You are on page 1of 18

Government College University Faisalabad Page 1

Government College University Faisalabad

Final Year Project Proposal


Face Mask Detection

By

ALI RAZA 2017-GCUF-071948


MUHAMMAD HAMZA 2017-GCUF-071938
IHTISHAM YOUNAS 2017-GCUF-071944

BACHELOR OF SCIENCE
IN
COMPUTER SCIENCE

DEPARTMENT OF COMPUTER SCIENCE

Government College University Faisalabad


2020
Government College University Faisalabad Page 2

Government College University Faisalabad Page ii

Table of Contents

Table of
Contents ...........................................................................................................................2
Revision History ........................................................................................................................... 3
1. Introduction .............................................................................................................................. 4
1.1 General Information.............................................................................................................. 4
1.2 Purpose................................................................................................................................ 5
1.3 Document Conventions ...................................................................................................... 5
1.4 Project Objective ................................................................................................................ 6
1.5 Intended Audience and Reading Suggestions.................................................................... 7
1.6 Project Scope ..................................................................................................................... 7
2. Overall Description ................................................................................................................ 8
2.1 Product Perspective........................................................................................................... 8
2.2 Product Features................................................................................................................ 8
2.3 User Classes and Characteristics...................................................................................... 8
2.4 Operating Environment..................................................................................................... 8
2.5 Design and Implementation Constraints ......................................................................... 9
2.6 User Documentation......................................................................................................... 9
2.7 Assumptions and Dependencies........................................................................................ 9
3. System Features ...................................................................................................................... 10
3.1 System Feature 1............................................................................................................... 10
4. External Interface Requirements......................................................................................... 10
4.1 User Interfaces................................................................................................................... 11
4.2 Hardware Interfaces ......................................................................................................... 11
4.3 Software Interfaces .......................................................................................................... 11
4.4 Communications Interfaces .............................................................................................. 12
Government College University Faisalabad Page 3

5. Other Nonfunctional Requirements ..................................................................................... 12


5.1 Performance Requirements............................................................................................... 12
5.2 Safety Requirements....................................................................................................... 12
5.3 Security Requirements..................................................................................................... 12
5.4 Software Quality Attributes ............................................................................................. 13

6. Face mask detection Project Management...........................................................................13


7. Tools & Technologies..............................................................................................................14
7.1 Programming Languages.................................................................................................. 14
7.2 Databases/Data storages..................................................................................................... 14
7.3 Operating System................................................................................................................ 14
Appendix A: Glossary ................................................................................................................15
Appendix B: Check
List ..............................................................................................................16 Appendix C:
Supervisory Committee ........................................................................................17

Revision History

Name Date Reason For Changes Version


Government College University Faisalabad Page 4

1. Introduction

The year 2020 has shown mankind some mind-boggling series of events amongst which the
COVID- 19 pandemic is the most life-changing event which has startled the world since the year
began. Affecting the health and lives of masses, COVID-19 has called for strict measures to be
followed in order to prevent the spread of disease. From the very basic hygiene standards to the
treatments in the hospitals, people are doing all they can for their own and the society’s safety; face
masks are one of the personal protective equipment. People wear face masks once they step out of
their homes and authorities strictly ensure that people are wearing face masks while they are in
groups and public places. To monitor that people are following this basic safety principle, a strategy
should be developed. A face mask detector system can be implemented to check this. Face mask
detection means to identify whether a person is wearing a mask or not. The first step to recognize
the presence of a mask on the face is to detect the face, which makes the strategy divided into two
parts: to detect faces and to detect masks on those faces.

Face detection is one of the applications of object detection and can be used in many areas like
security, biometrics, law enforcement and more. There are many detect- tor systems developed
around the world and being implemented. However, all this science needs optimization; a better,
more precise detector, because the world cannot afford any more increase in corona cases. In this
project, we will be developing a face mask detector that is able to distinguish between faces with
masks and faces with no masks. In this report, we have proposed a detector which employs SSD for
face detection and a neural network to detect presence of a face mask. The implementation of the
algorithm is on images, videos and live video streams. The rest of the report is organized as follows.

1.1 General Information


Below down the full information about the project name and the team who develop this and also
date on which we start working on project and the finalized date and the also give idea about the
authorized team name.
Government College University Faisalabad Page 5

Project Name: Face Mask Detection Starting Date:


______________________________ _______________

Controlling Agency: Final Date:


______________________________ _______________
_
Prepared By: Authorized by:
______________________________ ________________

1.2 Purpose
The Face Mask Detection System can be used at offices, institutes and other public places
to detect if employees are maintaining safety standards at work. After the breakout of the
worldwide pandemic COVID-19, there arises a severe need of protection mechanisms, face mask
being the primary one. The basic aim of the project is to detect the presence of a face mask on
human faces on live streaming video as well as on images. We have used deep learning to
develop our face detector model. Alongside this, we have used basic concepts of transfer learning
in neural networks to finally output presence or absence of a face mask in an image.

1.3 Document Conventions


The document is written in Times new Roman, The size of the font is 12 for normal text. The size
of topic name is in 16 and the sub-heading is of size 14 with bold specification. If the sub-
heading contains more headings, then such heading are in size 12. The line spacing is 1.5 cm.
Government College University Faisalabad Page 6

1.4 Project Objective


To identify the person on image/video stream wearing face mask with the help of computer vision
and deep learning algorithm by using the python, Opencv, Tenserflow, Keras library.The goal of
face mask detection is to determine if there are any faces in the live streaming video. If multiple
faces are present, each face is enclosed by a bounding box and thus we know the location of the
faces. Human faces are difficult to model as there are many variables that can change for example
facial expression, orientation, lighting conditions and partial occlusions such as sunglasses, scarf,
mask etc. The result of the detection gives the face location parameters and it could be required in
various forms, for instance, a rectangle covering the central part of the face, eye centers or
landmarks including eyes, nose and mouth corners, eyebrows, nostrils, etc.

The external oversight committee must approve the project performance measurement plan.

Agency Goals Project Objectives

 To collect the dataset from Kaggle  The objective is to train the model to
 Distributing the dataset for Testing detect the face mask from the person’s
and Training face
 Filtering dataset in order to change its  Detection of facemask from both
size and resolution in order to equally genders.
treat every image of dataset.  Giving the percentage of mask position,
 Training the dataset using Deep i.e. giving 100% if mask is properly on
learning the face.
 Testing the accuracy of the model  Providing output in form rectangle about
 Validating model by giving random status of facemask(i.e. Green rectangle if
picture as an Input mask is properly on the face and red
otherwise)
Government College University Faisalabad Page 7

1.5 Intended Audience and Reading Suggestions


The document is intended for software requirements engineer, domain expert, developer and
project manager. This project is a prototype for the face mask detection and it is restricted within
the college premises. This has been implemented under the guidance of college professors. This
project is useful for the protection from viruses and as well as the Health issues from smoke and
dust. Before reading this document it is highly recommended to read the introduction in
Document to get an overview of the product.

1.6 Project Scope


Face detection is one of the applications of object detection and can be used in many areas like
security, biometrics, law enforcement and more. There are many detect- tor systems developed
around the world and being implemented. However, all this science needs optimization; a better,
more precise detector, because the world cannot afford any more increase in corona cases. In this
project, we will be developing a face mask detector that is able to distinguish between faces with
masks and faces with no masks. In this report, we have proposed a detector which employs SSD for
face detection and a neural network to detect presence of a face mask.

 Detecting facemask from both genders


 Detecting the position of facemask
 Giving output in the form of rectangle around the mask. Red for not properly on the face and
green in case not properly on the face.

2. Overall Description

The External Interface Requirements can be described as follow:


Government College University Faisalabad Page 8

2.1 Product Perspective

We introduce a mask face detection model that is based on computer vision and deep learning.
The proposed model can be integrated with surveillance cameras to impede the COVID-19
transmission by allowing the detection of people who are wearing masks and not wearing face
masks. The model is integration between deep learning and classical machine learning
techniques with Opencv, tensor flow, mobilenetv2 and keras. We have used deep transfer
leering for feature extractions and combined it with three classical machine learning algorithms.
We introduced a comparison between them to find the most suitable algorithm that achieved the
highest accuracy and consumed the least time in the process of training and detection. 

2.2 Product Features

 Real Time Face Mask Detection


 Detect Many Faces At the Same time
 Cover Distance up to 3 meters mainly depends on camera quality

2.3 User Classes and Characteristics


The machine learning applications are normally embedded in any real life application and work on
automatic manner. By focusing this phenomena the project will be developed with less or no human
interaction.

2.4 Operating Environment


We used this model in windows 7 or latest version of windows. There is no server required for
this software it can freely run on windows system.

2.5 Design and Implementation Constraints


A multiplayer neural network (MLP) is used for the algorithm and a hidden layer containing
neurons. And information flow in the system and the way the becoming indistinct, and finally put
Government College University Faisalabad Page 9

the corner where device, a process or a system in sufficient detail to a human operator has to find
the comers, his geometric height and width lip envelope description. Implicitly uses the global
shape of mouth. He follows only work with the area around the lips. Because of all Outputs are
independently normalized in the range parameterization for later identification. [5, 6]. We have
pictures were taken with the seated people and at the predefined block of 245 by 245 pixels. Same
distance, this area is selected in all picture in the same position, i.e., we suppose that the lips area
inside a system works. Design is process of applying the various techniques and principles for the
purpose of defining a The MLP used was trained with back propagation the detailed design of the
system describes the data the upper and lower edges extend them when they are, they intersect. We
propose an adjustment process that works the same way. Detection is the first step in LISP..

The implementation methodology outlines key activities that should be considered and planned for
when developing or implementing an underwriting system. It begins with the design and
development activities involved in obtaining policy details, as a specification, provides a guideline
to develop and implement underwriting system.

2.6 User Documentation


This model will be trained and tested after using the required tools. The trained model will be
helpful to the developer to implement in any application or cameras. The manual for developer
will be in the form of documentation in which the guidelines will be given in step by step
manner.

2.7 Assumptions and Dependencies


The model is assumed to work in real-time environment and will be able to detect the face mask
even at the night mode of the camera. As the model is used with less human interaction that is
why the dependencies for this model are CCTV camera, Open CV, Keras, Jupyter Noteebok for
Python and Tensorflow
Government College University Faisalabad Page 10

3. System Features
The External Interface Requirements can be described as follow:

3.1 System Feature 1

Our system is real time face detection model, also scan more than one faces at the same time and
alert the on duty man, we don’t need any extra hardware to install.

3.1.1 Description and Priority

 It allows us to detect the person who is not wearing mask with


live video streaming.
 Stimulus/Response Sequences. It works like a real time
system and alert with red sign weather a person not wearing a
mask and it shows green signal when person wear mask.
3.1.2 Functional Requirements

Functional requirements reflect the core functionality of the model. The functional
requirements are detecting the face mask from person face. Identifying the position
of the face mask. Finally notifying about that either the mask is on the face or not.

4. External Interface Requirements

The External Interface Requirements can be described as follow:

4.1 User Interfaces


The user of this system can see the live camera streaming video and it can invisible keep an eye
on people. Its interface is very easy user friendly because most of the camera monitoring staff
Government College University Faisalabad Page 11

have very basic knowledge and also other people who are not much aware of this types of system
can easily handle. We include sample screen images.

Figure 1: Example interface of face mask detection model

4.2 Hardware Interfaces

 Operating System : Windows 8.1


 Hard Disk : 128 GB
 Ram : 4 GB
 Processer : Intel core i5

4.3 Software Interfaces

 Python language
 Visual Studio Code IDE

4.4 Communications Interfaces

 Windows Operating System


Government College University Faisalabad Page 12

5. Other Nonfunctional Requirements

The non-functional requirements can be detection of face mask at night. Designing the interface to
operate this model in easy sense. That is why bright color schemes and attractive graphics are the
part of non-functional requirements.

5.1 Performance Requirements


The face mask detection system uses AI technology to detect the person with or without a mask.
It can be connected with any surveillance system installed at your premise. The authorities or
admin can check the person through the system to confirm their identity. The system sends an
alert message to the authorized person if someone has entered the premise without a face mask.
The accuracy rate of detecting a person with a face mask is 95-97% depending on the digital
capabilities. The data has been transferred and stored automatically in the system to enable
reports whenever you want.

5.2 Safety Requirements


Humans are error-prone, we will check our training model by getting a plot graph and after that
we can say that this software is error free.

5.3 Security Requirements


The model will be embedded in any secure application so that any intruder or hacker may not
hack the system to change its work. But in this type of model security is not concerned.
Government College University Faisalabad Page 13

5.4 Software Quality Attributes


One time false detection or wrong detection may lead to great health issues. That is why the
quality of this model will be high enough to be accepted. For achieving the high quality the
model will be tested on the large dataset.

6. Face mask detection Project Management

Face Mask detection using the deep learning is a real-time project to detect the face masks. The
mask will be detected from the faces of both genders. The work flow of this model is given in
figure
Government College University Faisalabad Page 14

7. Tools & Technologies

 Opencv
 Tenserflow
 Keras
 MobileNet2

7.1Programming Language
 Python

7.2Dataset
For this model dataset is taken from Keras an online free data source for machine learning
purpose.

7.3 Operating System

 Windows Operating System (7 or Higher version)


Government College University Faisalabad Page 15

Appendix A: Glossary
Keras: Online datasource

ML: Machine Learning

DL: Deep Learning

Open CV: Open Computer Vision Library


Government College University Faisalabad Page 16

Appendix B: Check List

Check List Yes No


I. Starting/Ending Dates

II. Project Scope

III. Product modules (covering all aspects of scope)

IV. System Features (covering scope)

V. Interface Requirements

VI. Non-Functional Requirements

VII. WBS

VIII. Tools and Technologies Detail (for implementation)

IX. Plagiarism Report


Government College University Faisalabad Page 17

Appendix C: Supervisory Committee

For Approval of any two Consultant Teachers

Teacher Consulted Teacher Consulted

Name: ______________________________. Name: ______________________________.

Designation: _________________________ . Designation: _________________________ .

Comments:__________________________ Comments:__________________________

___________________________________ ___________________________________

___________________________________ ___________________________________

___________________________________ ___________________________________

___________________________________ ___________________________________

Signature: __________________________ Signature: __________________________

---------------------------------------------------------------------

(For office use only)

Date:_____________

➢ Approved Group ID:


____________
Government College University Faisalabad Page 18

➢ Meeting Required: Date:___________ Time: ___________ Place:


___________________

➢ Rejected

Remarks:

_____________________________________________________________________________
______
_____________________________________________________________________________
______
_____________________________________________________________________________
______

_____________________________________________________________________________
______

Project Title (if Revised):

________________________________________________________________________________
____

__________________________
__
Project Coordinator

You might also like