You are on page 1of 9

FACE MASK DETECTION

IN COVID CRISIS
Group Members And Course
Information:

 SHIVAM 18BEC0431 Course: IoT DOMAIN ANALYST


 SIDHANT MADHAB 18BEC0318 Faculty: Prof. SANKAR GANESH S.
MOHANTY Course code: ECE3502
 AAMIR NAIYER 18BEC0294
Slot: B2
Introduction:

 In the Covid-19 pandemic situation public places are opening in


stages. The World Health Organization (WHO) reports suggest that
the two main routes of transmission of the COVID-19 virus
are respiratory droplets and physical contact. Wearing a medical
mask is one of the prevention measures that can limit the spread of
certain respiratory viral diseases, including COVID-19.
 Thus, to contain the spread, entry based face mask detection
is essential and a recent necessity.
 Face mask detection has emerged as a very interesting problem in
image processing and computer vision. Many new algorithms are
being devised using convolutional architectures to make the
algorithm as accurate as possible. These convolutional architectures
have made it possible to extract even the pixel details.
 In this project, we aim to deployed such a model to build a binary
face classifier which can detect whether mask is present on a face or
not when people will stand before the detector mask with the help of
computer vision and deep learning algorithm.
Problem Statement:

 To create an entry-based system for FACE MASK DETECTOR


for deployment at various fields such as airports, bus and railway
stations, malls or any other crowded place using OpenCV and
MobileNet neural net based on deep learning and CNN
(convolutional neural network).

 This system detects and allows only those wearing mask and sets
off an indicator whenever a violation is observed.
ESSENSE OF IoT

 1. OpenCV - it’s a set of libraries for handling real time


computer vision.

 2. MobileNET - these are space-efficient CNN architecture.


Work Flow / Methodology

Image Generate Serialize


Load preprocessin g
Face and Train Face Mask TRAINING
using PyTorch
face Mask Classifier
Mask transforms and
Classifier and Save THE
OpenCV
data
MODEL

Image Apply t he Face


Load Face Load Faces processing Mask Detector
TESTING Mask from using t o determine
Classifier image/vide o
THE from Disk stream
PyTorch
and
“Mask” or “No
Mask”
MODEL OpenCV

Show
Result
Cost Analysis

• Since it is very labor-intensive to keep a check in public and private places


for face-mask, computer vision makes it easy for real-time monitoring.

• It took lot of energy, money and time to physically go around checking if


people are wearing mask or not.

• Rather no man power is required to keep an eye on people not wearing as


system will tell us.

• It will be the cost efficient but only thing requires is a hefty amount of
money for system to run the algorithms.
Applications and Use Cases:

• Airports
The Face Mask Detection System could be used at airports to detect travelers
without masks. Face data of travelers can be captured in the system at the
entrance. If a traveler is found to be without a face mask, their picture is sent to the
airport authorities so that they could take quick action.
• Hospitals
Using Face Mask Detector System, Hospitals can monitor if quarantined people
required to wear a mask are doing so or not. The same holds good for monitoring staff
on duty too.
• Offices & Working Spaces
The Face Mask Detection System can be used at office premises to ascertain if
employees are maintaining safety standards at work. It monitors employees without
masks and sends them a reminder to wear a mask.
• Government
To limit the spread of coronavirus, the police could deploy the face mask detector on
its fleet of surveillance cameras to enforce the compulsory wearing of face masks in
public places.
Gantt Chart

• Week 1: Brainstorming the idea

• Week 2: Finding the appropriate python libraries and the platform to code.

• Week 3: Coding and Debugging.

• Week 4: Collecting the training data.

• Week 5: Finalisation and result.

You might also like