on UNIX, Windows, and Macintosh.
5. Conventional Mode − Python has support for a sharp mode which licenses adroit
testing and looking at of bits of code.
6. Moderate − Python can run on a wide assembling of gear figures out and has
comparable quality of relationship on all stages.
7. Extendable −It can add low-level modules to the Python authority.
8. These modules interface with computer programmers to add to or re-endeavour their
gadgets to be more significant.
9. Data bases − Python gives points of relationship to all monstrous business informative
collections.

DEPT. OF MCA, RGMCET, NANDYAL 21 page

FINGERPRINT BASED ATM SYSTEM

10. GUI Programming − Python stays mindful of GUI applications that can be made and
ported to different advancement calls, libraries and windows structures, like Windows
MFC, Macintosh, and the X Window strategy of Unix.
11. Versatile − Python gives a typical game plan and sponsorship for massive tasks than
shell setting up.

4.2.1. Advantages of Python: -

1. Extensive Libraries:

Python downloads with an extensive library and it contain code for various purposes like
regular expressions, documentation-generation, unit-testing, web browsers, threading,
databases, CGI, email, image manipulation, and more. So, we don’t have to write the
complete code for that manually.

2. Extensible:

As we have seen earlier, Python can be extended to other languages. You can write some
of your code in languages like C++ or C. This comes in handy, especially in projects.

3. Embeddable:

Complimentary to extensibility, Python is embeddable as well. You can put your Python
code in your source code of a different language, like C++. This lets us add scripting
capabilities to our code in the other language.

4. Improved Productivity:

The language’s simplicity and extensive libraries render programmers more

productive than languages like Java and C++ do. Also, the fact that you need to write less
and get more things done.

5. IOT Opportunities:

Since Python forms the basis of new platforms like Raspberry Pi, it finds the future bright
for the Internet of Things. This is a way to connect the language with the real world.

6. Readable:

Because it is not such a verbose language, reading Python is much like reading English.
This is the reason why it is so easy to learn, understand, and code. It also does not need

DEPT. OF MCA, RGMCET, NANDYAL 22 page

FINGERPRINT BASED ATM SYSTEM

curly braces to define blocks, and indentation is mandatory. This further aids the readability
of the code.

7. Object-Oriented:

This language supports both the procedural and object-oriented programming paradigms.
While functions help us with code reusability, classes and objects let us model the real
world. A class allows the encapsulation of data and functions into one.

8. Free and Open-Source:

Like we said earlier, Python is freely available. But not only can you download
Python for free, but you can also download its source code, make changes to it, and even
distribute it. It downloads with an extensive collection of libraries to help you with your
tasks.

9. Portable:

When you code your project in a language like C++, you may need to make some changes to
it if you want to run it on another platform. But it isn’t the same with Python.

Need to code only once, and you can run it anywhere. This is called Write Once Run Anywhere
(WORA). However, you need to be careful enough not to include any system-dependent features.

10. Interpreted:

Lastly, we will say that it is an interpreted language. Since statements are executed one by
one, debugging is easier than in compiled languages.

4.2.2. Disadvantages of Python:

So far, we’ve seen why Python is a great choice for your project. But if you choose it, you
should be aware of its consequences as well. Let’s now see the downsides of choosing
Python over another language.

1. Speed Limitations:

We have seen that Python code is executed line by line. But since Python is interpreted, it
often results in slow execution. This, however, isn’t a problem unless speed is a focal point
for the project. In other words, unless high speed is a requirement, the benefits offered by
Python are enough to distract us from its speed limitations.

DEPT. OF MCA, RGMCET, NANDYAL 23 page

FINGERPRINT BASED ATM SYSTEM

2. Weak in Mobile Computing and Browsers:

While it serves as an excellent server-side language, Python is much rarely seen on

the client-side. Besides that, it is rarely ever used to implement smartphone-based
applications. One such application is called Carbonnell The reason it is not so famous
despite the existence of Brython is that it isn’t that secure.

3. Design Restrictions:

As you know, Python is dynamically-typed. This means that you don’t need to declare the
type of variable while writing the code. It uses duck-typing. But wait, what’s that? Well, it
just means that if it looks like a duck, it must be a duck. While this is easy on the
programmers during coding, it can raise run-time errors.

4. Underdeveloped Database Access Layers:

Compared to more widely used technologies like JDBC (Java Data Base
Connectivity) and ODBC (Open Data Base Connectivity), Python’s database access
layers are a bit underdeveloped. Consequently, it is less often applied in huge enterprises.

5.Simple:

Python’s simplicity can indeed be a problem. Take my example. I don’t do Java, I’m more
of a Python person. To me, its syntax is so simple that the verbosity.

Standard Data Types

The informational collection to the side in memory can be of many sorts. For example, a
singular's age is taken care of as a numeric worth and their area is taken care of as alphanumeric
characters. Python has different standard information types that are utilized to depict the tasks
conceivable on them and the collecting procedure for every one of them. Python has five
standard information types −

• Numbers
• String
• List
• Tuples

DEPT. OF MCA, RGMCET, NANDYAL 24 page

FINGERPRINT BASED ATM SYSTEM

Table :1 Data Dictionary

Name Type Collation Attributes Null Default

Id Int(11) No None

User Varchar (30) Latin_swedish_ci No None

name

email Varchar (30) Latin_swedish_ci No

Pswd Varchar (30) Latin_swedish_ci No

phone Varchar (30) Latin_swedish_ci No

no

country Varchar (30) Latin_swedish_ci No

State Varchar (30) Latin_swedish_ci No

Table :2 Data Table

Id User Email pswd phno country state city

name

1 vijay vkappati@gmail.com ******** 6281407028 India AP kurnool

2 vinod vinod@gmail.com ******** 8790557392 India AP kurnool

3 Ajay ajay@gmail.com ******** 7780490892 India AP mdk

4 vishnu Vishnukvr@gmail.co ******** 9849466191 India AP rzp

m

The use of fingerprint-based authentication in an ATM system typically involves

traditional machine learning techniques rather than deep learning. Machine learning
algorithms, such as those based on pattern recognition, are commonly employed to
match and verify fingerprints. Deep learning is more complex and is often used for
tasks that involve large amounts of data, such as image and speech recognition. In the
context of fingerprint recognition for ATMs, simpler machine learning methods are
typically sufficient.

DEPT. OF MCA, RGMCET, NANDYAL 25 page

FINGERPRINT BASED ATM SYSTEM

Machine Learning:

 GUI Applications (like Kivy , Tkinter, PyQt etc. )

 Web frameworks like Django (used by YouTube, Instagram, Dropbox)

 Image processing (like Opencv, Pillow)

 Web scraping (like Scrapy, BeautifulSoup, Selenium)

 Test frameworks

 Multimedia

4.2.3. Overview of Machine learning

The study of machine learning certainly arose from research in this context, but in the data
science application of machine learning methods, it's more helpful to think of machine
learning as a means of building models of data.

Fundamentally, machine learning involves building mathematical models to help understand

data. "Learning" enters the fray when we give these models tunable parameters that can be
adapted to observed data; in this way the program can be considered to be "learning" from
the data. Once these models have been fit to previously seen data, they can be used to predict
and understand aspects of newly observed data. I'll leave to the reader the more philosophical
digression regarding the extent to which this type of mathematical, model-based "learning"
is similar to the "learning" exhibited by the human brain. Understanding the problem setting
in machine learning is essential to using these tools effectively.

4.2.4. Categories Of Machine Learning: -

At the most fundamental level, machine learning can be categorized into two main types:
supervised learning and unsupervised learning.

Supervised learning involves somehow modeling the relationship between measured

features of data and some label associated with the data; once this model is determined, it
can be used to apply labels to new, unknown data. This is further subdivided
into classification tasks and regression tasks: in classification, the labels are discrete
categories, while in regression, the labels are continuous quantities.

DEPT. OF MCA, RGMCET, NANDYAL 26 page

FINGERPRINT BASED ATM SYSTEM

Unsupervised learning involves modeling the features of a dataset without reference to any
label, and is often described as "letting the dataset speak for itself." These models include
tasks such as clustering and dimensionality reduction. Clustering algorithms identify distinct
groups of data, while dimensionality reduction algorithms search for more succinct
representations of the data.

Semi-supervised Learning – This involves using unlabelled data like Unsupervised

Learning with a small amount of labeled data. Using labeled data vastly increases the
learning accuracy and is also more cost-effective than Supervised Learning.

Reinforcement Learning – This involves learning optimal actions through trial and error.
So the next action is decided by learning behaviors that are based on the current state and
that will maximize the reward in the future.

4.2.5 Need for Machine Learning:

Human beings, at this moment, are the most intelligent and advanced species on earth
because they can think, evaluate and solve complex problems. On the other side, AI is still
in its initial stage and haven’t surpassed human intelligence in many aspects. Then the
question is that what is the need to make machine learn? The most suitable reason for doing
this is, “to make decisions, based on data, with efficiency and scale”.

Lately, organizations are investing heavily in newer technologies like Artificial

Intelligence, Machine Learning and Deep Learning to get the key information from data to
perform several real-world tasks and solve problems. We can call it data-driven decisions
taken by machines, particularly to automate the process. These data-driven decisions can
be used, instead of using programing logic, in the problems that cannot be programmed
inherently. The fact is that we can’t do without human intelligence, but other aspect is that
we all need to solve real-world problems with efficiency at a huge scale. That is why the
need for machine learning arises.

4.2.6 Advantages of Machine Learning: -

1. Easily identifies trends and patterns:

Machine Learning can review large volumes of data and discover specific trends and
patterns that would not be apparent to humans. For instance, for an e-commerce website like
Amazon, it serves to understand the browsing behaviors and purchase histories of its users
to help cater to the right products, deals, and reminders relevant to them.

DEPT. OF MCA, RGMCET, NANDYAL 27 page

FINGERPRINT BASED ATM SYSTEM

2.No human intervention needed (automation):

With ML, you don’t need to babysit your project every step of the way. Since it means
giving machines the ability to learn, it lets them make predictions and also improve the
algorithms on their own. A common example of this is anti-virus softwares; they learn to filter
new threats as they are recognized. ML is also good at recognizing spam.

3. Continuous Improvement:

As ML algorithms gain experience, they keep improving in accuracy and efficiency. This
lets them make better decisions. Say you need to make a weather forecast model. As the
amount of data you have keeps growing, your algorithms learn to make more accurate
predictions faster.

4. Handling multi-dimensional and multi-variety data:

Machine Learning algorithms are good at handling data that are multi-dimensional and multi-
variety, and they can do this in dynamic or uncertain environments.

5. Wide Applications:

You could be an e-tailer or a healthcare provider and make ML work for you. Where it does
apply, it holds the capability to help deliver a much more personal experience to customers
while also targeting the right customers.

4.2.7. Disadvantages of Machine Learning: -

1. Data Acquisition:

Machine Learning requires massive data sets to train on, and these should be
inclusive/unbiased, and of good quality. There can also be times where they must wait for
new data to be generated.

2. Time and Resources:

ML needs enough time to let the algorithms learn and develop enough to fulfill their purpose
with a considerable amount of accuracy and relevancy. It also needs massive resources to
function. This can mean additional requirements of computer power for you.

3. Interpretation of Results:

Another major challenge is the ability to accurately interpret results generated by the
algorithms. You must also carefully choose the algorithms for your purpose.

DEPT. OF MCA, RGMCET, NANDYAL 28 page

FINGERPRINT BASED ATM SYSTEM

4. High error-susceptibility:

Machine Learning is autonomous but highly susceptible to errors. Suppose you train an
algorithm with data sets small enough to not be inclusive. You end up with biased predictions
coming from a biased training set. This leads to irrelevant advertisements being displayed to
customers. In the case of ML, such blunders can set off a chain of errors that can go undetected
for long periods of time. And when they do get noticed, it takes quite some time to recognize
the source of the issue, and even longer to correct it.

4.3 Features Used in Project :-

1.Tensorflow:

TensorFlow is a free and open-source software library for dataflow and differentiable
programming across a range of tasks. It is a symbolic math library, and is also used
for machine learning applications such as neural networks. It is used for both research and
production at Google.

TensorFlow was developed by the Google Brain team for internal Google use. It was
released under the Apache 2.0 open-source license on November 9, 2015.

2.Numpy:

Numpy is a general-purpose array-processing package. It provides a high-performance

multidimensional array object, and tools for working with these arrays.

It is the fundamental package for scientific computing with Python. It contains various
features including these important ones:

 A powerful N-dimensional array object

 Sophisticated (broadcasting) functions
 Tools for integrating C/C++ and Fortran code
 Useful linear algebra, Fourier transform, and random number capabilities
Besides its obvious scientific uses, Numpy can also be used as an efficient multi-dimensional
container of generic data. Arbitrary data-types can be defined using Numpy which allows
Numpy to seamlessly and speedily integrate with a wide variety of databases.

DEPT. OF MCA, RGMCET, NANDYAL 29 page

FINGERPRINT BASED ATM SYSTEM

3.Pandas:

Pandas is an open-source Python Library providing high-performance data manipulation and

analysis tool using its powerful data structures. Python was majorly used for data munging
and preparation. It had very little contribution towards data analysis. Pandas solved this
problem. Using Pandas, we can accomplish five typical steps in the processing and analysis
of data, regardless of the origin of data load, prepare, manipulate, model, and analyze.
Python with Pandas is used in a wide range of fields including academic and commercial
domains including finance, economics, Statistics, analytics, etc.

4.Matplotlib:

Matplotlib is a Python 2D plotting library which produces publication quality figures in a

variety of hardcopy formats and interactive environments across platforms. Matplotlib can
be used in Python scripts, the Python and IPython shells, the Jupiter Notebook, web
application servers, and four graphical user interface toolkits. Matplotlib tries to make easy
things easy and hard things possible. You can generate plots, histograms, power spectra, bar
charts, error charts, scatter plots, etc., with just a few lines of code. For examples, see
the sample plots and thumbnail gallery.

For simple plotting the pyplot module provides a MATLAB-like interface, particularly
when combined with IPython. For the power user, you have full control of line styles, font
properties, axes properties, etc, via an object oriented interface or via a set of functions
familiar to MATLAB users.

5.Scikit – learn:

Scikit-learn provides a range of supervised and unsupervised learning algorithms via a

consistent interface in Python. It is licensed under a permissive simplified BSD license and
is distributed under many Linux distributions, encouraging academic and commercial use.

4.4 Normalization

Normalization is the most well-known approach to upgrading data in an informational index

so it meets two crucial requirements:

Data conditions are astute, all associated data things are assembled away. Normalization is
critical for certain reasons, but essentially in light of the fact that it grants data bases to consume
as little circle room as could be anticipated, achieving extended execution.

DEPT. OF MCA, RGMCET, NANDYAL 30 page

FINGERPRINT BASED ATM SYSTEM

Standardization is otherwise called information standardization.

The three head sorts of normalization are recorded under.

4.4.1 First Normal Form (1NF)

Tables in 1NF should comply with certain standards:

1. Every cell should contain just a solitary (nuclear) esteem.

2. Each part in the table ought to be astoundingly named.
3. All characteristics in a part ought to connect with a comparative region.

Table:3 1NF

UserID Username Password

015 John ********

016 Princess ********

027 Tom ********

028 Claire ********

029 Robert ********

4.4.2 Second Normal Form (2NF)

Tables in 2NF ought to be in 1NF and not have any most of the way dependence (e.g., each
non-prime quality ought to be dependent upon the table's fundamental key).

Table:4 2NF

User Id Received Data pswd Login

through IOT
1 11 ******** Sign_up

2 12 ******** Sign_up

3 13 ******** Sign_up

4 14 ******** Sign_up

5 15 ******** Sign_up

DEPT. OF MCA, RGMCET, NANDYAL 31 page

FINGERPRINT BASED ATM SYSTEM

4.4.3 Third Normal Form (3NF)

Tables in 3NF ought to be in 2NF and have no transitive reasonable circumstances on the
fundamental key. The going with two NFs furthermore exists anyway are only here and there
used

Table:5 User Details

ID NAME EMAIL STATE CITY COUNTRY

11 Vijay vijay@gmail.com AP RZP INDIA

12 Vinod vinod@gmail.com AP RZP INDIA

13 Ramu Ramu@gmail.com AP RZP INDIA

14 Vishnu vishnu@gmail.com AP RZP INDIA

Table:6 User details

USER ID PASSSWORD LOGIN

server ******** Sign_up

Vijay ******** Sign_up

Vinod ******** Sign_up

Ramu ******** Sign_up

Boyce-Codd Normal Form (BCNF)

A higher transformation of the 3NF, the Boyce-Codd Normal Form is used to address the
abnormalities which could result accepting one more than one candidate key exists. Generally
called 3.5 Normal Form, the BCNF ought to be in 3NF and in each reasonable dependence (X
→ Y), X should be an extremely key.

4.4.4 Fourth Normal Form (4NF)

For a table to in 4NF, it ought to be in BCNF and not have a multi-regarded dependence.

The underlying three NFs were construed during the 1970s by the father of the social data
model, E.F. Codd. Basically, all of the current social data base engines use his standards.

DEPT. OF MCA, RGMCET, NANDYAL 32 page

FINGERPRINT BASED ATM SYSTEM

Data adjustment characteristics can be arranged into three sorts:

Insertion Anomaly: Insertion Anomaly implies when one can't install a new tuple into a
relationship due to nonappearance of data.

Deletion Anomaly: The eradicate irregularity suggests the situation where the deletion of
data achieves the inadvertent loss of another critical data.

Update molecule Anomaly: The update irregularity is the place where an update of a
lone data regard requires various lines of data to be invigorated.

DEPT. OF MCA, RGMCET, NANDYAL 33 page

FINGERPRINT BASED ATM SYSTEM

CHAPTER-V
Testing
5.1 Testing Methodologies
The following are the Testing Methodologies:

 Unit Testing.
 Integration Testing.
 User Acceptance Testing.
 Output Testing.
 Validation Testing.

5.1.1 Unit Testing

Unit testing puts together check exertion with respect to the smallest unit of Software plan
that is the module. Unit testing. rehearses unequivocal courses in a module's control
development to ensure all out consideration and most outrageous screw up distinguishing
proof. This test revolves around each module independently, ensuring that it limits suitably
as a unit. Subsequently, the naming is Unit Testing. During this testing, each module is
attempted solely and the module points of communication are affirmed for the consistency
with plan assurance. Extremely huge taking care of way are pursued for the ordinary results.
All bumble dealing with ways are moreover attempted.

5.1.2 Coordination Testing

Coordination testing settle the issues related with the twofold issues of affirmation and
program improvement. After the item has been incorporated a bunch of high request tests are
directed. The primary goal of testing process is to take unit attempted modules and collects
a program structure that has been coordinated by plan.

5.1.3 Integration Testing:

Coming up next are the kinds of:

1.Top-Down Integration

This method is a languid procedure for managing the progress of program structure. Modules
are composed by moving lower through the control request, beginning with the chief program
module. The module subordinates to the essential program module are coordinated into the

DEPT. OF MCA, RGMCET, NANDYAL 34 page

FINGERPRINT BASED ATM SYSTEM

development in either a significance first or breadth first way. The product is tried from
primary module and individual stubs are supplanted when the test continues downwards.

2. Base up Integration

This system begins the new turn of events and testing with the modules basically level in the
program structure. Since the modules are facilitated from the base up, taking care of expected
for modules subordinate to a given level is by and large available and the prerequisite for
nails is shed. The base up fuse system may be executed with the going with progresses:

1.The low-level modules are joined into bundles into bunches that play out a specific
Software sub-work.

2.A driver (i.e.) the control program for testing is made to work with analyse information and
result.

3.The bunch is tried.

4. Drivers are disposed of and bunches are joined moving vertical in the program structure.

5.The granular perspectives test every module independently and afterward every module
will be module is incorporated with a primary module and tried for usefulness.

5.1.4 User Acceptance Testing

Client Acceptance of a structure is the indispensable part for the advancement of any system.
The structure practical is pursued for client affirmation by constantly keeping in touch with
the arranged system clients at the hour of making and making changes any spot required. The
system made gives a well-disposed UI that can undoubtedly be another seen even by an
individual to the framework.

5.1.5 Output Testing

In the wake of playing out the endorsement testing, the ensuing stage is yield attempting of
the proposed system, since no structure could be useful if it doesn't convey the essential
outcome in the predefined plan. Getting some data about the setup expected by them tests the
outcomes made or displayed by the structure feasible. Consequently, the outcome
configuration is considered in 2 ways - one is on screen and one more in printed plan.

Approval Checking

Approval checks are performed on the accompanying fields.

DEPT. OF MCA, RGMCET, NANDYAL 35 page

FINGERPRINT BASED ATM SYSTEM

Software Testing Strategy:

A system for structure testing organizes structure examinations and plan methodologies into
an overall organized series of steps that results in the productive advancement of
programming. A strategy for programming testing ought to oblige low-level tests that are
critical to affirm that a little source code part has been precisely executed as well as
irrefutable level tests that endorse huge system limits against client requirements.

Programming testing is a fundamental part of programming quality affirmation and

addresses an authoritative study of specific arrangement and coding. Testing tends to an
intriguing irregularity for the item.

Framework Testing:

Programming once supported ought to be gotten together with other structure parts (for
instance Equipment, people, informational collection). Structure testing affirms that all of the
parts are real and that overall system work execution is achieved.

5.1.6 Test Cases

An experiment is a report, which has a lot of test data, preconditions, expected results and
postconditions, made for a particular test circumstance to really take a look at consistence
against a specific need. Try goes probably as the early phase for the test execution, and
ensuing to applying a lot of information regards, the application has a legitimate outcome
and leaves the structure at some end point or generally called execution postcondition.
Table:7 Test case Results

Status
Test Input Expected Behavior Observed P = Passed
S. No. behavior F = Failed
1 Login as user or Administrator or user Got Expected P
admin with Home page for manager result
correct login should be displayed
details
2 Login as user or Error message should Got Expected P
admin with wrong be displayed result
login details

DEPT. OF MCA, RGMCET, NANDYAL 36 page

FINGERPRINT BASED ATM SYSTEM

CHAPTER-VI

FEATURE ENHANCEMENT
Future Work

 Improving of the existing system through the use of a biometric fingerprint to secure
transactions at ATMs. This system will also be profitable as it is based on the existing
system and thus reduce cost for research work.

 Creating a database of customer biometrics and testing to reduce the time of

transaction compared to traditional system.

 Adding a card reader for people who are still using traditional methods.

Multi-factor Authentication: Combine fingerprint recognition with another

authentication factor, like a PIN or facial recognition, to bolster security.

Anti-Spoofing Measures: Integrate advanced anti-spoofing technologies to detect

fake fingerprints and ensure the authenticity of the biometric data.

Dynamic Authentication: Implement dynamic fingerprint recognition that analyzes

more features, making it harder for unauthorized access.

Encryption: Ensure that fingerprint data is encrypted during transmission and storage
to prevent unauthorized access.

Alerts and Notifications: Implement real-time alerts for unusual activities or multiple
failed authentication attempts to enhance security monitoring.

DEPT. OF MCA, RGMCET, NANDYAL 37 page

FINGERPRINT BASED ATM SYSTEM

CHAPTER-VII

CONCLUSION
In today’s modern world, autonomous systems play an important role in our day to day life.
As the social computerization and automation have drastically increased, it can be seen
evidently where the number of ATM centers increases rapidly. Most civilians use ATM’s
regularly. A good example can be a financial transaction, ease of money exchange etc. So
there exists an important factor called security.

The security features were enhanced largely for the stability and reliability of owner
recognition. The whole system was built on the fingerprint technology which makes the
system safer, reliable and easy to use.

The execution of ATM protection by availing fingerprint also has the traditional verifying
methods that were inputting the client's fingerprints, that is sent by the administrator and
checked correctly.

DEPT. OF MCA, RGMCET, NANDYAL 38 page

FINGERPRINT BASED ATM SYSTEM

APPENDIX

SCREENSHOTS
Sample Screens:

Fingerprint based on ATM System

All existing banking applications are authenticating users based on PIN NO or password but
this technique is not secured so in propose online banking application we are authenticating
user based on his finger print. To implement this project we have designed following
modules

1) Signup: using this module user can signup with the application by using username,
password and finger print image. All signup details will be saved in MYSQL database
2) Login: using this module user can login to application by entering username,
password and finger print image given at signup time to authenticate himself
3) Deposit: after successful authentication user can deposit amount and it will added to
his account
4) Withdraw: using this user can withdraw amount if sufficient balance available
5) View Balance: using this module user can view available balance

First create database in MYSQL by copying content from ‘DB.txt’ and then paste in MYSQL

To run project double click on ‘run.bat’ file to start python FLASK server.

Screenshot:1 In above screen server started and now open browser and enter URL as
‘http://localhost:5000/index’ and press enter key to get below.

DEPT. OF MCA, RGMCET, NANDYAL 39 page

FINGERPRINT BASED ATM SYSTEM

Screenshot:2 In above screen click on ‘Signup Here’ link to get below screen.

Screenshot:3 In above screen fill all signup details and then choose finger print image and
then click on ‘Open’ button to load image and to get below screen.

DEPT. OF MCA, RGMCET, NANDYAL 40 page

FINGERPRINT BASED ATM SYSTEM

Screenshot:4 In above screen after pressing ‘Register’ button we will get message as ‘Signup
process completed’ and now click on ‘Login Here’ link to get below screen

Screenshot:5 In above screen I am login and selecting wrong finger print as ‘4.png’ and then
click on ‘Open’ button to get below screen.

DEPT. OF MCA, RGMCET, NANDYAL 41 page

FINGERPRINT BASED ATM SYSTEM

Screenshot:6 In above screen image loaded and now click on ‘Login’ button to get below
output.

Screenshot:7 In above screen login is failed and now login with correct image.

DEPT. OF MCA, RGMCET, NANDYAL 42 page

FINGERPRINT BASED ATM SYSTEM

Screenshot:8 In above screen now i am uploading correct image and press ‘Login’ button to
get below output

Screenshot:9In above screen user login is successful and we got deposit and with draw option.

DEPT. OF MCA, RGMCET, NANDYAL 43 page

FINGERPRINT BASED ATM SYSTEM

BIBILOGRAPHY
[1] Prof. Ranjit Mane1, Sagar Chavan2, Trushali Birambole3, Asmita kamble4, “Fingerprint
Based ATM System”, International Journal for Research Trends and Innovation (IJRTI) ,
ISSN:2456-3315, Volume 4, Issue 4, 2017.

[2] Saima Rafat Bhandari1, Zarina Begum K Mundargi2, "A Review on Securing ATM
System Using Fingerprint", International Journal of Scientific Research in Computer Science,
Engineering and Information Technology (IJSRCSEIT), ISSN:2456-3307, Volume 3, Issue 2,
2018.

[3] Christiawan1, Bayu Aji Sahar2, Azel Fayyad Rahardian3, Elvayandri Muchtar4,
"Fingershield ATM – ATM Security System Using Fingerprint Authentication". Issue 4.

[4] Vijayraj A, "A Survey on Cardless Cash Access Using Biometric ATM Security System”,
Scholars Journal of Engineering and Technology (SJET), ISSN 2347-9523, Issue 2.

[5] Moses Okechukwu Onyesolu, Ignatius M. Ezeani, “ATM Security Using Fingerprint
Biometric Identifier: An Investigative Study”, International Journal of Advanced Computer
Science and Applications (IJACSA), 030412, 2012.

[6] Samayita Bhattacharya and Kalyani Mali,” Fingerprint Recognition Using Minutiae
Extraction Method”, (International World Wide Web Conference Committee) © 2011 IW3C2,
published under Creative Commons CC by 4.0 January,2011.

DEPT. OF MCA, RGMCET, NANDYAL 44 page