EXAM GUARD

Submitted in partial fulfillment of the requirements of

the degree.
BACHELOR OF ENGINEERING IN COMPUTER
ENGINEERING

By

Manav Purswani (2103143)

Hussain Rangwala(2103146)
Mehek Richharia (2104148)

Supervisor
Prof. Nabanita Mandal

Computer Engineering Department

Thadomal Shahani Engineering College

Bandra(w), Mumbai - 400 050

University of Mumbai
(AY 2023-24)

1
 CERTIFICATE

This is to certify that the Mini Project entitled “EXAM GUARD” is a bonafide work of
Manav Purswani (2103143), Hussain Rangwala (2103146), Mehek
Richharia (2104148) submitted to the University of Mumbai in partial fulfillment of
the requirement for the award of the degree of “Bachelor of Engineering” in
“Computer Engineering”.

(Prof. Nabanita Mandal)

Supervisor

(Prof. Tanuja Sarode) (Prof. G.T. Thampi)

Head of Department Principal

2
 Mini Project Approval

This Mini Project entitled “BALANCE- A productivity and wellbeing solution” by

Manav Purswani (2103143), Hussain Rangwala (2103146), Mehek
Richharia (2104148) is approved for the degree of Bachelor of Engineering in
Computer Engineering.

Examiners

1………………………………………
(Internal Examiner Name & Sign)

2…………………………………………
(External Examiner name & Sign)

Date:

Place:

3
 Contents

Abstract ii

Acknowledgments iii

List of Figures iv

1 Introduction 1
1.1 Introduction
1.2 Motivation
1.3 Problem Statement & Objectives
1.4 Organization of the Report

2 Literature Survey 10

2.1 Survey of Existing System

2.2 Limitation Existing system or research gap
2.3 Mini Project Contribution

3 Proposed System 12

3.1 Introduction
3.2 Architecture/ Framework
3.3 Algorithm and Process Design
3.4 Details of Hardware & Software
3.4 Experiment and Results
3.5 Conclusion and Future work.

References 24

4
 Abstract

The rapid proliferation of mobile phones has led to various challenges, including
their inappropriate use in restricted areas. This project aims to address these
challenges by developing a mobile phone detection system based on YOLOv8, a
state-of-the-art object detection algorithm. This report outlines the methodology,
experiments, and results obtained during the project. The system achieved promising
accuracy in mobile phone detection, providing a valuable tool for enhancing security
in sensitive environments.

5
 Acknowledgement

We would like to express our gratitude and thanks to Prof. Nabanita Mandal for her
valuable guidance and help. We are indebted for her guidance and constant
supervision as well as for providing necessary information regarding the project. We
would like to express our greatest appreciation to our principal Dr. G.T. Thampi and
head of the department Dr. Tanuja Sarode for their encouragement and tremendous
support. We take this opportunity to express our gratitude to the people who have been
instrumental in the successful completion of the project.

Mehek Richharia
Manav Purswani
Hussain Rangwala

6
 Chapter 1

Introduction
This chapter explains the aim, objectives, and scope of the proposed system.

1.1 Introduction
Mobile phone detection is a critical aspect of ensuring security and compliance in various
environments, such as secure facilities, schools, and workplaces. This project addresses
the need for a robust mobile phone detection system based on the YOLOv8 object
detection algorithm. The proposed mobile phone detection system is built upon the
YOLOv8 framework and is designed to address the limitations of existing systems. This
section provides a comprehensive overview of the system's architecture, algorithms, and
experimental results.

1.2 Motivation

The increasing incidents of unauthorized mobile phone usage in restricted areas have
prompted the development of an efficient detection system. Such a system can
significantly enhance security and safety.

There are several reasons why a mobile phone detection website can be beneficial for
individuals and organizations:

1. Preventing Academic Dishonesty: Mobile phones in exam halls can be used for
cheating and academic dishonesty. Students can access information, share answers, or
seek external assistance through text messages or calls. Developing a mobile phone
detection app aims to maintain the integrity of examinations and ensure that students
are evaluated fairly based on their knowledge and skills.

2. Fair Evaluation: Exams are a critical method for assessing a student's understanding
7
 and grasp of subject matter. The presence of mobile phones can undermine the
fairness of the evaluation process. By creating a reliable detection app, you contribute
to creating a level playing field for all students, ensuring that their hard work is
appropriately recognized.

3. Security and Confidentiality: In some cases, exams may contain sensitive or

confidential information, such as standardized tests. Mobile phones can be used to
capture and distribute such content, compromising its security and confidentiality.
Developing a detection app helps protect the privacy and security of examination
materials.

4. Efficient Monitoring: Traditional methods of mobile phone detection, such as

manual searches or metal detectors, can be time-consuming and resource-intensive.
An app automates this process, making it more efficient and reducing the burden on
exam administrators.

5. Technological Advancements: With advancements in technology, mobile phone

detection can be more accurate and less intrusive. Leveraging technologies like
computer vision and machine learning, a mobile phone detection app can identify
devices even if they are concealed or turned off, ensuring comprehensive detection.

6. Cost-Effective Solution: Developing an app can provide a cost-effective and

scalable solution for educational institutions. Instead of investing in expensive
hardware or security personnel, institutions can deploy a mobile phone detection app
on existing devices.

In summary, developing a mobile phone detection app for exam halls addresses the
critical issue of academic integrity, ensures fair evaluation, maintains security, and
embraces technological advancements. It provides an efficient, cost-effective, and
adaptable solution while offering opportunities for learning and skill development in
relevant domains.

8
1.3 Problem Statement & Objectives

Problem statement:

Unauthorized mobile phone use in secure environments such as exam halls poses risks to
security and productivity.

Objectives:

- Develop a mobile phone detection system based on YOLOv8.

- Achieve high accuracy in mobile phone detection.
- Enhance security and compliance in sensitive environments.

1.4 Organization of the Report

This report consists of three chapters. The first chapter deals with introduction of the
topic, problem statement, motivation behind the topic and objectives. The second chapter
is the Literature Survey. It includes all the research work done related to this topic. All
information related to study of existing systems as well as learning of new tools is
mentioned in this chapter. The third chapter is about the proposed system which is used
in this project. The block diagram, techniques used, hardware and software used
screenshots of the project are presented in this chapter. All the documents related to
development of this project are mentioned in References

9
 Chapter 2

Literature Survey
This chapter explains the concepts used in this project, study of existing system and
contribution of this project

2.1 Survey of Existing System

A survey of existing mobile phone detection systems reveals a range of technologies and
approaches used to identify and prevent the use of mobile phones in restricted areas, such
as exam halls, secure facilities, and other sensitive environments. These systems employ
various methods, including signal blocking, mobile phone detection apps, and hardware-
based solutions. Here is an overview of some of the existing mobile detection systems:

1. Signal Jamming Devices:

Cellular Signal Jammers: These devices emit radio frequency signals that interfere with
mobile phone signals, preventing them from connecting to cellular networks. However,
their use is often illegal due to potential disruptions of emergency services.

2. RF Scanners:

RF scanners are used to detect signals emitted by mobile phones. When a mobile phone
is active, it emits radio waves. RF scanners can detect these emissions. However, they do
not distinguish between authorized and unauthorized phones.

3. Mobile Phone Detection Apps:

Some apps, like "No Phone" are designed for use by exam proctors. They can scan for
nearby mobile devices using Bluetooth or Wi-Fi signals, alerting proctors when
unauthorized phones are detected.

10
 4. Network-Based Systems:

These systems monitor network traffic to detect mobile phones. When a phone connects
to a network, the system can identify it. This approach is more suitable for secure
facilities that can control network access.

5. Hardware-Based Systems:

- Metal Detectors: While not specifically mobile phone detectors, metal detectors are
sometimes used to detect any electronic devices, including mobile phones, in secure
areas.

6. Computer Vision and AI:

Some systems use computer vision and artificial intelligence to identify mobile phones
through security cameras. They can analyze video feeds to detect suspicious behavior or
objects.

It's essential to consider the legal and ethical implications of these systems, as well as
their effectiveness and the potential for false positives. The choice of a mobile phone
detection system will depend on the specific requirements, budget, and legal constraints
of the institution or facility implementing the solution.

2.2 Limitation of existing system

Despite the presence of existing systems, there remains a research gap in developing a
highly accurate and real-time mobile phone detection system. Existing systems often lack
robustness and efficiency.

2.3 Mini Project Contribution

This mini-project aims to bridge the research gap by developing a mobile phone detection
system based on YOLOv8. The system offers improved accuracy, real-time detection, and
better adaptability to various scenarios.

11
 Chapter 3

Proposed System
This chapter consists of detailed description about the methodology used, the hardware
and software components, the tools used and also the screenshots of the project

3.1 Introduction

Computer vision and object detection are two closely related fields within the domain of artificial
intelligence and image processing. They enable machines and computer systems to interpret and
understand visual information, making it possible for computers to "see" and identify objects in
images and videos. This has a wide range of applications, from autonomous vehicles and medical
imaging to security systems and augmented reality.

Computer Vision:

Computer vision is a multidisciplinary field that focuses on enabling computers to gain a high-
level understanding of visual data from the world. It involves the development of algorithms
and models that can extract meaningful information from images or video streams. The ultimate
goal of computer vision is to replicate the human visual system's ability to perceive, interpret,
and make decisions based on visual input.
Key components of computer vision include:

1. Image Processing: This involves tasks like image enhancement, filtering, and transformations
to improve image quality or highlight specific features.
2. Feature Extraction: Identifying and extracting relevant features from images, such as edges,
corners, or textures, that are essential for understanding the content.
3. Object Recognition: Recognizing and categorizing objects in images, often using machine
learning and deep learning techniques.
4. Motion Analysis: Detecting and tracking object motion in video sequences, which is crucial
for applications like surveillance and robotics.
5. 3D Reconstruction: Creating 3D models of objects or scenes from 2D images, enabling depth
perception and spatial understanding.

12
Object Detection:

Object detection is a specific task within computer vision that focuses on locating and
identifying objects of interest within an image or video frame. Unlike image classification,
which assigns a label to the entire image, object detection provides a bounding box around each
object and labels them individually. Object detection is typically used in applications where it's
important to know not just what is present in an image, but also where those objects are located.

Object detection often leverages deep learning techniques, such as Convolutional Neural
Networks (CNNs) and more advanced models like Faster R-CNN, YOLO (You Only Look
Once), and SSD (Single Shot MultiBox Detector). These models have revolutionized object
detection by improving accuracy and speed, enabling real-time applications.

Open Images V7:

Open Images V7 is a versatile and expansive dataset championed by Google. Aimed at
propelling research in the realm of computer vision, it boasts a vast collection of images
annotated with a plethora of data, including image-level labels, object bounding boxes, object
segmentation masks, visual relationships, and localized narratives.

Yolov8:
Ultralytics YOLOv8, the latest version of the acclaimed real-time object detection and image
segmentation model. YOLOv8 is built on cutting-edge advancements in deep learning and
computer vision, offering unparalleled performance in terms of speed and accuracy. Its
streamlined design makes it suitable for various applications and easily adaptable to different
hardware platforms, from edge devices to cloud APIs.

OpenCV:
OpenCV is a vast library that helps in providing various functions for image and video
operations. With OpenCV, we can capture a video from the camera. It lets you create a video
capture object which is helpful to capture videos through webcam and then you may perform
desired operations on that video.

CVAT:
CVAT is a web-based, open-source image annotation tool originally developed by Intel and
now maintained by OpenCV. CVAT provides annotation features for object detection,

13
classification, tracking, and segmentation tasks.
Python:
Python is a high-level, general-purpose programming language. Its design philosophy
emphasizes code readability with the use of significant indentation. Python is a multi-paradigm
programming language. Object-oriented programming and structured programming are fully
supported, and many of their features support functional programming and aspect-oriented
programming .

3.2 Architecture

 Figure 1: Flow Diagram

LANDING PAGE

NO ACCOUNT
LOGIN

SIGN UP HOMEPAGE

TASK LIST TIMER

ONGOING PROJECTS FOCUS MODE

USER EFFICIENCY

CREATED LISTS

CREATE NEW PROJECT

14
3.3Algorithm and Process Design

The YOLOv8 object detection process is based on deep learning and convolutional
neural networks (CNNs). YOLOv8 splits the input image into a grid and assigns
bounding boxes and class predictions to objects within grid cells. The system uses anchor
boxes and anchor box clustering to improve detection accuracy.

Implementing YOLOv8 for mobile phone detection with a frontend involves several
steps. YOLO (You Only Look Once) is a popular real-time object detection algorithm
known for its speed and accuracy. YOLOv8 is one of its latest versions, and it can be
used for various object detection tasks, including mobile phone detection. Here's a high-
level overview of the process:

1. Data Collection and Annotation:

 Gather a dataset of images containing mobile phones.

 Annotate the images with bounding boxes around the mobile phones to create
labeled training data.

2. Model Training:

 Preprocess the annotated dataset using cvat.

 Train a YOLOv8 model on the dataset
 Fine-tune the model for mobile phone detection using transfer learning, starting
from a pre-trained YOLOv8 model on a large object detection.

3. Model Optimization:

 Optimize the model for deployment:

 Prune the model to reduce its size while maintaining performance.
 Compress the model for faster inference on mobile devices.

15
4. Backend Implementation:

 Develop a backend server to host the optimized YOLOv8 model.

 Create an API to receive images from the frontend and perform inference using
the model.
 Return the detected mobile phone objects with their bounding boxes as the API
response.

5. Frontend Implementation:

 Develop a user-friendly frontend application for users to interact with.

 Allow users to upload images.
 Send the uploaded images to the backend API for mobile phone detection.
 Display the detection results with bounding boxes on the frontend.

6. Deployment:

 Deploy the backend API on a cloud server or a hosting platform.

 Publish the frontend.

7. User Testing and Feedback:

 Testing is vital before making any application live. Hence, on the development
of each feature, they were tested independently and after integration, the system
was tested as a whole. If any bugs were found, it was immediately worked upon.
 Conduct user testing to ensure the system works as expected.
 Gather feedback and make improvements based on user suggestions.

This is a high-level overview, and each step involves detailed technical work. Depending
on your expertise, you may need to work with deep learning, web development, mobile
app development, and deployment technologies. Additionally, consider privacy and
security measures when handling user data and images.

16
3.4 Details of Hardware & Software

Hardware:

● Ethernet

● Processor: Intel 10TH Generation and above

● high-end GPU for efficient training and inference.

Software:

● Windows 11

● Internet connectivity Ethernet

● Python for coding

3.4Results
3.4.1 List of Results
1. Validation
2. Testing
3. Index Page
4. About us Page
5. Sign Up Page
6. Log In Page

17
3.4.2 Implementation

1. Validation
2. Testing
3. Index Page
4. About us Page
5. Sign Up Page
6. Log In Page

18
3.5Conclusion and Future Work
The proposed mobile phone detection system based on YOLOv8 demonstrates its
potential for accurate detection.

In conclusion, this project has provided a strong foundation for future work in
improving real-time detection, extending the system to video streams, and enhancing
its adaptability to diverse environments.

19
References
● Vishal Khoda "HTML5 Complete Reference"

GeeksForGeeks.com [Online]

Accessed at: February 5, 2023

Available at: https://www.geeksforgeeks.org/html5-completereference/

● W3 Schools "CSS Tutorial"

W3Schools.com [Online]

Accessed at: February 20, 2023

Available at: https://www.w3schools.com/css/default.asp

● Ultralytics “YOLOv8”

Ultralytics.com [Online]

Accessed at: February 27, 2023

Available at: https://docs.ultralytics.com/

20