0% found this document useful (0 votes)

136 views

Face Mask Detection System

This document describes a face mask detection system using computer vision and deep learning to detect whether people are wearing masks in public spaces like stores. The system uses a Single Shot Detector (SSD) model with a lightweight backbone network for fast, real-time detection from camera feeds. It is intended to send notifications to store owners if customers are not wearing masks to help curb the spread of COVID-19 and ensure customer safety. The system achieved 97% accuracy in detecting masks and is intended to continuously optimize the model for more precise detection.

Uploaded by

Ashok Lord

Available Formats

Download as PPTX, PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

136 views

Face Mask Detection System

Uploaded by

Ashok Lord

Available Formats

Download as PPTX, PDF, TXT or read online on Scribd

You are on page 1/ 17

FACE MASK ETIQUETTE

DETECTION SYSTEM FOR

STORE OWNERS
6.53
AND
SHOPPERS
Guide: Prof. Punith Bekal
Presented By :
K Gautham Kamath
Mishal Ramesh Salian
Rakshith
Swasthik
CONTENTS

• Abstract
• Introduction
• Literature Survey
• System Design
• Methodology Adapted
• System Requirements
• Advantages
• Expected Results
• References
CONTENTS 2
ABSTRACT
Ever since the pandemic began, people have must wear face masks to curb the spread of
Covid-19 The aim of this project is to replicate on a computer to detect the presence of
faces in their field of vision.

This project aims at using a camera placed in different places around the area, to capture
images and detect the presence of a facemask in real-time. We present an object detection
method, based on single-shot detector (SSD), which centers around accurate and real
time facemask detection in general stores and supermarkets.

Introducing a lightweight backbone network for feature extraction, which dependent on

SSD and spatial separable convolution, expecting to further develop the detection speed
and meet the necessities of real-time detection .

ABSTRACT 3
INTRODUCTION

INTRODUCTION
Epidemiological survey and genotyping have confirmed that COVID-19 is highly infectious.

To prevent the spread of the infection, researchers suggest that all individuals wear facial coverings
or masks in public.

Grocery store and supermarkets are highly people intensive place. The possibility of infection is
very high .

We are using SSD and FEM technology.

So we are developing an app that sends real-time notification to the owner of the establishment
regarding the mask wearing etiquette of the customers.

4
LITERATURE SURVEY
Howard A G, Zhu M, Chen B, et al. Mobile Nets: Efficient Convolutional Neural Networks for Mobile
Vision Applications. 2017.
They present a class of efficient models called MobileNets for mobile embedded vision applications; which
demonstrates the effectiveness of MobileNets across a wide range of applications

Zou Z, Shi Z. Ship detection in spaceborne optical image with SVD networks.
Automatic Ship detection on Spaceborne optical images is a challenging task, which has attached wide attention
due to its extensivity potential application in maritime security & traffic control

Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector//European conference on computer
vision. Springer, Cham, 2016: 21-37.
Proposed a thesis for detecting objects in images using a single deep neural network, Our approach named SSD
discretizes the output space of bounding boxes into a set of default boxes

Chen X, Kundu K, Zhu Y, et al. 3d object proposals for accurate object class detection//Advances in Neural
Information Processing Systems.
Our Method exploits stereo imagery to place proposals in the form of 3D bounding boxes.

Cao G, Xie X, Yang W, et al. Feature-fused SSD: Fast detection for small objects//Ninth International
Conference on Graphic and Image Processing (ICGIP 2017). International Society for Optics and Photonics,
2018, 10615: 106151E.
Small object detection is a challenging task in computer vision due to its limited resolution and information. The
aim to detect images at blistering fast speed using SSD. 5
SYSTEM DESIGN

Using the existing CCTV’s or web cam we propose to use the existing hardware to implement SSD
and backbone network

Where the convolution layers are deeply studied and trained leading the proposed algorithm to send
a warning if the mask is not worn

An app notification is directly sent to the establishment owner as to inform the mask etiquette
warning

6
IMPLEMENTATION 7
Pitch deck title 8
METHODOLOGY ADAPTED
Lightweight backbone network:
• The backbone network is based on SSD.

Feature Enhancement Module (FEM):

• To improve the representation capability of the network the small objects we
presented the Feature Improvement Module (FEM).

10
Convolutional neural network:
In deep learning convolutional neural
network is a algorithm which can take in
an input image ,
assign importance to various aspects in the
image

11
SYSTEM REQUIRMENTS

H/W S/W
• Working Camera • Python
• 4 GB RAM or above • SSD
• 1TB Hard Disk
• Android Studio
• 64-bit processor
• Operating System • Flutter
• Android Phone • Open-CV
• Power Supply • Kotlin