MAHARASHTRA STATE BOARD OF TECHNICAL EDUCATION,

MUMBAI
A
Project Report
on

Facial Recognition for Social Media Profile Discovery.

Submitted by:

Sr. No. Name of Student Exam Seat No.

1) Sailee Ganesh Abhale
2) Aishwaray Vinod Bhagwat
3) Mayur Chandrakant Chaudhari

Under the Guidance of:

Name of Guide: Mr. H. M. Gaikwad
Designation: HOD, Artificial Intelligence & Machine Learning

Department of Artificial Intelligence & Machine Learning

K. K. WAGH POLYTECHNIC, NASHIK
Academic Year 2022-23

I
 K. K. Wagh Education Society’s

K. K. WAGH POLYTECHNIC
HirabaiHaridasVidyanagari, Amrutdham, Panchavati, Nashik-422003, Maharastra

Certificate
This is certify that :
Name of Student Class Enrolment No. Exam Seat No.

Sailee Ganesh Abhale TYAN

TYAN
AishwarayVinod Bhagwat
Mayur Chandrakant Chaudhari TYAN

From the institute - K. K. Wagh Polytechnic, Nashik has completed the Project (Capstone
ProjectPlanning and Execution (CPE)) for their final year having title Facial
Recognition for Social Media Profile Discovery during the Academic Year
2023-24 in the partial fulfillment of Diploma in Artificial Intelligence & Machine
Learning. The project is completed in a group consisting of 3 people under the guidance
of the Faculty Guide.
Date :
Place : Nashik

Mrs. Jyoti Mahajan Mr. H. M. Gaikwad

Internal Faculty Guide HOD- Artificial Intelligence & Machine

Seal of Institu

Learning.
Prof. P. T. Kadave
Principal – K. K. Wagh Polytechnic, Nashik

II
Participation in State Level Project Competition

III
IV
V
 ACKNOWLEDGEMENT
With deep sense of gratitude we would like to thanks all the people who have lit our path with their kind
guidance for our Project Selection, Design and Development. We are very grateful to these intellectuals,
experts, who did their best to help during our completion of project work.
It is our proud privilege to express deep sense of gratitude to, Prof. P. T. Kadave-Principal,
K. K. Wagh Polytechnic, Nashik for his comments and kind permission to complete this project. We remain
indebted to Prof. H. M. Gaikwad, Head of Artificial Intelligence & Machine Learning Department for his
timely suggestion and valuable guidance.
The special gratitude goes to our Internal Faculty Guide Mr. H. M. Gaikwad, staff members, technical staff
members, of Artificial Intelligence & Machine Learning Department for his/her technical, timely, excellent
and coercive guidance in completion of this project work. We thanks to all the class colleagues for their
appreciable, encouraging help for completion of our project.

We are also thankful to our parents who providing their wishful support for our project completion
successfully. Lastly we thanks to our all friends and the people who are directly or indirectly related to our
project work.

Names of Students:

1) Sailee Abhale (TYAN-03)

2) Aishwaray Bhagwat (TYAN-07)
3) Mayur Chaudhari (TYAN-11)

(Academic Year: 2023-24)

VI
 Vision & Mission
Institute Vision : -Strive to empower students with Quality Technical Education.

Institute Mission :- Committed to develop students as Competent and Socially Responsible

Diploma Engineers by inculcating learning to learn skills, values and ethics, entrepreneurial attitude,
safe and eco-friendly outlook and innovative thinking to fulfill aspirations of all the stakeholders
and contribute in the development of Organization, Society and Nation.

Department Vision :-To impart quality technical education for development of technocrats.

Department Mission :-

M1- To provide quality in education and facilities for students to help them to achieve higher
academic career growths.
M2- To impart education to meet the requirements of the industry and society by
technological
solutions.
M3- Develop technical & soft skill through co–curricular and extra-curricular activities for
improving personality.

Program Educational Objectives:-

PEO1: Provide socially responsible, environment friendly solutions to Computer

engineering related broad-based problems adapting professional ethics.
PEO2: Adapt state-of-the-art Computer engineering broad-based technologies to work in
multi-disciplinary work environments.

PEO3: Solve broad-based problems individually and as a team member communicating

effectively in the world of work.

Program Specific Outcome:-(Version – 1.2)

PSO 1: Computer Software and Hardware Usage: Use state-of-the-art technologies for
operation and application of computer software and hardware.

PSO 2: Computer Engineering Maintenance: Maintain computer engineering related

software and hardware systems.

VI
Program Outcomes:-
PO1. Basic and Discipline specific knowledge: Apply knowledge of basic mathematics,
science and engineering fundamentals and engineering specialization to solve the
engineering problems.

PO2. Problem analysis: Identify and analyse well-defined engineering problems using
codified standard methods.

PO3. Design/ development of solutions: Design solutions for well-defined technical

problems and assist with the design of systems components or processes to meet specified
needs.

PO4. Engineering Tools, Experimentation and Testing: Apply modern engineering tools and
appropriate technique to conduct standard tests and measurements.

PO5. Engineering practices for society, sustainability and environment: Apply appropriate
technology in context of society, sustainability, environment and ethical practices.

PO6. Project Management: Use engineering management principles individually, as a team

member or a leader to manage projects and effectively communicate about well-defined
engineering activities.

PO7. Life-long learning: Ability to analyse individual needs and engage in updating in the
context of technological changes.

VI
 Abstract

Face recognition technology has gained significant traction in recent years, revolutionizing the way we interact
with digital platforms and enhancing security in various domains. This abstract focuses on its application in
social media for the retrieval of user identities. In the context of social media, the process begins with user-
generated content, such as images and videos. Face detection algorithms are employed to locate and isolate
faces within this multimedia uploads. Subsequently, facial features are extracted to create unique facial
embedding or descriptors, which serve as compact representations of individual identities.

A database is maintained by social media platforms to store these facial embedding’s, linked to respective user
profiles. When users engage with the platform, either by uploading new content or attempting to access their
accounts, facial recognition technology compares the newly captured facial features to the stored embedding’s
in the database. The matching process involves similarity scores or distance metrics, and upon a successful
match, the user's identity is retrieved.

This technology enhances user convenience by offering frictionless access to accounts, simplifying the login
process, and reducing the need for passwords or other authentication methods. However, the deployment of face
recognition in social media also raises important ethical and privacy considerations. Striking a balance between
user conveniences and safeguarding personal data is paramount. Robust security measures must be in place to
protect stored facial data, and users should have control over its usage.

In conclusion, the integration of face recognition for social media ID retrieval represents a significant
advancement in user experience and security. However, responsible implementation, transparency, and
adherence to privacy regulations are essential to ensure that the benefits are realized without compromising user
privacy and security.

Keywords: Authentication, Social media, Face Extraction, Similarity Score, Face embeddings

IX
 Table of Contents
Ch. No. Name of topic Page no.
 Title Page I
 Certificate II
 Participation in State Level Project Competition III
 Acknowledgement IX
 Vision & Mission X
 Abstract XII
 Table of Contents XIII
 Index of Figures XIV
1 Introduction
1
1.1 Literature Survey
1.2 Existing System 2
1.3 Proposed System 3
2 Analysis & Feasibility
4
2.1 Preliminary Survey
2.2 Operational Feasibility
2.3 Technical Feasibility 5
2.4 Economic Feasibility
3 Project Requirements
3.1 About Proposed Project 6
3.2 Area of Implementation
3.3 Software requirement specification 7
3.4 Software requirements
9
3.5 Hardware Requirements
4 Project Design & Implementations 10
4.1 System Diagram
4.2 DFD Diagram 11
4.3 UML Diagram 14
4.4 Class Diagram 15
4.5 Module Analysis 16
5 Result and Outputs
21
5.1 Swapping Interface
5.2 Help From ChatGpt 26
5.3 Token Economics 27
6 Testing of Software Application 28

X
 6.1 Unit Testing 29
7 Costing of Project
33
7.1 Cost Estimation Using COCOMO Model
8 Application 35
9 Future Scope 36
10 Conclusion 37
11 References 38
12 Paper Publication in Online International Journal

Index of Figures
Fig.No. Name of Page no.
figure
4.1 System Diagram 10
4.2.1 DFD Level 0 11
4.2.2 DFD Level 1 12
4.2.3 DFD Level 2 13
4.3 UML Diagram 14
4.4 Class Diagram 15
5.1.1 Swapping Model 21
5.1.2 Wallet Connect
22
5.1.3 Dynamic Token Value
5.1.4 Login Success
23
5.1.5 Advanced Trade Setting
5.1.6 Transaction Confirmation 24
5.1.7 Transaction Hash Generation
25
5.1.8 Swap Transaction Details
5.1.9 ChatGpt Message Model 26
5.2.0 Trade Analysis
27
s5.3.1 Token Economics

XI
 CHAPTER 1 : INTRODUCTION
Face recognition simplifies the process of discovering and accessing one's social media profiles. By
analyzing facial features in images, the software identifies individuals and locates their corresponding
Instagram handles, providing a convenient and efficient way to connect with people across the platform.
This project not only showcases the capabilities of facial recognition but also addresses the growing
need for enhanced social media search functionalities, offering users a novel and time-saving approach
to discover and connect with others on Instagram.
1.1 LITERATURE SURVEY

1. Your Face Belongs to Us: Kashmir hills

he story of a small AI company that gave facial recognition to law enforcement, billionaires, and
businesses, threatening to end privacy as we know it.
Your Face Belongs to Us is a gripping true story. It illuminates our tortured relationship with
technology, the way it entertains us even as it exploits us, and it presents a powerful warning that in
the absence of regulation, this technology will spell the end of our anonymity.

2. A Review of Face Recognition Technology by Peng Haipeng -

Face recognition technology is a biometric technology, which is based on the identification of facial
features of a person. People collect the face images, and the recognition equipment automatically
processes the images.

3. face detection artical by techtarget.

his artical is published by tech target about face detection all about the face detections.
here they have specified all information about how it actually works.
what can be advantages and disadvantages of using it.

Concept -
Facial recognition for social media ID discovery is the use of technology to identify and authenticate
users by analyzing unique facial features. I
t simplifies the login process, enhances security, and enables personalized content recommendations.
However, it raises privacy concerns, necessitating responsible implementation and data protection
measures. This technology streamlines user access while requiring ethical considerations to balance
convenience and privacy

Working -
1. Data Collection: Gather a diverse dataset of social media profile pictures and user information.

1
2. Preprocessing: Standardize image sizes, detect faces, and enhance image quality.
3. Recognition Model: Train a facial recognition model using deep learning techniques.
4. User Interface: Build a simple app where users can upload profile images or provide social media
links.
5. Matching Profiles: Implement facial recognition to find potential matches in the dataset.
6. Results Display: Display the top matches with profile details and confidence scores.
7. Privacy Measures: Include user consent and data protection features.
8. Testing and Refinement: Test the app with various images and gather user feedback for
improvements.
9. Documentation: Create documentation including code, instructions, and a project report.
10. Compliance: Ensure compliance with privacy and ethical guidelines.
11. Deployment: Make the app available for use on web and mobile platforms.

-This simplified plan focuses on creating a user-friendly app for social media profile discovery while
keeping the project manageable

1
CHAPTER 2 : ANALYSIS & FEASIBILITY

2.1 PRELIMINARY SURVEY

Surveyed public perceptions and concerns on using facial recognition for social media profile discovery.
Analyzed responses to identify trends and insights. Findings will inform project direction and future
research.

2.1.1 Technical considerations:

2.1.1.1 Choice of blockchain platform: Explored blockchain platforms focusing on

scalability, security, and compatibility with facial recognition technology. Chose
Ethereum for its established ecosystem, smart contract capabilities, and potential for
integrating facial recognition features into social media profile discovery.

2.1.1.2 Smart contract development: Implemented smart contracts on Ethereum to

facilitate secure and automated transactions within the Facial Recognition for Social
Media Profile Discovery project. Leveraged solidity to develop contracts enabling
seamless interaction and authentication between users and the platform, ensuring privacy
and accuracy in profile discovery.

2.1.1.3 User interface and experience: Creating an intuitive and user-friendly interface
for the profile discovery app so that users can have cool experience and engage on our
app for long time.

2.1.1.4 Security and auditing: robust security measures, including encryption and
access controls, to safeguard user data and ensure privacy in the Facial Recognition for
Social Media Profile Discovery project.

2.1.2 Economic considerations:

2.1.2.1 Compliance with existing regulations: Depending on the jurisdiction of the

project, the team may need to comply with existing financial and securities regulations,
which could add additional legal and compliance costs.

2.1.2.2 Potential regulatory changes: Maintained flexibility in design and operations to

adapt to evolving regulations related to data privacy, facial recognition technology, and
social media usage. Engaged legal experts to ensure compliance and mitigate any
regulatory risks.

1
2.2 OPERATIONAL FEASIBILITY
Conducted operational feasibility analysis for the Facial Recognition for Social Media
Profile Discovery project, evaluating factors such as technology infrastructure, resource
availability, and organizational readiness. Determined that project implementation is
viable based on existing capabilities and identified areas for enhancement.

2.3 TECHNICAL FEASIBILITY

Evaluated existing algorithms, data storage capabilities, and integration challenges.
Determined viable solutions to ensure accurate and efficient profile matching while
addressing scalability and privacy concerns.

2.4 ECONOMIC FEASIBILITY

Conducted comprehensive economic feasibility analysis, Evaluated cost factors, revenue
projections, market demand. Findings suggest a favorable economic outlook, supported
by growing demand for personalized social media experiences and advancements in
facial recognition technology.

1
 CHAPTER 3 : PROJECT REQUIREMENTS

3.1 ABOUT PROPOSED PROJECT

Our proposed project, aims to revolutionize user experience in social

media platforms by integrating facial recognition technology. This innovative
solution will allow users to discover and connect with others more efficiently by
simply uploading a photo and letting the system identify matching profiles across
various social media platforms.

Through this project, we aspire to enhance user engagement, streamline

networking processes, and unlock new possibilities for social interaction in the
digital world.The project's primary objective is to streamline the process of
discovering and connecting with individuals on social media platforms. To
achieve this, the project will develop a sophisticated facial recognition algorithm
capable of accurately identifying individuals based on uploaded photos. This
algorithm will be integrated into a user-friendly interface, allowing users to
simply upload a photo and receive matches from platforms such as Instagram.
.

3.2 AREA OF IMPLEMENTATION

Software Development: we will be creating the user interface, backend systems,

and integration with social media platforms. This area will involve coding,
testing, and debugging to ensure the smooth functioning of the application.

Data Management: Given the sensitive nature of facial data, a dedicated area
will oversee data management practices. This includes establishing protocols for
data collection, storage, encryption, and access control to ensure compliance with
privacy regulations and safeguard user information.

User Experience (UX) Design: here we will focus on creating an intuitive and
user-friendly interface for the application. This area will involve conducting user
research, prototyping, and iterative testing to optimize the user experience and
maximize user engagement.

Security and Privacy: we will focus on implementing robust security measures

to protect user data and privacy. This includes encryption techniques,
authentication mechanisms, and regular security audits to identify and mitigate
potential vulnerabilities.

1
 3.3 SOFTWARE REQUIREMENT SPECIFICATION (SRS)

3.3.1 INTRODUCTION

Facial recognition for social media profile discovery is a cutting-edge technology that leverages the
power of artificial intelligence to identify and verify individuals based on their facial features. In the
realm of social media, this technology plays a pivotal role in enhancing user experiences, privacy, and
security.

At its core, facial recognition for social media profile discovery involves the automatic detection,
analysis, and recognition of faces within photos shared on social platforms.

This technology allows users to easily identify and connect with friends and family members in photos,
streamlining the process of tagging individuals. It also has the potential to enhance profile verification,
reducing the prevalence of fake or duplicate profiles on social media platforms, thereby increasing trust
and security.

In this era of rapid technological advancements, facial recognition for social media profile discovery
represents both an opportunity and a responsibility. When used ethically and responsibly, it has the
potential to revolutionize the way we interact, connect, and share on social media platforms.
As it continues to evolve, its impact on the social media landscape is expected to be significant

3.3.2 FUNCTIONAL REQUIREMENTS

● Facial Recognition Algorithm: Develop a robust facial

recognition algorithm capable of accurately identifying individuals
across various social media platforms based on uploaded photos.

● User Registration and Authentication: Implement a user

registration system that allows users to create accounts and
authenticate their identities securely. This may involve traditional
username/password authentication or alternative methods such as
biometric authentication.

● Profile Discovery: Enable users to upload a photo and discover

matching social media profiles across platforms such as Facebook,
Twitter, Instagram, and LinkedIn.

● Privacy Settings: Implement privacy settings that allow users to

control the visibility of their profiles and manage who can discover

1
 them through facial recognition.

● Notification System: Incorporate a notification system to alert

users when a matching profile is discovered or when there are
updates to their profile discovery preferences.

● User Interface: Design an intuitive and user-friendly interface that

makes it easy for users to upload photos, view search results, and
manage their profile discovery settings.

3.3.3 NON-FUNCTIONAL REQUIREMENTS

● Performance: The system should be able to process facial

recognition requests and retrieve search results quickly, with
minimal latency, even during peak usage periods.

● Scalability: The system should be designed to handle increasing

numbers of users and data volumes without sacrificing
performance or reliability.

● Reliability: The system should be highly reliable, with minimal

downtime and robust error handling mechanisms in place to ensure
uninterrupted service availability.

● Security: The system should adhere to strict security standards to

protect user data and ensure privacy. This includes encryption of
sensitive data, secure authentication mechanisms, and adherence to
industry best practices for data security.

● Usability: The user interface should be intuitive and user-friendly,

with clear navigation paths and informative feedback to guide
users through the profile discovery process.

● Compatibility: The system should be compatible with a wide

range of devices and browsers to ensure accessibility for all users.

3.3.4 TECHNOLOGIES USED

● Language for Development : Python

● Library for EDA : Numpy, face recognition, firebase_admin,

1
 Dlib
● Software Package : Google Colab, Virtual studio code
● MS OFFICE : MS Word 2019 Student, MS Excel 2019 Student

3.3.5 CONCLUSION

The Facial Recognition for Social Media Profile Discovery project holds significant
promise for enhancing user experience, increasing engagement, and fostering meaningful
connections within social media platforms. By embracing innovation, prioritizing user
privacy and security, and adhering to ethical principles, the project sets a new standard
for personalized social networking experiences in the digital era.

1
3.4 SOFTWARE REQUIREMENTS

Visual Studio Code: A source-code editor made by Microsoft with the Electron
Framework, for Windows, Linux and macOS.

Chrome: A Web browser for testing the web app builds on a live environment.

Git: Distributed version control software for tracking changes in a set of build
files.

3.5 HARDWARE REQUIREMENTS

Computer System or Laptop with mid-range Specification

CPU: Intel Core i3 2nd Gen or Higher Processor with at least 2 cores & 4 threads

RAM: 4GB DDR3 with at least 1600Mhz frequency

GPU: Any Integrated Graphics processor or Discrete Graphics processor

2
CHAPTER 4 : PROJECT DESIGN & IMPLEMENTATIONS

4.1 SYSTEM DIAGRAM

Fig 4.1 : System diagram

2
4.2 DFD DIAGRAM

4.2.1 DFD Level 0

Fig. 4.2.1: DFD Level 0 diagram

2
4.2.2 DFD Level 1

Fig 4.2.2 : DFD Level 1 Diagram

DFD LEVEL 1

Input Image : The user input one image

Preprocessing : Photo will be send to preprocessing

Feature Extraction : Extracting the details from the face

Classification from Database: Database is classified and send for further process.

2
4.2.3 DFD Level 2

Fig 4.2.3 : DFD Level 2 Diagram

2
4.3 UML Diagram

Fig 4.3 : UML Diagram

2
4.4Class Diagram

Fig 4.4 : Class Diagram

2
4.4 Module Analysis

4.5.1 Module

1. Module Name : Face Recognition

1.1 Purpose of Module

The face recognition model utilizes algorithms and techniques from the field of computer vision
and machine learning to analyze and compare facial features in images. It extracts unique
characteristics from each face, such as the arrangement of eyes, nose, and mouth, and creates a
digital representation (often referred to as a face embedding or face descriptor) for each detected
face.

1.2 Inputs and Outputs of

Module : Input: Image

Output: Extraction of the facial features and provid the percentage of

match(if found)

1.3 Files Used by Module

1. Trained Model File: This file contains the pre-trained deep

learning model used for facial recognition tasks. It may be a file
with extensions like `.h5`, `.pb`, `.pth`, or other formats depending
on the framework used (e.g., TensorFlow, PyTorch). This model
file has been trained on a large dataset of faces to extract facial
features and generate face embeddings.

2. Configuration File: The configuration file contains parameters

and settings used by the face recognition module. It may specify
details such as the model architecture, input image size,
preprocessing steps, and any other configurations specific to the
face recognition model.

3. Preprocessing Scripts: These scripts are used to preprocess

images before feeding them into the face recognition model.
Preprocessing steps may include tasks such as resizing images,
normalizing pixel values, and performing data augmentation to

2
improve model performance.

4. Training Data : If the face recognition model needs to be

retrained or fine-tuned on specific data, training data files may be
used. These files contain annotated images with labeled faces for
training the model.

2
 1.4 Algorithm

1. Start

2. Face Detection: Identify and locate faces within an image using techniques like cascade
classifiers or deep learning-based methods.

3. Face Alignment: Correct variations in head pose and orientation to standardize the
face's position.

4. Feature Extraction: Capture distinctive characteristics from the aligned face region,
such as pixel intensities or geometric properties.

5. Feature Matching or Classification: Compare extracted features to known faces in a

database using similarity measures or machine learning algorithms.

6. Verification or Identification: Determine if the detected face matches a specific

individual's identity (verification) or identify the individual among a group of known faces
(identification)

7. Stop

2.Module Name : Database Management

2.1 Purpose of Module

The purpose of this module is to store data into the firebase.

2.2 Inputs and Outputs of Module :

Input: upload image

Output: stores data to cloud base firebase.

2.3 Files Used by Module

 Database Backup Script: This script is used to perform regular backups of the database to
ensure data integrity and disaster recovery. It may include commands for exporting
database contents to backup files in a specific format.

 Database Query Scripts: These scripts contain SQL queries or database manipulation
commands used by the application to interact with the database. They include queries for
retrieving, inserting, updating, and deleting data from the database.

 Database configuration file: This file includes database connection parameters

2
 3. Module Name : dlib

3.1 Purpose of Module

Its primary focus is on providing tools and algorithms for facial recognition

3.2 Inputs and Outputs of Module :

Input: Image containing one or more human faces

Output:
For each detected face, a set of facial landmarks such as the coordinates of key
points on the face (e.g., corners of the eyes, nose, mouth, and jawline).

3.3 Files Used by Module

The dlib module typically doesn't involve the direct usage of files; rather, it primarily
operates on input data in the form of images or video frames and produces output results
based on the processing performed by its algorithms.

3
 4. Module Name : OpenCV

4.1 Purpose of Module

The OpenCV (Open Source Computer Vision) module is designed to provide a

comprehensive toolkit for various computer vision tasks. Its primary purposes include:

4.2 Inputs and Outputs of Module :

Input: Image containing one or more human faces

Output: for each detected face the coordinates, the distance in each feature

4.3 Files Used by Module

Input Images: These are the image files that you load into your program for processing. Common
formats include JPEG, PNG, BMP, and TIFF.
Output Images: After processing with OpenCV algorithms, you may save the results as new image
files. These could be in the same formats as the input images or others, depending on your
requirements.

XML/YAML Files:
OpenCV often uses XML or YAML files for storing trained models or configuration data. For
example, Haar cascades for object detection are typically stored in XML format.

Text Files:
You might use text files to store metadata or annotations associated with images or videos
processed with OpenCV. These could include labels, bounding box coordinates, or other
annotations.

4.4 Algorithm

1. Start.
2. Read Image.
3. Preprocessing.
4. Apply Image Processing Algorithms.
5. Object Detection or Feature Extraction.
6. Display Results.
7. Stop.

3
CHAPTER 5 : RESULT AND OUTPUTS/ SCREEN SHOTS

5.1 Swapping Interface

Fig 5.1.1 : Swapping Model

This is the Page where the User will Select the Tokens it has three tabs on top, where the
first swap tab is the above page displayed then there is tokens tab which will display
details of 8 selected tokens then their is pool’s tab on clicking it user will be able to
analyze his trade with the help of ChatGpt.

On Right Side the 1st Button Display’s Polygon Which is the Blockchain where the
swapping transaction will happen. Then their is Connect Button, on Clicking the
Connect Button a pop-up will appear on screen which will ask user to select the wallet of
their choice so that the further process of transaction can happen

On Clicking the Connect Button Following pop-up will appear and user can choose
wallet of his choice and the balance of the tokens that the user have will be automatically
fetched and displayed below the selected two token’s name. After Selecting the wallet
address of the user’s wallet will be displayed on the connect button.

3
 Fig 5.1.2 : Wallet Connect

This is the message model (pop-up) that will appear and it will ask user to select
‘MetaMask’ or ‘Coinbase’ wallet. User should already have metamask or coinbase
installed and settled before using the app.

Fig 5.1.3 : Dynamic Token Value

3
 Fig 5.1.4 : Login Success

On Clicking Ok user will be allowed to resume his transaction work i.e swapping or
analyze the details of tokens After Selecting the input and output Token and Entering
the input amount , User
On clicking the Settings icon on right top corner of swap model user will be able to set
the advanced trading option such as Slippage Tolerance and Deadline for Transaction.

Fig 5.1.5 : Advanced Trade Setting

3
After Clicking on Swap Button. User will be prompted a metamask pop-up which will
ask user to allow the use of his crypto tokens for the purpose of swapping. user will have
to enter the number of tokens he wants to allow or just simply can click on use default
option to use the token value he entered. After entering token value user will have to sign
the transaction which is the confirmation that he has approved the use of his tokens and
wants to swap the token for another token. User will have to click on confirm button and
his transaction will be booked for miners in the polygon blockchain.

Fig 5.1.6 : Transaction Confirmation

After Confirming user will have to wait until his transaction gets mined by a miner. The
transaction id (hash) will be returned to user so that he will be able to check his
transaction status on polygon’s official website.

Here is the Example of the trade that we have done of swapping 0.00012 Wrapped
Ether to 0.20 Dai Token

3
Fig 5.1.7 : Transaction Hash Generation

Fig 5.1.8 : Swap Transaction Details

3
5.2 Help From ChatGpt
This is the Page who’s UI is same as of Swapping Model. It will help user to analyze his
trade with the help of ChatGpt. User just have to select the two tokens , enter the value of
token 1 , token 2 (output token) value will be automatically calculated and click on
submit button. ChatGpt prompt will include the names of tokens , their value , their value
in US Dollar, their market cap , their volume , etc for in depth analysis of trade. On
clicking Submit user will have to wait for the response from ChaGpt and the result will
be displayed to user in the message model.

Fig 5.1.9: ChatGpt Message Model

3
 Fig 5.2.0 : Trade Analysis

5.3 Token Economics

In this page details such as Token Name , Change in 24H (Price Change), Price (USD),
Total Supply and Volume of the selected tokens will be displayed to user so that it will be
more helpful for the user to smartly perform the trade.

Fig 5.3.1 Token Economics

3
CHAPTER 6 : TESTING OF SOFTWARE APPLICATION

Software testing is the process of evaluating a software system or application with the
intention of identifying any errors, bugs, or defects. The main objective of software
testing is to ensure that the software meets its requirements and functions as expected.
Other objectives of software testing include:

1. To find defects early: Testing helps to identify defects early in the software
development life cycle, which helps to reduce the cost and effort required to fix
them later.

2. To improve software quality: Testing helps to identify and remove defects that
could affect the quality of the software, such as errors in functionality, usability,
performance, security, and compatibility.

3. To increase user satisfaction: Testing helps to ensure that the software meets the
needs and expectations of the end-users, which can help to increase user
satisfaction and adoption.

4. To ensure compliance with standards: Testing helps to ensure that the software
complies with relevant standards, such as industry standards or regulatory
requirements.

5. To improve developer productivity: Testing helps to identify defects early,

which can reduce the amount of time developers spend fixing issues later,
allowing them to be more productive.

6. To reduce risk: Testing helps to identify and mitigate risks associated with the
software, such as security risks or performance issues.

3
6.1 Unit Testing

Test Test case Test Case Steps to follow/Input Expected Status

Case ID Name Description Data Result

TC_#01 Test Connect This test case Open the app and click The wallet Pass
Wallet verifies that on the "Connect should be
Functionality the connect Wallet" button. connected
wallet successfully
functionality is Select the type of wallet and the user
working as you want to connect should be able
expected. (e.g. MetaMask). to view their
wallet balance.
Follow the instructions
to connect your wallet.

TC_#02 Test Token This test case Connect your wallet to The tokens Pass
Swap verifies that the app. should be
Functionality the token swap swapped
functionality is Select the token you successfully
working as want to swap from the and the user's
expected. dropdown menu. wallet balance
should be
Enter the amount of updated
tokens you want to accordingly.
swap.

Select the token you

want to receive in
exchange.

Click on the "Swap"

button.

TC_#03 Test Study This test case Open the app and click The details and Pass
Token Details verifies that on the "Study Token relevant
Functionality the study token Details" button. information for
details the selected
functionality is Select the token you token should be
working as want to analyze from displayed
expected. the dropdown menu. accurately,
providing the
View the details and user with
relevant information for valuable
the selected token. insights into the
token's price

4
 and volume
trends.

TC_#04 Test ChatGPT This test case Open the app and click The ChatGPT Pass
API verifies that on the "ChatGpt" API should
Integration the ChatGPT button. generate an
API is accurate and
integrated and Select the token you relevant
working as want to analyze from response to the
expected. the dropdown menu. user's message
or question,
Verify that a response providing
is generated using the valuable
ChatGPT API. information and
insights into
token trading.

TC_#05 Test Invalid This test case Connect your wallet to The app should Pass
Token Swap verifies that the app. display an error
the app message and
handles invalid Select the token you prevent the user
token swap want to swap from the from initiating
inputs dropdown menu. an invalid token
appropriately. swap.
Enter an invalid amount
of tokens (e.g. a
negative value or a
value higher than the
user's balance).

Select the token you

want to receive in
exchange.

Click on the "Swap"

button.

TC_#06 Test Token This test case Connect your wallet to The app should Pass
Swap Fees verifies that the app. calculate and
the app display the
calculates and Select the token you token swap fee
displays token want to swap from the accurately,
swap fees dropdown menu. based on the
accurately. current fee
Enter the amount of structure.
tokens you want to
swap.

Select the token you

4
 want to receive in
exchange.

Click on the "Swap"

button.

View the transaction

details, including the
token swap fee.

TC_#07 Test ChatGPT This test case Open the app and click The ChatGPT Pass
API Accuracy verifies that on the "ChatGpt" API should
the ChatGPT button. generate
API generates accurate and
accurate and Select the token you relevant
relevant want to analyze from responses to a
responses. the dropdown menu. variety of
questions
Verify that the related to token
ChatGPT API generates trading.
accurate and relevant
responses to each
question.

TC_#08 Test User This test case Open the app on The app should pass
Interface verifies that different devices and be responsive
Responsivene the user screen sizes (e.g. and work well
ss interface is desktop, laptop, tablet, on different
responsive and mobile phone). devices and
works well on screen sizes,
different Test each functionality without any
devices and of the app on each issues or
screen sizes. device and screen size. glitches.

TC_#09 Test Token This test case Open the app and select The token Pass
Price Update verifies that a token pair to swap. prices should be
the token updated in
prices are Wait for a few real-time and
updated in minutes and observe reflect the
real-time. the token prices. current market
conditions.

TC_#10 Test Error This test case Connect your wallet to The app should Pass
Handling verifies that the app. handle errors
the app gracefully and
handles errors Attempt to initiate an prevent the user
gracefully. invalid token swap (e.g. from initiating

4
 enter an invalid amount invalid token
or select an unsupported swaps.
token).

Verify that the app

displays an error
message and prevents
the user from initiating
the invalid token swap.

4
CHAPTER 7 : COSTING OF THE PROJECT

7.1 COCOMO Model:

Step 1: Determine the size of the project in lines of code (LOC).

For this project (Decentralized Token Swapping ), the size is 1546 LOC.

Step 2: Determine the complexity of the project.

We need to determine the complexity of the project based on the project's characteristics.
the project has a moderate level of complexity.

Step 3: Calculate the effort required to complete the project.

To calculate the effort, we need to use the COCOMO
formula:

Effort = a * (LOC ^ b) * (c + sum(Si))

Here, a, b, and c are constants that depend on the project's complexity, and Si are the
software size factors. For a project of moderate complexity, the constants are:

a = 3.0
b = 1.12
c = 0.35

The weights for each factor are determined based on the project's characteristics, and are
usually provided in a table in COCOMO model. For our Project the weights are as
follows:

Technical Complexity Factors Weight

Required software reliability 1.10
Size of the application database 0.94
Complexity of product 1.15
Execution time constraints 1.00
Main storage constraints 1.00
Virtual machine volatility 1.18
Analyst capability 0.85
Programmer capability 0.88

4
 Application experience 1.10
Use of software tools 0.90
Multisite development 1.00

We can now calculate the effort required to complete the project:

Effort = 3.0 * (1500 ^ 1.12) * (0.35 + 1.10 + 0.94 + 1.15 + 1.00 + 1.18 + 0.85 + 0.88 +
1.10 + 0.90 + 1.00 + 1.12) = 67 person-months

Step 4: Calculate the duration of the project.

To calculate the duration, we use the
formula:

Duration = 3.67 * (Effort ^ 0.33)

For our project, the duration would be:

Duration = 3.67 * (67 ^ 0.33) = 3.8 months

Step 5: Calculate the total cost of the project.

To calculate the total cost, we need to determine the cost per person-month. the cost
per person-month is ₹3000.

Total cost = Duration * Cost per person-month = 3.8 * ₹3000 = ₹11,400

So, the estimated cost of the decentralized token swapping app using COCOMO model is
₹11,400.

4
CHAPTER 8 : APPLICATIONS OF PROJECT

I. Token Swapping: The primary function of the app is to facilitate the swapping of
various cryptocurrencies in a decentralized manner. This could be useful for users
who want to quickly and easily exchange one cryptocurrency for another.

II. Price Analysis: With the integration of the ChatGPT API, the app can provide
users with price analysis and other market insights for the cryptocurrencies being
traded. This could be useful for traders and investors who want to stay up-to-date
on market trends.

III. Educational Purposes: The app could be used as a tool for learning about
decentralized exchanges and how they work. Users could experiment with
swapping different cryptocurrencies and get a better understanding of how the
process works.

IV. Decentralized Finance (DeFi) Trading: Decentralized token swapping apps are
widely used in the DeFi space to enable users to trade cryptocurrencies without
relying on centralized exchanges. DeFi platforms use smart contracts to facilitate
these trades.

V. Cryptocurrency Wallet Integration: Some decentralized token swapping apps

offer integration with cryptocurrency wallets. This allows users to swap tokens
directly from their wallets, without needing to transfer them to an exchange.

VI. Token Sales: Decentralized token swapping apps can also be used for initial
token sales (ICOs). They can be integrated with smart contracts that manage the
distribution of tokens to investors.

4
CHAPTER 9 : FUTURE SCOPE

I. Adoption of decentralized finance (DeFi): This project is an important

component of the DeFi ecosystem, which is a set of financial applications and
services that are built on blockchain technology and operate in a decentralized
manner. As DeFi continues to grow and mature, DEXs are likely to see increased
usage and adoption.

II. Improvement of user experience: This project has a minimal user experience
compared to centralized exchanges. However, as it will continue to evolve and
improve in future, it is likely that the user experience will become more seamless
and intuitive, making it easier for more people to use them.

III. Advanced analytics: Advanced analytics can be added to the app to help users
make better decisions when swapping tokens.

IV. Integration with other DeFi applications: The app can be integrated with other
DeFi applications such as lending platforms, stablecoins, and prediction markets.

V. Mobile application development: The app can be developed as a mobile

application to make it more accessible to a larger audience.

VI. Advanced security features: Advanced security features such as multi-factor

authentication and biometric authentication can be added to the app to make it
more secure.

4
CHAPTER 10 : CONCLUSION
Centralized Exchanges like Coinbase, Binance, etc. allows exchanges between fiat and
cryptocurrency. Companies that are responsible for the holdings of their customers
operate centralized exchanges. This may create an emotion of insecurity among the
customers as Centralized Exchanges can go Bankrupt anytime. Ex FTX Exchange Also
Unlike peer-to-peer transactions, centralized exchanges often charge high transaction fees
for their services and convenience, which can be especially high when trading in large
amounts.

Thus, the Decentralized Exchange creates a sense of security and builds trust of users for
the system. It also indicates that there is room for peer-to-peer marketplaces ,allowing
users to make transactions anonymously and without third-party involvement.

4
CHAPTER 11 : REFERENCES
Blogs:

● A Graphical Guide for Understanding Uniswap By Hayden Adams and Fernando

Martinelli

● Why are DEXs gaining more popularity? By Kalkine Mehta

IEEE Research Paper:

● A Payment Channel Based Hybrid Decentralized Ethereum Token Exchange By

W. Cai, Z. Wang, J. B. Ernst, Z. Hong, C. Feng, and V. C. M. Leung,
“Decentralized applications: The blockchain-empowered software system,”
IEEE Access, no. 99, 2018

Web Reference

● https://docs.uniswap.org/protocol/V2/guides/smart-contract-integration/quick-start

● https://www.youtube.com/watch?v=gyMwXuJrbJQ&t=19844s

●z