Download as pdf or txt
Download as pdf or txt
You are on page 1of 9

REAL TIME FACE MASK DETECTION SYSTEM

A PROJECT REPORT
Submitted
in partial fulfillment for the award of the degree of
Bachelor of Technology
IN
COMPUTER SCIENCE & ENGINEERING

Name of supervisor Name of student


Ruchi rai Harsh Namdev
Riya Tomar

DEPARTMENT OF COMPUTER SCIENCE ENGINEERING


SHRI RAM GROUP OF COLLEGES, MUZAFFARNAGAR, U.P.
AFFILIATED TO DR. A.P.J. ABDUL KALAM TECHNICAL UNIVERSITY, LUCKNOW, U.P.

2022

1
DECLARATION BY THE CANDIDATE

We hereby declare that the Project entitled “FACE MASK DETECTION SYSTEM”
submitted for the B.Tech. in Computer Science & Engineering degree is my original work and
the project has not formed the basis for the award of any other degree, diploma, fellowship or
any other similar titles.

We declare that we have not willfully lifted up some other’s work, para, text, data, results, etc.
reported in the journals, books, magazines, reports, dissertations, etc. or available at websites.

Date: Signature:

Place: Harsh Namdev, Riya Tomar

1869510021,1869510047

II
CERTIFICATE

This is to certify that the Project thesis, entitled FACE MASK DETECTION SYSTEM submitted by
Ms. Riya Tomar and Mr. Harsh Namdev embodies the findings of her original project/research work
carried out under my supervision and it fulfills all the conditions prescribed by Dr. A.P.J. Abdul Kalam
Technical University , Lucknow for the award of Bachelor of Technology Degree in Department of
Computer Science Engineering the best of my/our knowledge, the matter embodied in this Project/ thesis
has not been submitted elsewhere for the award of any other degree or diploma .

Signature and Name of Supervisor: RUCHI RAI

Designation: Asst. Professor

Department: Computer Science Engineering

Signature and Name of Head of Department: Mr. Pawan Kumar Goel

Designation: Associate Professor and Head of Department

Department: Computer Science Engineering

Signature of External Examiner:

Date:

III
ACKNOWLEDGEMENT

It gives us a great sense of pleasure to present the report of the B. Tech Project undertaken during B.
Tech. Final Year. We owe special debt of gratitude to our Supervisor Asst. Prof. Ruchi Rai,
Department of Computer Science & Engineering, Shri Ram Group of Colleges, Muzaffarnagar for
his constant support and guidance throughout the course of our work. His sincerity, thoroughness and
perseverance have been a constant source of inspiration for us. It is only his cognizant efforts that our
endeavors have seen light of the day.

We also take the opportunity to acknowledge the contribution of Prof. Pawan Kumar Goel, (Head
Department of Computer Science & Engineering) for his full support and assistance during the
development of the project.

We also do not like to miss the opportunity to acknowledge the contribution of all faculty members
of the department for their kind assistance and cooperation during for their contribution in the
completion of the project.

Name: Harsh Namdev

Roll No.: 1869510021

Date:

Signature:

Name: Riya Tomar

Roll No.: 1869510047

Date:

Signature:

IV
ABSTRACT

Gl obal pandemic COVID-1 9 ci rcumsta nces emerged in an epidemic of


dange rou s disease in all over t he world. Weari ng a face mask will hel p
prevent the spread of infection and pre vent the individual from
contracting any airborne infectious germs. Using Face Mask Detection
System, one can monitor if the peo ple are weari ng masks or not.

Here HAAR-CASACADE algorithm is used for image detection. Collating


with ot her exi sti ng a lgorithms, this classifie r produces a high rec ognition
rat e e ve n wit h v a ryi n g e xpres si o ns, effi ci ent feat ure s ele c ti o n a nd l ow
assortment of false positi ve features. HAAR feature-based cascade
classifier system utili zes o nly 200 features out of 6000 features to yield a
recogni tion rate of 85 -95%.

According to this motivation we demand mask detection as a unique and


public health se rvice system during the global pandemic COVID-19
e pidem ic . The m ode l i s t ra ine d by f ace m as k i ma ge a nd non-fa ce ma sk
i ma ge .

After the breakout of the worldwide pa nde mic COVID-19, the re arises a
se vere need of protection mechani sms, face mask being the primary one.
According to the World Health Organization, the corona virusCOVID-19
pande mic is causing a global health epidemic, and the most succe ssful
safet y measu re is wearing a face mas k i n p ublic p laces. Convolutio nal
Neural Networks (C NNs) have develope d themselves as a dominant class
of image recognition models. The aim of this re searc h i s to e xamine and
test machine learning capabilities for detecting and recognize face masks
worn by people in an y given video o r picture or in real t ime. Th is project
develops a real -time, GUI-based automat ic Face detection and recogn ition
system. It can be used as an entry management de vice by registe ring an
organization's employees or students with their faces, and then
reco gni zing i ndi vidual s whe n t he y approac h or l ea ve the pre m ises b y

V
recording their photographs with faces.The proposed methodology makes
uses of Principal Component Analysis (PCA) and HAAR Cascade
Al gorithm. Based on t he performa nce and accurac y of our model, the
result of the binary classifier will be indicated showing a gree n rectangle
superi mposed a round the section of the face indicating that the pe rson at
t he camera is wearing a mask, or a re d rectan gle i ndicat ing that the
person on camera is no t wearing a mask alo ng with face ident ification of
t he person.

Ke ywords: COVID-19 epidemic, HAAR-CASACADE a lgorithm, mask


detection, face mask image, non-face mask image

VI
LIST OF SYMBOLS

H - Height

W - Width

F - Filter

D - Dimension

X
LIST OF FIGURES
Fig.no. Description Page.no.

1. Layer in NN 28
2. Basic structure of CNN 30
3. Hierarchy of local filter 31
4. Convolution with a filter 32
5. Output of Convolution Layer 32
6. Max Pooling Layer 34
7. Overall structure of CNN 34
8. System Architecture 38
9. Building the Model 40
10. Use Case Diagram 44
11. Sequence Diagram 45
12. Activity Diagram 46
13. Block Diagram 47
14. Class Diagram 48
15. Data Flow Diagram 51
16. Flowchart Diagram 52
17. Dataset1 54
18. Dataset 2 55
19. Code implementation 56
20. Identifying ROI 57
21. Identifying many faces 58
22. Sample Output 62
23. Real time input 63
24. Real time output 64s

XI
LIST OF ABBREVATIONS

MTCNN - Multi-Task Cascaded Convolutions Neural


Networks

CNN - Convolutional Neural Network

CCTV - Closed-Circuit Television

MIT - Massachusetts Institute Technology

CNRI - Corporation for National Research Initiatives

LLNL - Lawrence Livermore National Laboratory

PyPI - Python Package Index

SIFT - Scale-Invariant Feature Transform

HOG - Histogram of Oriented Gradients

UML - Unified Modelling Language

XII

You might also like