AUTOMATIC FACEMASK DETECTION 2020-2021

Topic: AUTOMATIC FACE MASK DETECTION

Submitted by
RANDHIR KUMAR YADAV 1NH17EE741

ROHAN ASHISH 1NH17EE743

MOHAMMED ARBAS 1NH17EE066

B.E (EEE) Project Phase I Page 1

 AUTOMATIC FACEMASK DETECTION 2020-2021

CHAPTER 1
INTRODUCTION

The nation-wide lockdown to contain the novel coronavirus pictures the Havoc and
catastrophic on the whole world claiming 1 crore lies and still lives of people affected
and in spite on our and then the news of new strain of coming and students appeared in
the common citizens but people have adapted to the new normal and have begun to
Resume the life with the daily activities such as travelling to places carrying out their
work study travelling with family spending time.

 To provide a proper safety and every SOP is followed for the safety
of students we have come off the idea of project which contains a
free fire and safety course of the functional module with the
machine learning code by python libraries

 Powering focus is to provide an intelligent and data driven system

which would only open the gate or if the face is on the contour of
the person's face by analyzing thousands of data sets of people
wearing Face masks

Problem Statements
The Public places & crowded area requires people to wear face masks, some people often
forget to put their masks on —

1. Increased Risk of Covid Transmission.

2. Challenge of Authorities to manually instruct thousands of people at a time to
wear masks.

B.E (EEE) Project Phase I Page 2

 AUTOMATIC FACEMASK DETECTION 2020-2021

Implementation

[1]

[2]

Our working methodology is a data science approach in which we are utilizing the
Google colab resource which is an online platform to execute machine learning quotes
with a very highest speed of operation then we download it
B.E (EEE) Project Phase I Page 3
 AUTOMATIC FACEMASK DETECTION 2020-2021

1. 0pened a new terminal on Pi by pressing Ctrl-T.

2.Cloning from GitHub.

git clone https://github.com/carolinedunn/face_mask_detection

3. Running the pre-made model trained with over 1,000 images. In terminal
changing directory (cd) into the directory you just cloned from GitHub.
cd face_mask_detection

4. Running the Python 3 code to open up your webcam and start the mask
detection algorithm.
python3 detect_mask_webcam.py

entering python3 detect_mask_picam.py

After a few seconds, we should see camera view pop-up window and see a green
box indicating face mask presence. Or a red box indicating lack of face mask.

Face Mask Model Training

Over one thousand photos were used to train the model

that detect_mask_webcam.py uses to make the mask or no mask determination.
The more examples provided, the better the machine learning because fewer photos
= less accuracy.

Photos divided into 2 folders in our dataset, with_mask and without_mask and
the training algorithm created a model of mask vs. no mask based on the dataset.
The sample photos provided in the dataset folder downloaded from GitHub
.
we trained our Raspberry Pi Mask Detection system on 20 photos. Fortunately, we
B.E (EEE) Project Phase I Page 4
 AUTOMATIC FACEMASK DETECTION 2020-2021

have a pre-trained model to test out.

From face_mask_detection folder in terminal, running the Python 3 code to open
webcam with the 20 photo model.

python3 detect_mask_webcam.py --model mask_detector-20. model

If you are using a Pi Camera, enter python3 detect_mask_picam

Training the Raspberry Pi face mask model

To train the Pi with photos, we simply saved your photos (headshots of people
wearing or not wearing face masks) to the appropriate folder. Have fun with this
and take photos of yourself and your family.

Take train photos with Raspberry Pi

1.Open a Terminal, press Ctrl-T.

2. Change directories into the face_mask_detection folder.

cd face_mask_detection

3.Run Python code to take photos of yourself wearing a mask, the same for no
mask photos.

If using a webcam run:

python withMaskDataset.py
or
python withoutMaskDataset.py
If using a pi camera run:
python withMaskDataset-picam.py
or
python withoutMaskDataset-picam.py

4.Press your spacebar to take a photo.

5 Press q to quit when you are done taking photos.

2. Installed sklearn and matplotlib packages to your Pi.

sudo pip3 install sklearn

B.E (EEE) Project Phase I Page 5
 AUTOMATIC FACEMASK DETECTION 2020-2021

sudo pip3 install matplotlib

3. Train the model. Keep in mind that, the more photos you have in the dataset
folder, the longer it will take to create the model. If you get an “out of memory”
error, reduce the number of photos in your dataset until you can successfully run
the Python code.
cd face_mask_detection

python3 train_mask_detector.py --dataset dataset --plot mymode

Testing Your Raspberry Pi face mask model

let’s put it to the test!

Running the same detection script, but specify your model instead of the default
model.
From the same Terminal window:

python3 detect_mask_webcam.py --model my_mask_detector.model

If you are using a Pi Camera, enter python3 detect_mask_picam.py

--model my_mask_detector.model

B.E (EEE) Project Phase I Page 6

AUTOMATIC FACEMASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 7

 AUTOMATIC FACEMASK DETECTION 2020-2021

Adding a Buzzer and LEDs

Now that we’ve trained our model for Raspberry Pi face mask detection, we can
have some fun with the results.
we add a buzzer and 2 LEDs to quickly identify if someone is wearing their face
mask or not.

For this step, we add-on:

 Small Breadboard
 Two 330 Ohm resistors
 1 Red LED
 2 Green LED
 1 Buzzer

B.E (EEE) Project Phase I Page 8

AUTOMATIC FACEMASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 9

 AUTOMATIC FACEMASK DETECTION 2020-2021

CHAPTER 2
Components required

1. Raspberry pi [3]

3. Pc- based webcam [4]

3.Servo Motor [5]

B.E (EEE) Project Phase I Page 10

 AUTOMATIC FACEMASK DETECTION 2020-2021

4.Jumper Cables [6]

5.Green and Red LED lights [7]

6.Ethernet cable [8]

B.E (EEE) Project Phase I Page 11

AUTOMATIC FACEMASK DETECTION 2020-2021

Components Description

1. Raspberry pi
It is a microcontroller board having a 2.6 Ghz of processor and 2GB of RAM, its used
to function as a standalone computer or as a embedded processor board.
Raspberry Pi is a progression of little single-board PCs created in the Assembled
Realm by the Raspberry Pi Establishment in relationship with Broadcom. From the
get-go, the Raspberry Pi project inclined towards the advancement of showing
fundamental software engineering in schools and in creating countries. Later, the first
model got definitely more famous than anticipated, selling outside its objective
market for utilizations, for example, mechanical technology. It is currently generally
utilized in numerous regions, for example, for climate monitoring, on account of its
ease, seclusion, and open plan.
After the arrival of the subsequent board type, the Raspberry Pi Establishment set up
another element, named Raspberry Pi Exchanging, and introduced Eben Upton as
President, with the obligation of creating technology. The Establishment was
rededicated as an instructive foundation for advancing the educating of fundamental
software engineering in schools and agricultural nations.

2.Servo Motor
A servomotor is a rotational actuator or direct actuator that takes into consideration
exact control of precise or straight position, speed and acceleration. It comprises of
an appropriate engine coupled to a sensor for position criticism. It additionally
requires a moderately refined regulator, regularly a committed module planned
explicitly for use with servomotors.
Servomotors are not a particular class of engine, despite the fact that the term
servomotor is frequently used to allude to an engine reasonable for use in a shut circle
control framework.

B.E (EEE) Project Phase I Page 12

 AUTOMATIC FACEMASK DETECTION 2020-2021

3.pi- camera module [9]

The Raspberry Pi Camera Module is a 5MP CMOS camera with a fixed center focal point
that is equipped for catching actually pictures just as superior quality video. Stills are
caught at a goal of 2592 x 1944, while video is upheld at 1080p at 30 FPS, 720p at 60
FPS and 640x480 at 60 or 90 FPS.The camera is upheld in the most recent rendition of
Raspbian, Raspberry Pi's favored working framework.

4.Ethernet cable

It is a group of wired PC organizing innovations ordinarily utilized in neighborhood

(LAN), metropolitan territory organizations (MAN) and wide zone organizations
(WAN). It was industrially presented in 1980 and first normalized in 1983 as IEEE
802.3. Ethernet has since been refined to help higher piece rates, a more noteworthy
number of hubs, and longer connection distances, yet holds a lot of in reverse
similarity. Over the long run, Ethernet has generally supplanted contending wired
LAN advances, for example, Token Ring, FDDI and ARCNET.

The first 10BASE5 Ethernet utilizes coaxial link as a shared medium, while the more
current Ethernet variations utilize curved pair and fiber optic connections related to
switches. Throughout the span of its set of experiences, Ethernet information move
B.E (EEE) Project Phase I Page 13
AUTOMATIC FACEMASK DETECTION 2020-2021

rates have been expanded from the first 2.94 megabits every second (Mbit/s) to the
most recent 400 gigabits for each second (Gbit/s). The Ethernet norms include a
few wiring and flagging variations of the OSI actual layer being used with Ethernet.

Frameworks imparting over Ethernet partition a surge of information into more limited
pieces called outlines. Each casing contains source and objective locations, and
blunder checking information so that harmed edges can be recognized and disposed
of; regularly, higher-layer conventions trigger retransmission of lost edges. Per the
OSI model, Ethernet offers types of assistance up to and including the information
interface layer. The 48-piece Macintosh address was embraced by other IE802
systems administration principles, including IEEE 802.11 (Wi-Fi), just as by FDDI.
EtherType esteems are likewise utilized in Subnetwork Access Convention
(SNAP) headers.

Ethernet is generally utilized in homes and industry, and interworks well with remote
Wi-Fi innovations. The Web Convention is regularly continued Ethernet thus it is
viewed as one of the key advances that make up the Web.

Ethernet has developed to incorporate higher data transmission, improved medium

access control strategies, and diverse physical media. The coaxial link was
supplanted with highlight point joins associated by Ethernet repeaters or switches.

Ethernet stations convey by sending each other information parcels: squares of

information exclusively sent and conveyed. Similarly as with other IEEE 802
LANs, connectors come modified with universally novel 48-piece Macintosh
address so every Ethernet station has an interesting address.The Macintosh delivers
are utilized to determine both the objective and the wellspring of every information
parcel. Ethernet builds up connection level associations, which can be characterized
utilizing both the objective and source addresses. On gathering of a transmission,
the collector utilizes the objective location to decide if the transmission is pertinent
B.E (EEE) Project Phase I Page 14
AUTOMATIC FACEMASK DETECTION 2020-2021

to the station or ought to be disregarded. An organization interface regularly doesn't

acknowledge bundles routed to other Ethernet stations
EtherType field in each casing is utilized by the working framework on the getting
station to choose the proper convention module (e.g., a Web Convention form, for
example, IPv4). Ethernet outlines are supposed to act naturally recognizing, in view
of the EtherType field. Self-recognizing outlines make it conceivable to intermix
various conventions on a similar actual organize and permit a solitary PC to utilize
different conventions together. Regardless of the advancement of Ethernet
innovation, all ages of Ethernet (barring early exploratory renditions) utilize a
similar edge formats. Blended speed organizations can be assembled utilizing
Ethernet switches and repeaters supporting the ideal Ethernet variants.

Because of the universality of Ethernet, and the consistently diminishing expense of

the equipment expected to help it, most makers presently fabricate Ethernet
interfaces straightforwardly into PC motherboards, wiping out the requirement for
a different organization card.

B.E (EEE) Project Phase I Page 15

 AUTOMATIC FACEMASK DETECTION 2020-2021

2.2Software Packages & Libraries used

1. Anaconda Editor [10]

Anaconda constrictor Guide is a work area graphical UI (GUI) remembered for Boa
constrictor circulation that permits clients to dispatch applications and oversee conda
bundles, conditions and channels without utilizing order line orders. Pilot can look for
bundles on Boa Constrictor Cloud or in a neighborhood Boa Constrictor Storehouse,

introduce them in a climate, run the bundles and update them. It is accessible for
Windows, macOS and Linux.
Conda is an open source, cross-platform, language-agnostic bundle administrator] that
introduces, runs, and updates bundles and their dependencies. made for Python
programs, however it can bundle and circulate programming for any language (e.g., R),
including multi-language projects. The conda bundle and climate supervisor is
remembered for all renditions of Boa constrictor, Mini conda, and Boa Constrictor
Repository.

2.Pycharm Editor [11]

B.E (EEE) Project Phase I Page 16

 AUTOMATIC FACEMASK DETECTION 2020-2021

PyCharm is a coordinated improvement climate (IDE) utilized in PC programming,

explicitly for the Python language. It is created by the Czech organization JetBrains. It
gives code investigation, a graphical debugger, a coordinated unit analyzer, combination
with form control frameworks (VCSes), and supports web improvement with Django just
as information science with Anaconda. PyCharm is cross-stage, with Windows, macOS
and Linux renditions
3.Python 3.9.1 compiler
Python is a deciphered, elevated level and universally useful programming language.
Python's plan theory stresses code intelligibility with its striking utilization of huge
whitespace. Its language develops and object-arranged methodology expect to assist
software engineers with composing, coherent code for little and huge scope projects.
Python is powerfully composed and trash gathered. It underpins different programming
ideal models, including organized (especially, procedural), object-situated and utilitarian
programming.

4.tensorflow>=1.15.2 [12]

Tensor Flow is a free and open-source programming library for AI. It tends to be utilized
across a scope of errands yet has a specific spotlight on preparing and surmising of
profound neural networks.
Tensor flow is an emblematic numerical library dependent on dataflow and differentiable
B.E (EEE) Project Phase I Page 17
 AUTOMATIC FACEMASK DETECTION 2020-2021

programming. It is utilized for both examination and creation at Google.

Tensor Flow was created by the Google Mind group for inside Google use.

5.keras==2.3.1 [13]

Keras is an open-source programming library that gives a Python interface to fake neural
organizations. Keras goes about as an interface for the Tensor Flow library.

6.imutils==0.5.3 [14]

A progression of comfort capacities to make essential picture handling capacities, for

example, interpretation, pivot, resizing, skeletonization, showing Matplotlib pictures,
arranging shapes, distinguishing edges, and considerably simpler with OpenCV and both
Python 2.7 and Python 3.

7.numpy==1.18.2 [15]

is a library for the Python programming language, adding support for huge, multi-
dimensional clusters and grids, alongside an enormous assortment of elevated level

B.E (EEE) Project Phase I Page 18

 AUTOMATIC FACEMASK DETECTION 2020-2021

numerical capacities to work on these exhibit?

8.opencv-python==4.2.0. [15]

OpenCV (Open Source PC Vision Library) is a library of programming capacities

principally focused on continuous PC vision. Initially created by Intel, it was later upheld
by Willow Carport then Itseez (which was later procured by Intel. The library is cross-
stage and free for use under the open-source Apache Permit. Beginning with 2011,
OpenCV highlights GPU increasing speed for ongoing operations.

9.matplotlib==3.2.1 [16]

Matplotlib is a plotting library for the Python programming language and its
mathematical science augmentation NumPy. It gives an article arranged Programming
interface to installing plots into applications utilizing universally useful GUI tool stash
like Tkinter

B.E (EEE) Project Phase I Page 19

 AUTOMATIC FACEMASK DETECTION 2020-2021

10.scipy==1.4.1 [17]

is a free and open-source Python library utilized for logical processing and specialized
computing. SciPy contains modules for streamlining, straight variable based math, mix,
addition, uncommon capacities, FFT, sign and picture preparing, Tribute solvers and
different undertakings regular in science and designing.

B.E (EEE) Project Phase I Page 20

 AUTOMATIC FACEMASK DETECTION 2020-2021

CHAPTER 3
Block Diagram

[17]

Description of Block Diagram

Block diagram we have shown that-

 there is a Raspberry Pi board containing 40 g p i o pin and on board
Ethernet and consisting display and processing boards is fed with the
camera web camera input
 as soon as the user approaches camera he is evaluated by open CV
library for the face recognition then
 its face recognition data is sent to the deep learning model using
tensorflow and keras wherein it is evaluated by the existing thousand faces
of data sets and

B.E (EEE) Project Phase I Page 21

AUTOMATIC FACEMASK DETECTION 2020-2021

 the signal is sent to Raspberry Pi board if the person is wearing the face
mask on screen terminal shows face mask is on or else it shows based
fast is not on if there is a face mask detected the Servo Motor by action
and control of Raspberry Pi board opens up door

B.E (EEE) Project Phase I Page 22

AUTOMATIC FACEMASK DETECTION 2020-2021

CHAPTER 4
Circuit Diagram

4.1 Raspberry pi interfacing with servo motor. [18]

T1.

B.E (EEE) Project Phase I Page 23

AUTOMATIC FACEMASK DETECTION 2020-2021

2.Raspberry pi interface with HDMI cable and webcam [19]

B.E (EEE) Project Phase I Page 24

AUTOMATIC FACE MASK DETECTION 2020-2021

4.2 Program for working

B.E (EEE) Project Phase I Page 25

AUTOMATIC FACE MASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 26

AUTOMATIC FACE MASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 27

AUTOMATIC FACE MASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 28

AUTOMATIC FACE MASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 29

AUTOMATIC FACE MASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 30

AUTOMATIC FACE MASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 31

AUTOMATIC FACE MASK DETECTION 2020-2021

B.E (EEE) Project Phase I Page 32

 AUTOMATIC FACE MASK DETECTION 2020-2021

4.3Working of the Program: -

The working of the model is as follows: -

Raspberry Pi face mask works as –

At the point when a client approaches our webcam, the python code using Tensorflow,
OpenCV, Also, imutils bundles will recognize if a client is wearing a face cover will be
assigned with a red box around their face cover will see a green box around their face
veil with the content.

"Much obliged to you Veil On”. The clients who are not wearing the cover will see the
red box around Their face with, “no face veil identified." Term the Raspberry Pi veil
identifier takes. Beginning with a new introduce of the Raspberry Pi So to complete all
components of this venture.

Will take in any event 5 hours. We can subtract 1.5 hours for the introduce of OpenCV.
Even better, we have incorporated a pre - prepared model for the task to bounce
straightforwardly to a working Pi cover discovery framework. Numerous clients are as
yet utilizing a similar rule of AI and fake intelligence, but we are adding Tensorflow
venture that decided whether a feline was conveying prey to its proprietor entryway.

Part 1:installing conditions for Raspberry Pi face cover discovery

In this step, we will introduce OpenCV ,imutils, and Tensorflow.

OpenCV is an open source programming library for preparing continuous picture and
video with AI abilities.

Imutils is a progression of comfort capacities to facilitate OpenCV registering on the

Raspberry Pi Tensorflow is an open source AI stage.

1.Installed new duplicate of the Raspberry Pi working framework on your 16GB or

bigger micro SD card.

2.Plugged in webcam into one of the USB ports of your Raspberry Pi. If you are utilizing
a Raspberry Pi camera rather than a webcam, use your lace link to interface it to your Pi.
Booting our Raspberry Pi.

B.E (EEE) Project Phase I Page 33

 AUTOMATIC FACE MASK DETECTION 2020-2021

Face detection by
OpenCv and
tensorflow via
webcam

Servo Motor
action and door Deep learning
opening if only Model Pre
the person created by keras
detected with & scipy
face mask On

On screen alert
on terminal Classification of
window wish 1. Person wearing
Mask is on or Face mask or not
2. mask is not on

Further Innovation & Improvements done by us are –

Further improvements and innovations done by us are

 The dynamic creation of face mask library that is the function and
the data set of over 2,000 people who are wearing mask
 And 2008 asset of people not wearing a face mask
 then we have implemented and we are trying to implement the
hardware by placing a Raspberry Pi as sole microcontroller.
 and the interface of a Servo Motor to act as the river of the door to
open the gates
 when a person's face mask is on and a buzzer and a green and red
LED light to indicate whether t
B.E (EEE) Project Phase I Page 34
AUTOMATIC FACE MASK DETECTION 2020-2021

 The mask is on or not in green LED blinks when the mask is on and the
screen is founded by the contribution and when the face mask is not
on the red LED closed and the burner alerts the user to put the mask on

B.E (EEE) Project Phase I Page 35

 AUTOMATIC FACE MASK DETECTION 2020-2021

CHAPTER 5
5.1 Advantages: -

• It is very portable.

• Smart & IoT enabled.

• Use of AI & Deep learning aids no human presence.

• Prevents much manual labor & supervision.

• Data Analytics to gather data for prediction statistics.

5.2 Disadvantages: -

• Power limitation
• Accuracy of detection.
• Requires continuous Internet link to scan the data sets.

5.3 Applications: -

The following are the applications of our developed project & its technology in real world
–
 The applications of our project in very fast and it can be used in surveillance and
detection systems of whether the face mask is on or not
 It can be used at big and bigger public gathering such as airport bus stations railway
stations sports events public events marriage concerts music concerts where the
manual instructions of putting the face mask on is not possible
 To leverage the power of Artificial Intelligence and deep learning to put into
Practical uses
B.E (EEE) Project Phase I Page 36
AUTOMATIC FACE MASK DETECTION 2020-2021

 It can be used for educational purposes training the Computer Science Students as
well as
 The making the deep learning library and models
 It can be also integrated with microcontroller and processes to for a iot controlled
environment

B.E (EEE) Project Phase I Page 37

 AUTOMATIC FACE MASK DETECTION 2020-2021

CHAPTER 6
CONCLUSION

We conclude that any complex problem can also be solved by breaking it into individual
much smaller units and by focusing solution to each of these small solutions. And when
these small solutions are integrated we arrive at a solution to a much bigger problem.
In this project we leverage the power of AI particularly in Face detection System to make
An efficient and accurate system to detect the presence of face masks in order to curb the
spread of coronavirus disease in times of heavy of flow of public as everything has been
unlocked to return back to normal state it causes the great risk of Transmission as large
public bodies are difficult to address be manual instruction to wear the face mask.
We have used the concept of face detection along with deep learning models and utilize
Library such as tensorflow now by and keras to predict the contour region of a person
space dynamically and determine whether he or she is wearing the face mask or not.
Upon detecting the face mask on the person space the prompt is given as thank you your
mask is on and for the hardware implementation we have utilized the action of Servo
Motors controlled by GP IO pins of Raspberry pi to operate a motor which acts as a Lever
of a door to grant access to people wearing mask and for those who are not wearing the
mask are prompted by these wear the mask is not on and the green and red LED light
blinks up and the motor does not open the doors
It Can also be used in various inter-disciplinary fields such as defense & security,
education & Training of students in Practical IOT based operations.

B.E (EEE) Project Phase I Page 38

 AUTOMATIC FACE MASK DETECTION 2020-2021

CHAPTER 7
Bibliography

[1]. https://www.kaggle.com/
[2]. https://www.udemy.com/
[3]. https://www.allaboutcircuits.com/projects/building-raspberry-pi-controllers-
part-3-object-detection-dc-motor-controll/
[4]. Google.com, image search service.

[5]. An Application of a Deep Learning Algorithm for Automatic

Detection of Unexpected Accidents
Date of Conference: 26-28 Aug. 2019
DOI: 10.1109/Deep-ML.2019.00010
Authors : Kyu Beom Lee , Hyu Soung Shin
[6]. A Survey of Scalable Deep Learning Frameworks
Date of Conference: 24-27 Sept. 2019
DOI: 10.1109/eScience.2019.00102
Authors : Saba Amiri, A.S.Z. Belloum
[7]. Review and comparison of face detection algorithms
Date of Conference:12-13 Jan. 2017
DOI: 10.1109/CONFLUENCE.2017.7943228
Authors : Kirti Dang
CSE Department, Shanu Sharma , ASET Amity University Noida, India

[8]. Robust face detection from still images

Date of Conference: 9-12 Dec. 2014
DOI: 10.1109/CIBIM.2014.7015446
Authors : Patrick Laytner ,Chrisford Ling,Qinghan Xiao
Radar Electronic Warfare DRDC Ottawa, Ottawa, Canada
[9]. Raspberry PI Based OFFLINE MEDIA SERVER
Date of Conference: 27-29 March 2019
DOI: 10.1109/ICCMC.2019.8819718
Authors : Anurag P. Jadhav ,V.B. Malode

Electronics and Telecommunication Engineering, MGM’s Jawaharlal Nehru

Engineering College, Aurangabad, India

B.E (EEE) Project Phase I Page 39

 AUTOMATIC FACE MASK DETECTION 2020-2021

[18]. Created by self-using fritzing.org

B.E (EEE) Project Phase I Page 40