Don`t Worry! This report is 100% safe & secure.

It`s not available publically and it`s not accessible by search engines
(Google, Yahoo. Bing, etc)

Sentence
CHAPTER 1 INTRODUCTION Coronaviruses are a form of the virus that can trigger a variety of illnesses, from colds to life-
threatening infections including Middle East Respiratory Syndrome to Severe Acute Respiratory Syndrome. In December
of last year, the first corona virus-infected patient was discovered. COVID-19 has been a worldwide pandemic since that
time. Humans all around the world are in precarious conditions as a consequence of the pandemic. Every day, a huge
amount of people become contaminated with the disease and suffer as a result of it. According to the World Health
Organization (WHO), the most frequent signs of coronavirus are fever, dry cough, exhaustion, diarrhea, loss of taste, and
smell. Many researchers and developers are working with diseases for several years using machine learning and deep
learning. Jiang et al. suggest Retina Facemask, a paradigm for detecting the face mask that combines it with a bridge
entity elimination algorithm. The developed model includes a single-stage detector that uses a feature pyramid network
to achieve slightly better precision and recall than the baseline result. To address the lack of datasets, they used a
learning algorithm, well DL methodology. Gupta et al. suggested a model implement social distance utilizing smart
communities and Intelligent Transportation Systems during the COVID-19 pandemic (ITS). Their model called for the
installation of sensors in the city to monitor the movement of objects in real-time, as well as the development of a data-
sharing network. Won Sonn and Lee clarify how a smart city will aid in the control of coronavirus spread in South Korea.
A time-space cartographer sped up the city's communication monitoring, which included patient movement, transaction
background, mobile phone use, and cell phone position. CCTV cameras in residential building hallways have been
monitored in real-time. The use of face masks in public places is increasing due to the COVID- 19 epidemic all over the
world. People used masks to protect their health from air pollution. While other people are uncomfortable about their
looks, they hide their feelings in public to hide their faces. More than five million cases were infected by COVID- 19 in
less than 6 months across 188 countries. The virus spreads in crowded and overcrowded places. We can handle and
predict new diseases with the help of new technologies such as AI, IoT, Big data, and Machine learning. To better
understand infection rates might be decreased through our technique. People are forced by restrictions to use face
masks in public in our country. These laws and restrictions were created as a precaution to the exponential increase in
victims and deaths in many areas. The process of monitoring greater groups of people is becoming more hard in
crowded places. So we will create an automation process to recognizing the faces mask. In this, we are introducing a
facemask detection model that is based on CV and deep learning. The proposed model can be combined with Recording
Cameras to control the COVID-19 spread by allowing the detection of people who are using face masks / not using face
masks. The model is combined between DL and classical machine learning techniques with Open cv, Tensor flow, and
Keras. We will achieve accuracy and consume the least time in the process of preparing and detecting of face masks.
1.1 Motivation The COVID-19 coronavirus pandemic is wreaking havoc on the world's health. The healthcare sector is in
a state of disaster. Many precautionary steps have been taken to prevent the spread of this disease, including the usage
of a mask, which is strongly recommended by the World Health Organization (WHO). 1.2 Problem Definition The rapid
outbreak of COVID-19 has caused serious harm and infected tens of millions of people worldwide. Since there is no
specific treatment, using masks has become an effective method to prevent the spread of COVID-19.   CHAPTER 3
SOFTWARE REQUIREMENTS SPECIFICATION SRS is detail of software to be developed. It defines out functional and non-
functional requirements and also may include a set of use cases that describe user interactions that the proposed
software must provide to its users. To understand any project, they must come up with a software requirements
specification (SRS) listing out their requirements, how are they going to meet them and how will they complete the
project. It will help the project team members to save upon their time and energy as they can comprehend how are
going to go about the project. Doing this will also enable the team to find out about the limitations and the risks early.
3.1 INTRODUCTION The use of face masks in public is increasing due to the COVID-19 epidemic throughout the nation.
People used face masks to prevent themself from pollution. While some people are uncomfortable about their looks,
they hide their feelings in public to hide their faces. More than four to 5 million cases were getting infected by COVID- 19
in less than 6 to 7 months across 199 countries. The virus spreads in crowded and overcrowded places. Now as per the
new law/restrictions people are forced to use masks in public places which are for their protection and others as well.
These protocols(rules and restrictions) were developed as an action to the exponential growth in cases and deaths in
many places across the countries. The process of monitoring greater groups of people is becoming more difficult in a
public areas. So we will create an automation process for detecting the faces. Here we introduce a facemask detection
model that is based on CV and machine learning. The proposed model can be combined with Recording Cameras to
impede the COVID-19 spread by allowing the face detection of people who are using masks or not using face masks. The
model is integration is a classical machine learning technique with Open cv, Tensor flow, and Keras. (python libraries)
We will provide high accuracy and consume less time in the process of preparing the model and detection of objects (i.e
mask /nonmask). 3.1.1 PROJECT SCOPE By the development of our project, we can detect if the person is using a face
mask which would be a great help to society. The accuracy of the model will be maintained and the optimization of the
model is a continuous process and So we are building a highly accurate solution. We can prevent people from Virus
Spread through this System. 3.1.2 ASSUMPTIONS AND DEPENDENCIES 1. Assumptions • User i.e Admin must have basic
knowledge of computer. 2. Dependencies • Data will be fetched from the video   3.2 FUNCTIONAL REQUIREMENTS 1.
We built a greater dataset of masked faces, the Properly-Using Masked Face Detection Dataset (PWMFD). Three
predefined classes were included concerning the targeted cases. 2. Combined with the channel dimension of the
attention mechanism, the backbone of YOLOv3 was improved. We add the Squeeze and Excitation block (SE block)
between the CL of Darknet53, which helped the model to learn the relationship between channels. The accuracy of the
model was improved with negligible additional computational cost. 3. We proposed an algorithmic improvement to the
loss function of the original YOLOv3. We have replaced the Mean Squared Error (MSE) with GIoU loss and employed focal
loss to address the problem of extreme foreground-background class imbalance. Further analysis of these modifications
in our experiments was done, which showed that with the SE block, GIoU loss, and focal loss, the mAP was improved by
6.7% from the baseline model. 4. To adjust the model to application scenarios in the real world, we applied the mix-up
technique to further improve the robustness of the model.   3.3 EXTERNAL INTERFACE REQUIREMENTS External
interface requirements specify hardware, software, or database elements with which a system or component must
interface." This section provides information to ensure that the system will communicate properly with external
components. 3.3.1 USER INTERFACES • The user will be provided with a simple and user-friendly GUI. The GUI
components of the System will be developed using swing. • The application provides a good graphical interface for the
user that operates • on the system, performing the required task such as giving authentication • details and input to the
system. Allows the user to view quick reports like successful log in and final output as a frequent itemset in between
particular times. 3.3.2 HARDWARE INTERFACES • Processor: I3 and above • RAM: minimum 3GB or above • Hard Disk:
30 GB or above • Camera 3.3.3 SOFTWARE INTERFACES • Operating System: Windows and Linux • Technology: Java 8 •
Database: MySQL 5.5 • Python 3.8 • Eclipse IDE and Python IDE 3.3.4 COMMUNICATION INTERFACES JAVA Java: Java
platform is used for developing applications. JDK 1.8: Java development kit is used for running the program it has its own
JRE.JRE 1.8: It is a Java runtime environment used for compilation. JVM: Java virtual machine is used for running the java
program. Jvm has 3 notions i.e. specification, implementation, and instance. JMF: Java media framework is used to
manage and configure external and internal hardware devices in an application on the Java platform. Communication
Interfaces The stakeholders will communicate through the application interface. FIGURE 3.3.3 Representing
Communication Interface   3.4 NON FUNCTIONAL REQUIREMENTS NFR specifies the quality attribute of a software
system. The software system is judged based on Responsiveness, Usability, Security, Portability, and other non-
functional standards that are critical to the success of the software system. 3.4.1 PERFORMANCE REQUIREMENTS The
proposed system that we are going to develop will be used by the greater scale and small scale organizations at a
private level. Therefore, it is expected that the system would perform functionally all the requirements that are
specified. 1. The performance of the system should be fast and accurate 2. System shall tackle expected and non-
expected errors in ways that prevent loss Such that there is no hindrance while manipulating diseases Safety
Requirements Systems Knowledge base should be saved somewhere else(back up) for future use of similar kind of work
and also for extending this work. Platform Independent: The application should be platform-independent and run on any
OS. 3.4.2 SAFETY REQUIREMENTS Data safety must be ensured by arranging for a secure and reliable spread media. The
source and destination information must be entered correctly to avoid any misuse or malfunctioning. 3.4.3 SECURITY
REQUIREMENTS All the user details shall be accessible to only high authority persons. 3.4.4 SOFTWARE QUALITY
ATTRIBUTES • Maintainable software should have Encourage in-code documentation ( .py docs in .ipynb, etc.) • Use a
wiki to maintain the documentation • Unit Tests = Good for documenting specifications • Comments = Good for
documenting design decisions. • Unit Tests + Comments = Good for documenting specifications and design decisions. =
Easily maintainable software. • Providing better transparency into the changes happening to the system • Propagating
environmental changes and code change more rapidly while maintaining control. 3.5 SYSTEM REQUIREMENTS System
demands are the configuration that a system must have for a good hardware or software application to run smoothly
and efficiently. 3.5.1 Database Requirements: The database is required to be created and maintained in MySQL Server.
Stored procedures are also created to retrieve and operate on data. A Database will be required in the following
scenarios: • Communication Interface process is intended to give an approach to archive and track extend interfaces
from the Planning stage (FEP) to the end of the projects. • The system uses the HTTP protocol for communication over
the internet and for the intranet communication will be through TCP/IP protocol suite. • Real-time data handling and
processing: Sensors used in IoT system gathers some real-time decisions that are made based on captured data. •
Capability to handle heterogeneous data: DBMS must be able to handle data diversity. • Spatiotemporal scalability: The
system gathers real-world data which shows spatial as well as temporal characteristics. Spatiotemporal phenomena
have become an important aspect of many real-world applications. As data objects other real-world have attributes
related to both space and time, and managing them using existing RDBMS is complex and inefficient, as These objects
which show spatiotemporal behavior are multidimensional. • Fast and reliable: -The query language for the system must
produce the data at a very fast rate. The quantities of data are so vast that it would be unrealistic to expect any sort of
uniform structure except for closed systems. Current popular query languages like SQL rely on structured data. Semi-
structured data on the internet can be represented in Hypertext markup language(html5) It is a well-accepted
technology that supports interoperability at a technical rather than a semantic level. CSS3, a language for querying
HTML, can combine documents, web pages, and links to relational databases. 3.5.2 Software Requirements JDK 7: • The
Java Development Kit (JDK) is an SDE used for developing Java applications and applets. It includes the JRE, an
interpreter/loader (java), javac, jar, Javadoc, and other tools needed in Java development. • JVM is an abstract computing
machine that enables a computer to run a Java program. There are three notions of the JVM: specification,
implementation, and instance. The specification is a document that formally describes what is needed of a JVM
implementation. Having a single specification ensures all implementations are interoperable. • The Java Virtual Machine
implementation is a computer program that meets the requirements of the JVM specification. An instance of a JVM is an
implementation running in a process that executes a computer program compiled into Java byte code. Operating
System: Windows or Linux Technology: Java and J2EE IDE: Eclipse or Net Bean Database: MYSQL & File System Java
Version: JDK1.6 or Above Algo Implementation: Python 3.5.3 Hardware Requirements Hardware - Intel Core 2 Duo or
Above Speed - 1.1 GHz RAM - 1 GB Hard Disk - 20 GB 3.5.4 INTERNALIZATION REQUIREMENTS The system only supports
the English language. 3.5.5 LEGAL REQUIREMENTS Licensed copies need to be purchased for the application/software
that is used by the client.   3.6 ANALYSIS MODEL: SDLC MODEL TO BE APPLIED The SDLC, is the application
development life-cycle, is a term used in systems engineering, information systems, and software engineering to
describe a process for planning, creating, testing, and deploying an information system. The systems development life-
cycle concept applies to a range of hardware and software configurations. A system can have different parts like
hardware only, software, or a combination of both. An SDLC has different parts in a number of needed and distinct work
phases which are used by engineers and systems developers to plan for, design, build, test, and deliver information
systems. Like anything that is developed on an assembly line, an SDLC aims to produce high-quality systems that meet
or are expected by customer, customer requirements, by delivering systems that move clearly defined phases, within
scheduled time frames and cost estimates. Computer systems are complex and often link multiple systems potentially
supplied by different software vendors.   Waterfall model – design The waterfall approach was the first Software
Development Life Cycle Model to be used widely in SE to ensure the success of the project. In "The Waterfall" approach,
the whole process of software development is into different phases. In the Waterfall model, the output of one phase is
the input for the next phase. The following illustration is a representation of the different phases of the Waterfall Model.
SDLC Waterfall Model:- The sequential phases in the Waterfall model are – Requirement Gathering and analysis − All
possible requirements of the system to be developed are captured in this phase like we have collected data of previous
matches and documented in a requirement specification document. System Design − While developing the system it
needs to be designed first so that the system implementation is done properly. In this phase through the SRS document,
the needs given by cthe ustomers are designed. Implementation – As we know waterfall model has an implementation
phase where all the development work is done i.e development of software is done with a crossing check-in the SRS
document and output from the design phase. Integration and Testing – In this phase, the testing of software is done
using a different approaches in testing like unit , integration etc. The final output is taken from implementation phase for
testing it . Deployment of system – After testing all the functional and non functional requirements from SRS the final
stage is deployment phase . In this phase the software that is developed is send or deployed in user / customer
environment . Maintenance – After deploying the software there is a need to patch up is any defaults are found in the
customer environment .In this phase all the faults and bugs are solved after deployment of a software. All these phases
are integrated to each other in which progress is seen as flowing steadily downwards (like a waterfall) through the
phases. The next phase is started only after the defined set of goals are achieved for previous phase and it is signed off,
so the name "Waterfall Model". In this model, phases do not overlap. 3.7 System Implementation Plan 1. Implementing
Login and Registration Model (2-3 Weeks) 2. Implementing Dataset Preprocessing and Feature Extraction (2-3 Weeks) 3.
Implementing Convert Image to Face Model (2-3 Weeks) 4. Implementing Apply Yolo Algorithm Model (2-3 Weeks) 5.
Implementing LSTM Module (1 Week) 6. Unit Testing for each developed model/module (1-2 Weeks) 7. Integrating Above
Models (2-3 Weeks) 8. Integration Testing (2 Weeks) 9. System Testing (3 Weeks) 10. Acceptance Testing (2-4 Weeks)
11. Improvements Based on Reviews and Testing: parallel process (2 weeks) PERT Table Activity Time required (days)
Description A 20 Implementing Login and Registration Model B 20 Implementing Dataset Preprocessing and Feature
Extraction C 30-35 Implementing Convert Doc to text Model D 20 Implementing Apply LSTM Algorithm Model E 20
Implementing LSTM Module F 20 Integration of implemented modules. G 40 Evaluation & improvements based on
testing. Table 3.1: PERT Table PERT Diagram Figure 3.3: PERT diagram   CHAPTER 4 SYSTEM DESIGN The major
requirement for implementing this project using java, python programming language along with Machine learning ML,
CV and also with python libraries. We are using YOLO Algorithm in our proposed system. Implementation: We have four
modules 1. Datasets Collecting: We collect no of data sets with face mask and without masks. we can get high accuracy
depends on collecting the number of images. 2. Datasets Extracting: We can extract the features using mobile net v2 of
mask and no mask sets 3. Models Training: We will train the the model using open cv, keras (python library). 4.
Facemask Detection : We can detect Pre-processing image and also detect via live video . If people use mask, it will
permit them if not then it will give the buzzer to use mask to prevent them from virus spread. . 4.1 SYSTEM
ARCHITECTURE Histopathological images are categorized by three methods. The first method is nuclei segmentation
that signifies cellular changes, the second method deals about texture properties, and the third method . based on the
dissimilarities of colour densities. A shape feature is one of the important features that define the behavior of mitosis.
Finally, the best shape features are extracted, which is describes the mitosis behavior. Texture features are extracted
using of detected nuclei. The text features are divided into three types like co-occurrence matrix, run-length matrix, and
local phase quantization. Fig 4.1 System Architecture For An Approach Against Covid 19 : Face Mask Detection And
Recognition With Machine Learning 4.2 DATA FLOW DIAGRAMS In Software engineering DFD(data flow diagram) can be
drawn to show the system of different levels of abstraction. Higher-level DFDs are partitioned into low levels-hacking
more information and functional elements. Levels in DFD are numbered 0, 1, 2 or beyond. Here, we will see mainly 3
levels in the data flow diagram, which are: 0-level DFD, 1-level DFD, and 2-level DFD. 4.2.1 DFD0 : It is also known as a
context diagram. It’s designed to be an abstraction view, showing the system as a single process with its relationship to
external entities. Fig 4.2.1 DFD 0 For An Approach Against Covid 19 : Face Mask Detection And Recognition With
Machine Learning   4.2.2 DFD1: In 1-level DFD, the context diagram is decomposed into multiple bubbles/processes. In
this level, we highlight the main functions of the system and breakdown the high-level process of 0-level DFD into sub
processes. Fig 4.2.2 DFD 1 For An Apporach Against Covid 19 : Face Mask Detection And Recoginition With Machine
Learning 4.2.3 DFD2: Fig 4.2.3 DFD 2 For An Approach Against Covid 19 : Face Mask Detection And Recognition With
Machine Learning 4.3 UML DIAGRAMS A class diagram in the Unified Modeling Language (UML) is a type of static
structure diagram that describes the structure of a system by showing the system. 4.3.1 USE CASE DIAGRAM Use-case
diagram models the behavior of a system and help to capture the requirements of the system. Use-case diagrams detail
the high-level functions and scope of a system. These diagrams also identify the interactions between the system and its
actors. Fig 4.3.1 Use Case For An Approach Against Covid 19 : Face Mask Detection And Recognition With Machine
Learning 4.3.2 SEQUENCE DIAGRAM Sequence diagrams, commonly used by developers, model the interactions between
objects in a single use case. They illustrate how the different parts of a system interact with each other to carry out a
function, and the order in which the interactions occur when a particular use case is executed. Fig 4.3.2 Sequence
Diagram For An Apporach Against Covid 19 : Face Mask Detection And Recoginition With Machine Learning 4.3.3 ER
DIAGRAM An ER diagram shows the relationship among entity sets. An entity set is a real time object ,entities and these
entities can have common attributes. In terms of DBMS, an entity is a table or attribute of a table in database, so by
showing relationship among tables and their attributes, ER diagram shows the complete logical structure of a database.
Fig 4.3.3 E.R Diagram For An Apporach Against Covid 19 : Face Mask Detection And Recoginition With Machine Learning
4.3.4 CLASS DIAGRAM A class diagram resembles a flowchart in which classes are portrayed as boxes, each box having
three rectangles inside. The top rectangle contains the name of the class; the middle rectangle contains the attributes of
the class; the lower rectangle contains the methods, also called operations, of the class. Fig 4.3.4 Class Diagram For An
Apporach Against Covid 19 : Face Mask Detection And Recoginition With Machine Learning 4.3.5 Component Diagram In
this uml diagram we describe the organization and writing of physical components that are used in the project . It will
also cover that did we have covered the planned development in it . This will help us in implementation model . Fig 4.3.5
Component Diagram For An Apporach Against Covid 19 : Face Mask Detection And Recoginition With Machine Learning
  4.3.6 Deployment Diagram Deployment Diagram is used to check the topology of the physical components of a
system where the hardware components are deployed. It describes the static deployment view of the system.
Deployment diagram consist nodes and their relationships. Fig 4.3.6 Deployment Diagram For An Apporach Against
Covid 19 : Face Mask Detection And Recoginition With Machine Learning   CHAPTER 5 OTHER SPECIFICATION In this
chapter we are going to see the specifications which includes advantages, limitations, future scope & future work etc.
5.1 Advantages • Pandemic has put us in such a situation that useing a mask has become essential world wide. • Our
project proposes a method to detect mask on human face, which will be useful in offices, other work place with lot of
people coming together to work. • Physical Monitoring is very difficult for officers to check whether the peoples are
useing mask or not. So in our technique, We are using web cam recording to detect peoples face mask and to prevent
from virus spread. • It has fast and high accuracy • This system can be implemented in many public places such as
ATMs, Banks etc 5.2 Limitations : • Massive data storage burden. The ML technology used in face detection requires
powerful data storage that may not be available to all users. • Detection is vulnerable. While face detection provides
more accuracy in results than manual identification processes, it can also be more easily shown by changes in
appearance or camera angles. • A potential breach of privacy. Face recognition ability to help the government track
criminals creates huge benefits; however, the same recording can allow the government to observe private citizens.
Strict regulations must be set to ensure the technology is used fairly and in compliance with human privacy rights. 5.3
Conclusions & Future Work :- The proposed system to classify face mask detection using COVID-19 precaution in images
using yolo algorithm. The work opens interesting future directions for researchers.The proposed technique can be
combined into any high-resolution video recording devices and not limited to mask detection only. Secondly, the model
can be trained and upgraded to mask datasets that include different images related to correctly/incorrectly use mask
and achieve the ultimate purpose of detecting facemask for cutting down the risk of contagious diseases. 5.4 Future
Scope: In our future work, we will collect more data and make a balance between different categories of the data to
improve the accuracy. We will consider parameters and flops into consideration and deploy advanced level of YOLOv3 on
lightweight devices, which can further contribute to global health. CHAPTER 6 CONCLUSION The proposed system to
classify face mask detection using COVID-19 precaution in images using yolo algorithm. The work opens interesting
future directions for researchers.. The model can be trained and upgraded to mask datasets that include different
images related to correctly/incorrectly use mask and achieve the ultimate purpose of detecting facemask for cutting
down the risk of contagious diseases.  

Report Title: Plagiarism Report

Report Link: https://www.check-plagiarism.com/plag-report/51941880f27dc8ed6753c2d012a7082
(Use this link to send report to anyone) cd411e1638902661

Report Generated Date: 07 December, 2021

Total Words: 4176

Total Characters: 27526

Keywords/Total Words Ratio: 0%

Excluded URL: No

Unique: 79%

Matched: 21%

Sentence wise detail:

CHAPTER 1 INTRODUCTION Coronaviruses are a form of the virus that can trigger a variety of
illnesses, from colds to life-threatening infections including Middle East Respiratory Syndrome to Severe Acute
Respiratory Syndrome.
In December of last year, the first corona virus-infected patient was discovered.
COVID-19 has been a worldwide pandemic since that time.
Humans all around the world are in precarious conditions as a consequence of the pandemic.
Every day, a huge amount of people become contaminated with the disease and suffer as a result of it.
According to the World Health Organization (WHO), the most frequent signs of coronavirus are fever, dry cough,
exhaustion, diarrhea, loss of taste, and smell. Many researchers and developers are working with diseases for several
years using machine learning and deep learning. Jiang et al. (0)
According to the World Health Organization (WHO), the most frequent signs of coronavirus are fever, dry cough,
exhaustion, diarrhea, loss of taste, and smell. suggest Retina Facemask, a paradigm for detecting the face mask that
combines it with a bridge entity elimination algorithm. (1)
The developed model includes a single-stage detector that uses a feature pyramid network to achieve slightly better
precision and recall than the baseline result.
To address the lack of datasets, they used a learning algorithm, well DL methodology. Gupta et al. suggested a model
implement social distance utilizing smart communities and Intelligent Transportation Systems during the COVID-19
pandemic (ITS). (2)
Their model called for the installation of sensors in the city to monitor the movement of objects in real-time, as well as
the development of a data-sharing network.
Won Sonn and Lee clarify how a smart city will aid in the control of coronavirus spread in South Korea.
A time-space cartographer sped up the citys communication monitoring, which included patient movement, transaction
background, mobile phone use, and cell phone position.
CCTV cameras in residential building hallways have been monitored in real-time.
The use of face masks in public places is increasing due to the COVID- 19 epidemic all over the world.
People used masks to protect their health from air pollution.
While other people are uncomfortable about their looks, they hide their feelings in public to hide their faces. More than
five million cases were infected by COVID- 19 in less than 6 months across 188 countries. (3)
The virus spreads in crowded and overcrowded places.
We can handle and predict new diseases with the help of new technologies such as AI, IoT, Big data, and Machine
learning. To better understand infection rates might be decreased through our technique. (4)
People are forced by restrictions to use face masks in public in our country.
These laws and restrictions were created as a precaution to the exponential increase in victims and deaths in many
areas.
The process of monitoring greater groups of people is becoming more hard in crowded places. So we will create an
automation process to recognizing the faces mask. (5)
The process of monitoring greater groups of people is becoming more hard in crowded places. In this, we are introducing
a facemask detection model that is based on CV and deep learning. (6)
The proposed model can be combined with Recording Cameras to control the COVID-19 spread
by allowing the detection of people who are using face masks / not using face
masks.
The model is combined between DL and classical machine learning techniques with Open cv, Tensor flow, and Keras.
We will achieve accuracy and consume the least time in the process of preparing and detecting of face masks. 1.
1 Motivation The COVID-19 coronavirus pandemic is wreaking havoc on the worlds health. The healthcare sector is in a
state of disaster. (7)
1 Motivation The COVID-19 coronavirus pandemic is wreaking havoc on the worlds health. Many precautionary steps
have been taken to prevent the spread of this disease, including (8)
1 Motivation The COVID-19 coronavirus pandemic is wreaking havoc on the worlds health. the usage of a mask, which is
strongly recommended by the World Health Organization (WHO). (9)
1 Motivation The COVID-19 coronavirus pandemic is wreaking havoc on the worlds health. 1. (10)
2 Problem Definition The rapid outbreak of COVID-19 has caused serious harm and infected tens of millions of people
worldwide. Since there is no specific treatment, using masks has become an effective method to prevent the spread of
COVID-19. (11)
2 Problem Definition The rapid outbreak of COVID-19 has caused serious harm and infected tens of millions of people
worldwide. CHAPTER 3 SOFTWARE REQUIREMENTS SPECIFICATION SRS is detail of software to be developed. (12)
It defines out functional and non-functional requirements and also may include a set of
use cases that describe user interactions that the proposed software must provide to its users.
To understand any project, they must come up with a software requirements specification (SRS) listing
out their requirements, how are they going to meet them and how will they complete the
project.
It will help the project team members to save upon their time and energy as they can comprehend how are going to go
about the project.
Doing this will also enable the team to find out about the limitations and the risks early. 3.
1 INTRODUCTION The use of face masks in public is increasing due to the COVID-19 epidemic throughout the nation.
People used face masks to prevent themself from pollution.
While some people are uncomfortable about their looks, they hide their feelings in public to hide their faces.
More than four to 5 million cases were getting infected by COVID- 19 in less than 6 to 7 months across 199 countries.
The virus spreads in crowded and overcrowded places.
Now as per the new law/restrictions people are forced to use masks in public places which are for their protection and
others as well.
These protocols(rules and restrictions) were developed as an action to the exponential growth in cases and deaths in
many places across the countries.
The process of monitoring greater groups of people is becoming more difficult in a public areas.
So we will create an automation process for detecting the faces.
Here we introduce a facemask detection model that is based on CV and machine learning.
The proposed model can be combined with Recording Cameras to impede the COVID-19 spread by allowing the face
detection of people who are using masks or not using face (13)
The proposed model can be combined with Recording Cameras to impede the COVID-19 spread masks. (14)
The model is integration is a classical machine learning technique with Open cv, Tensor flow, and Keras.
(python libraries) We will provide high accuracy and consume less time in the process of preparing the model and
detection of objects (i. e mask /nonmask). 3.1.
1 PROJECT SCOPE By the development of our project, we can detect if the person is using a face mask which would be a
great help to society.
The accuracy of the model will be maintained and the optimization of the model is a continuous process and So we are
building a highly accurate solution.
We can prevent people from Virus Spread through this System. 3.1. 2 ASSUMPTIONS AND DEPENDENCIES 1. (15)
Assumptions • User i.
e Admin must have basic knowledge of computer. 2.
Dependencies • Data will be fetched from the video 3.
2 FUNCTIONAL REQUIREMENTS 1.
We built a greater dataset of masked faces, the Properly-Using Masked Face Detection Dataset (PWMFD).
Three predefined classes were included concerning the targeted cases. 2. Combined with the channel dimension of the
attention mechanism, the backbone of YOLOv3 was improved. (16)
We add the Squeeze and Excitation block (SE block) between the CL of Darknet53, which helped the model to learn the
relationship between channels.
The accuracy of the model was improved with negligible additional computational cost. 3.
Allows the user to view quick reports like successful log in and final output as a frequent itemset in between particular
times. 3.3.
2 HARDWARE INTERFACES • Processor: I3 and above • RAM: minimum 3GB or above • Hard Disk: 30 GB or above •
Camera 3.3.
3 SOFTWARE INTERFACES • Operating System: Windows and Linux • Technology: Java 8 • Database: MySQL 5.5 •
Python 3.
8 • Eclipse IDE and Python IDE 3.3.
4 COMMUNICATION INTERFACES JAVA Java: Java platform is used for developing applications. JDK 1.
8: Java development kit is used for running the program it has its own JRE. JRE 1.
8: It is a Java runtime environment used for compilation.
JVM: Java virtual machine is used for running the java program.
Jvm has 3 notions i. e.
specification, implementation, and instance. JMF: Java media framework is used to manage and configure external and
internal hardware devices in an application on the Java platform. (17)
Communication Interfaces The stakeholders will communicate through the application interface. FIGURE 3.3.
3 Representing Communication Interface 3.
4 NON FUNCTIONAL REQUIREMENTS NFR specifies the quality attribute of a software system.
The software system is judged based on Responsiveness, Usability, Security, Portability, and other non-functional
standards that are critical to the success of the software
system. 3.4.
1 PERFORMANCE REQUIREMENTS The proposed system that we are going to develop will be used by the greater scale
and small scale organizations at a private level.
Therefore, it is expected that the system would perform functionally all the requirements that are specified. 1.
The performance of the system should be fast and accurate 2.
System shall tackle expected and non-expected errors in ways that prevent loss Such that there is no hindrance while
manipulating diseases Safety Requirements
Systems Knowledge base should be saved somewhere else(back up) for future use of similar kind of work and also for
extending this work.
Platform Independent: The application should be platform-independent and run on any OS. 3.4.
2 SAFETY REQUIREMENTS Data safety must be ensured by arranging for a secure and reliable spread media.
The source and destination information must be entered correctly to avoid any misuse or malfunctioning. 3.4.
3 SECURITY REQUIREMENTS All the user details shall be accessible to only high authority persons. 3.4.
4 SOFTWARE QUALITY ATTRIBUTES • Maintainable software should have Encourage in-code documentation ( . py docs in
. ipynb, etc.
) • Use a wiki to maintain the documentation • Unit Tests = Good for documenting specifications • Comments = Good
for documenting design decisions. • Unit Tests + Comments = Good for documenting specifications and design
decisions. (18)
= Easily maintainable software.
• Providing better transparency into the changes happening to the system • Propagating environmental changes and
code change more rapidly while maintaining control. 3. (19)
5 SYSTEM REQUIREMENTS System demands are the configuration that a system must have for a good hardware or
software application to run smoothly and efficiently. 3.5.
1 Database Requirements: The database is required to be created and maintained in MySQL Server. Stored procedures
are also created to retrieve and operate on data. (20)
A Database will be required in the following scenarios: • Communication Interface process is intended to give
an approach to archive and track extend interfaces from the Planning stage (FEP) to the end of the
projects.
• The system uses the HTTP protocol for communication over the internet and for the intranet communication will be
through TCP/IP protocol suite.
• Real-time data handling and processing: Sensors used in IoT system gathers some real-time decisions that are made
based on captured data. • Capability to handle heterogeneous data: DBMS must be able to handle data diversity. (21)
• Spatiotemporal scalability: The system gathers real-world data which shows spatial as well as temporal characteristics.
Spatiotemporal phenomena have become an important aspect of many real-world applications.
As data objects other real-world have attributes related to both space and time, and managing them
using existing RDBMS is complex and inefficient, as These objects which show spatiotemporal behavior are
multidimensional.
• Fast and reliable: -The query language for the system must produce the data at a very fast rate.
The quantities of data are so vast that it would be unrealistic to expect any sort of uniform structure except for closed
systems.
Current popular query languages like SQL rely on structured data.
Semi-structured data on the internet can be represented in Hypertext markup language(html5) It is a well-accepted
technology that supports interoperability at a technical rather than a semantic level. (22)
CSS3, a language for querying HTML, can combine documents, web pages, and links to relational databases. 3.5.
2 Software Requirements JDK 7: • The Java Development Kit (JDK) is an SDE used for developing Java applications and
applets.
It includes the JRE, an interpreter/loader (java), javac, jar, Javadoc, and other tools needed in Java development.
• JVM is an abstract computing machine that enables a computer to run a Java program. There are three notions of the
JVM: specification, implementation, and instance. (23)
The specification is a document that formally describes what is needed of a JVM implementation.
Having a single specification ensures all implementations are interoperable.
• The Java Virtual Machine implementation is a computer program that meets the requirements of the JVM specification.
An instance of a JVM is an implementation running in a process that executes a computer program compiled into Java
byte code. (24)
Operating System: Windows or Linux Technology: Java and J2EE IDE: Eclipse or Net Bean Database: MYSQL & File
System Java Version: JDK1.
6 or Above Algo Implementation: Python 3.5.
3 Hardware Requirements Hardware - Intel Core 2 Duo or Above Speed - 1.
1 GHz RAM - 1 GB Hard Disk - 20 GB 3.5.
4 INTERNALIZATION REQUIREMENTS The system only supports the English language. 3.5. 5 LEGAL REQUIREMENTS
Licensed copies need to be purchased for the application/software that is used by the client. 3. (25)
6 ANALYSIS MODEL: SDLC MODEL TO BE APPLIED The SDLC, is the application development life-cycle, is a term used in
systems engineering, information systems, and software engineering to describe a process for planning, creating,
testing, and deploying an information system. (26)
6 ANALYSIS MODEL: SDLC MODEL TO BE APPLIED The SDLC, is the application development life-cycle, is a term used in
The systems development life-cycle concept applies to a range of hardware and software configurations. (27)
A system can have different parts like hardware only, software, or a combination of both.
An SDLC has different parts in a number of needed and distinct work phases which
are used by engineers and systems developers to plan for, design, build, test, and deliver information
systems.
Like anything that is developed on an assembly line, an SDLC aims to produce high-quality systems that meet or
are expected by customer, customer requirements, by delivering systems that move clearly defined phases, within
scheduled time frames and cost estimates. (28)
Computer systems are complex and often link multiple systems potentially supplied by different software vendors.
Waterfall model – design The waterfall approach was the first Software Development Life Cycle Model to be used widely
in SE to ensure the success of the project. In The Waterfall" approach, the whole process of software development
is into different phases. (29)
In the Waterfall model, the output of one phase is the input for the next phase. The following illustration is a
representation of the different phases of the Waterfall Model. (30)
SDLC Waterfall Model:- The sequential phases in the Waterfall model are – Requirement Gathering and analysis − All
possible requirements of the
system to be developed are captured in this phase like we have collected data of previous matches and documented in
a requirement specification document. (31)
System Design − While developing the system it needs to be designed first so that the system implementation is done
properly. In this phase through the SRS document, the needs given by cthe ustomers are designed. (32)
Implementation – As we know waterfall model has an implementation phase where all the development work is done i.
e development of software is done with a crossing check-in the SRS document and output from the design phase.
Integration and Testing – In this phase, the testing of software is done using a different approaches in testing like unit ,
integration etc.
The final output is taken from implementation phase for testing it .
Deployment of system – After testing all the functional and non functional requirements from SRS the final stage is
deployment phase .
In this phase the software that is developed is send or deployed in user / customer environment .
Maintenance – After deploying the software there is a need to patch up is any defaults are found in the customer
environment .
In this phase all the faults and bugs are solved after deployment of a software.
All these phases are integrated to each other in which progress is seen as flowing steadily downwards (like a waterfall)
through the phases. The next phase is started only after the defined set of goals are achieved for previous phase and it
is signed off, so the name Waterfall Model". (33)
All these phases are integrated to each other in which progress is seen as flowing steadily downwards (like a waterfall)
through the phases. In this model, phases do not overlap. 3. (34)
7 System Implementation Plan 1.
Implementing Login and Registration Model (2-3 Weeks) 2.
Implementing Dataset Preprocessing and Feature Extraction (2-3 Weeks) 3.
Implementing Convert Image to Face Model (2-3 Weeks) 4.
Implementing Apply Yolo Algorithm Model (2-3 Weeks) 5.
Implementing LSTM Module (1 Week) 6.
Unit Testing for each developed model/module (1-2 Weeks) 7.
Integrating Above Models (2-3 Weeks) 8.
Integration Testing (2 Weeks) 9.
System Testing (3 Weeks) 10.
Acceptance Testing (2-4 Weeks) 11.
Improvements Based on Reviews and Testing: parallel process (2 weeks) PERT Table Activity Time required (days)
Description A 20 Implementing Login and Registration Model B 20 Implementing Dataset Preprocessing and Feature
Extraction C
30-35 Implementing Convert Doc to text Model D 20 Implementing Apply LSTM Algorithm Model E 20 Implementing
LSTM Module F 20 Integration of implemented modules.
G 40 Evaluation & improvements based on testing. Table 3.
1: PERT Table PERT Diagram Figure 3.
3: PERT diagram CHAPTER 4 SYSTEM DESIGN The major requirement for implementing this project
using java, python programming language along with Machine learning ML, CV and also with
python libraries.
We are using YOLO Algorithm in our proposed system. Implementation: We have four modules 1. (4)
We are using YOLO Algorithm in our proposed system. Datasets Collecting: We collect no of data sets with face mask
and without masks. (4)
we can get high accuracy depends on collecting the number of images. 2.
Datasets Extracting: We can extract the features using mobile net v2 of mask and no mask sets 3. Models Training: We
will train the the model using open cv, keras (python library). 4. (4)
Facemask Detection : We can detect Pre-processing image and also detect via live video .
If people use mask, it will permit them if not then it will give the buzzer to use mask to prevent them from virus spread. .
4.
1 SYSTEM ARCHITECTURE Histopathological images are categorized by three methods. The first method is nuclei
segmentation that signifies cellular changes, the second method deals about texture properties, and the third method .
(38)
based on the dissimilarities of colour densities.
A shape feature is one of the important features that define the behavior of mitosis.
Finally, the best shape features are extracted, which is describes the mitosis behavior.
Texture features are extracted using of detected nuclei.
The text features are divided into three types like co-occurrence matrix, run-length matrix, and local phase quantization.
Fig 4.
1 System Architecture For An Approach Against Covid 19 : Face Mask Detection And Recognition With Machine Learning
4.
2 DATA FLOW DIAGRAMS In Software engineering DFD(data flow diagram) can be drawn to show the system of different
levels of abstraction.
Higher-level DFDs are partitioned into low levels-hacking more information and functional elements. Levels in DFD are
numbered 0, 1, 2 or beyond. (39)
Here, we will see mainly 3 levels in the data flow diagram, which are: 0-level DFD, 1-level DFD, and 2-level DFD. 4.2.
1 DFD0 : It is also known as a context diagram.
It’s designed to be an abstraction view, showing the system as a single process with its relationship to external entities.
Fig 4.2.
1 DFD 0 For An Approach Against Covid 19 : Face Mask Detection And Recognition With Machine Learning 4.2.
They illustrate how the different parts of a system interact with each other to carry out a
function, and the order in which the interactions occur when a particular use case is executed. Fig
4.3. 2 Sequence Diagram For An Apporach Against Covid 19 : Face Mask Detection And Recoginition With Machine
Learning 4.3. (40)
3 ER DIAGRAM An ER diagram shows the relationship among entity sets.
An entity set is a real time object ,entities and these entities can have common attributes.
In terms of DBMS, an entity is a table or attribute of a table in database, so by
showing relationship among tables and their attributes, ER diagram shows the complete logical structure of a database.
Fig 4.3.3 E. (41)
showing relationship among tables and their attributes, ER diagram shows the complete logical structure of a database.
Fig 4.3.3 R Diagram For An Apporach Against Covid 19 : Face Mask Detection And Recoginition With Machine Learning
4.3. (40)
4 CLASS DIAGRAM A class diagram resembles a flowchart in which classes are portrayed as boxes, each box having
three rectangles inside. The top rectangle contains the name of the class; the middle rectangle contains the attributes
(43)
of the class; the lower rectangle contains the methods, also called operations, of the class. Fig
4.3. 4 Class Diagram For An Apporach Against Covid 19 : Face Mask Detection And Recoginition With Machine Learning
4.3. (40)
5 Component Diagram In this uml diagram we describe the organization and writing of physical components that are
used in the project .
So in our technique, We are using web cam recording to detect peoples face mask and to prevent from virus spread.
• It has fast and high accuracy • This system can be implemented in many public places such as ATMs, Banks etc 5.
2 Limitations : • Massive data storage burden. The ML technology used in face detection requires powerful data storage
that may not be available to all users. (45)
2 Limitations : • Massive data storage burden. • Detection is vulnerable. (45)
While face detection provides more accuracy in results than manual identification processes, it can also be more easily
shown by changes in appearance or camera angles. • A potential breach of privacy. (45)
Face recognition ability to help the government track criminals creates huge benefits; however, the same recording can
allow the government to observe private citizens. Strict regulations must be set to ensure the technology is used fairly
and in compliance with human privacy rights. 5. (45)
3 Conclusions & Future Work :- The proposed system to classify face mask detection using COVID-19 precaution in
images using yolo algorithm. The work opens interesting future directions for researchers. (45)
The proposed technique can be combined into any high-resolution video recording devices and not limited to mask
detection only.
Secondly, the model can be trained and upgraded to mask datasets that include different images related to
correctly/incorrectly
use mask and achieve the ultimate purpose of detecting facemask for cutting down the risk of contagious diseases. 5.
4 Future Scope: In our future work, we will collect more data and make a balance between different categories of the
data to improve the accuracy.
We will consider parameters and flops into consideration and deploy advanced level of YOLOv3 on lightweight devices,
which can further contribute to global health.
CHAPTER 6 CONCLUSION The proposed system to classify face mask detection using COVID-19 precaution in images
using yolo algorithm. The work opens interesting future directions for researchers.. (45)
The model can be trained and upgraded to mask datasets that include different images related to correctly/incorrectly
use mask and achieve the ultimate purpose of detecting facemask for cutting down the risk of contagious diseases. (45)

Match Urls:
0: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7983091/
1:
https://www.researchgate.net/profile/Fm-Shamrat/publication/350906163_Face_Mask_Detection_using_Convolutional_Ne
ural_Network_CNN_to_reduce_the_spread_of_Covid-19/links/60b2433592851cd0d98187b4/Face-Mask-Detection-using-
Convolutional-Neural-Network-CNN-to-reduce-the-spread-of-Covid-19.pdf
2: https://researchgate.net/figure/The-system-architecture_fig6_336161955
3: https://www.ijser.org/researchpaper/Face-Counting-and-Mask-Detection-using-Deep-Learning.pdf
4:
https://www.ijert.org/research/covid-19-facemask-detection-with-deep-learning-and-computer-vision-IJERTCONV9IS05017
.pdf
5: https://www.leewayhertz.com/face-mask-detection-system/
6: https://github.com/Kim-Hye-Jun/Face-Mask-Detection-1
7: https://ieeexplore.ieee.org/document/9452836
8: https://www.coursehero.com/file/114942411/Face-Mask-Detection-Systemdocx/
9: https://www.academia.edu/Documents/in/Convolutional_Neural_Network_CNN_
10: https://www.ionos.co.uk/
11: https://voxeu.org/article/unmasked-effect-face-masks-spread-covid-19
12: https://cse.msu.edu/~cherngcl/deliverable/PCAS3-SRS_V2.pdf
13: http://cs230.stanford.edu/projects_fall_2020/reports/55790723.pdf
14: https://www.target.com/c/face-masks/-/N-7tvo0
15: http://jdbv.sourceforge.net/InceptionDocs/Vision/Vision.htm
16: https://www.mdpi.com/2079-9292/10/7/837/htm
17:
https://www.researchgate.net/publication/276344756_Leveraging_VOIP_on_Local_Area_Network_using_Java_Media_Fram
ework
18: https://www.scribd.com/document/273350923/Photo-Morphing-Detection-REPORT-1
19: https://www.amazon.com/Leashboss-15-Foot-Dog-Leash/dp/B074DYH896
20:
https://www.coursehero.com/file/p6h2m55k/The-Gabor-function-represents-an-excellent-local-and-multi-scale-decomposi
tion/
21: https://www.ijcaonline.org/archives/volume159/number8/gurav-2017-ijca-913021.pdf
22: http://www.doc88.com/p-0002459168897.html
23: https://www.scribd.com/document/428542606/300-Core-Java-Interview-Questions-Javatpoint
24: https://www.ques10.com/p/21864/explain-the-following-1-java-compiler-environmen-1/
25: https://www.linguee.com/english-chinese/translation/can+be+licensed.html
26: https://hunterbusinessschool.edu/the-9-phases-of-the-systems-development-lifecycle-sdlc/
27: https://www.conceptdraw.com/examples/with-the-aid-of-diagram-describe-system-development-life-cycle
28: https://dictionary.cambridge.org/dictionary/english/estimate
29: https://www.tutorialspoint.com/sdlc/pdf/sdlc_waterfall_model.pdf
30: https://www.emmell.org/wp-content/uploads/2019/03/SDLC-Waterfall.pdf
31: https://www.google.com/docs/about/
32: https://www.raiseupwa.com/lifehacks/what-is-the-difference-between-fs-document-and-srs-document/
33: https://theintactone.com/2019/02/19/ism-u3-topic-6-waterfall-method/
34: https://www.scribd.com/document/474316572/SE-MONOGRAPH-CST-220-pdf
35:
https://www.researchgate.net/publication/351937605_The_Face_Mask_Detection_Technology_for_Image_Analysis_in_the_
Covid-19_Surveillance_System/fulltext/60b0e27d299bf1f6d57de351/The-Face-Mask-Detection-Technology-for-Image-
Analysis-in-the-Covid-19-Surveillance-System.pdf
36: https://online.visual-paradigm.com/knowledge/software-design/dfd-in-ssadm/
37: https://github.com/vra/face-mask-detection-website
38: http://www.google.pl/
39: https://www.freeprojectz.com/class-diagram
40: https://www.linkedin.com/pulse/face-detection-using-artificial-intelligence-kirti-swagat-mohanty
41: https://searchenterpriseai.techtarget.com/definition/face-detection
42: https://www.reuters.com/article/us-microsoft-privacy-idUSKCN1VH18T
43: https://www.hhs.gov/hipaa/for-professionals/privacy/index.html
44:
https://www.techscience.com/ueditor/files/cmes/TSP-CMES-127-2/TSP_CMES_14478/TSP_CMES_14478/TSP_CMES_14478.
xhtml
45: https://www.youtube.com/watch?v=cziJoGFTL_8
 Keywords Density

One Word 2 Words 3 Words

system 2.6% face mask 0.96% face mask detection 0.48%

face 2.2% covid 19 0.92% covid 19 face 0.4%

mask 2.12% machine learning 0.64% 19 face mask 0.4%

model 1.76% mask detection 0.64% machine learning 4 0.36%

data 1.68% learning 4 0.36% recoginition machine learning

0.24%

Plagiarism Report
By check-plagiarism.com