A

PROJECT REPORT
ON
Mask Detector
Submitted to
Dr. Babasaheb Ambedkar Technological
University, Lonere
IN PARTICAL FULFILMENT OF THE REQUIREMENT
FOR THE DEGREE
OF BACHELOR OF COMPUTER ENGINEERING
Submitted by
GUND MAYUR MAHADEV 4027
ALASE AKASH KALLUSHA 4028
MANE YESHIKA SUNIL 4029
HINGMIRE AISHWARYA GAJANAN 4030

Under the Guidance of

Prof. A.A.TODKAR

DEPARTMENT OF COMPUTER ENGINEERING

Sanjay Bhokare Group of Institutes, Miraj

Academic Year 2022 – 2023

 Shri Ambabai Talim Sanstha's
Sanjay Bhokare Group of Institutes, Miraj — 416 410.

CERTIFICATE
This is to certify that the following students of B.TECH
(Computer) at Sanjay Bhokare Group of Institutes, Miraj has
satisfactorily completed the project work entitled “MASK
DETECTOR” in partial fulfillment for award of Bachelor of
Technology Degree in Computer Engineering by Dr.Babasaheb
Ambedkar Technological University, Lonere in the year 2022-2023.

Sr. No Name Roll.No

1 MAYUR MAHADEV GUND 4027
2 ALASE AKASH KALLUSHA 4028
3 MANE YESHIKA SUNIL 4029
4 HIGMIRE AISHWARYA GAJANAN 4030

Prof. A. A. Todkar Prof. C.G. Kokane Pawar Dr. A. C. Bhagali

Guide
Faculty HoD Director Examiner
 Shri Ambabai Talim Sanstha's
Sanjay Bhokare Group of Institutes, Miraj
Department of Computer Engineering

CERTIFICATE
This is to certify that, the project entitled “MASK DETECTOR” is
presented before Departmental research committee (DRC) by the
following students under the guidance of Prof.A.A.Todkar for the
academic year 2022-2023. The DRC has approved the said project.

Sr. No Name Roll.No

1 GUND MAYUR MAHADEV 4027

2 ALASE AKASH KALLUSHA 4028

3 MANE YESHIKA SUNIL 4029

4 HINGMIRE AISHWARYA GAJANAN 4030

Head,
Departmental Research Committee
Department of Computer Engineering.
 ACKNOWLEDGEMENT

Every orientation work has an imprint of many people and it becomes our
duty to express deep gratitude for the same. During the entire duration of preparation
for this Dissertation, we received endless help from a number of people and feel that
this report would be incomplete if we do not convey graceful thanks to them.

This acknowledgement is hummable attempt to thanks all those who were

involved in the project work and were of immense help to us. First and foremost we
take the opportunity to extend our deep heartfelt gratitude to our project guide
Ms.A.A.Todkar for guiding us throughout the entire project and for his kind and
valuable suggestions, without which this idea won't have executed. I also humbly
thanks Mr.C.G.Kokane Head of Department of Computer Engineering, SBGI, Miraj
(Sangli), for his indispensable support, his priceless suggestion and for his teaching
and non-teaching staff for their advice and kind cooperation. We also thanks our
parents and all my colleagues for encouraging me with their valuable suggestions
and motivating me from time to time. Finally, last but not least, we would thank the
almighty without whose care and blessing this work would have not completed.

Thank You.

No. Name Sign.

1 GUND MAYUR MAHADEV

2 ALASE AKASH KALLUSHA

3 MANE YESHIKA SUNIL

4 HINGMIRE AISHWARYA GAJANAN

 Abstract
In this project, we propose a deep learning-based approach for face mask
detection to ensure compliance with mask-wearing guidelines.
Our methodology leverages deep neural networks to develop an accurate
and efficient face mask detector system. We utilize a large dataset of labelled
images containing individuals wearing or not wearing face masks, which is used
to train our deep learning model. The dataset encompasses diverse scenarios,
lighting conditions, and facial orientations to enhance the system's robustness.
The proposed system follows a multi-step approach. First, faces are
detected in video frames using a pre-trained face detection algorithm.
Subsequently, the regions of interest containing the faces are extracted for further
processing. Our deep learning model is then applied to classify each face as either
wearing a mask or not.
The results demonstrate the effectiveness of our deep learning-based face
mask detector system in accurately identifying individuals wearing or not wearing
masks. The system achieves high accuracy and demonstrates robustness against
real-world challenges. System generates a beep alert if peoples are without mask.
This project's findings can be instrumental in automating mask-wearing
compliance monitoring in public spaces, enhancing public health safety, and
enabling efficient resource allocation.
 CONTENTS

Ch.No Topic Page No.

Acknowledgement
Abstract
Contents
Figures Index
Chapter 1 Introduction 1
1.1 Background 1
1.2 Need for Mask Detection 2
1.3 Scope 3
1.4 Overview 3
Chapter 2 Software Requirement
2.1 Python IDE 4
Chapter 3 Literature Review 5

Chapter 4 Design Methodology 7

4.1 System Design 7
4.2 Sequence Diagram 8
4.3 Use Case Diagram 9
4.4 Activity Diagram 10
4.5 Class Diagram 11

Chapter 5 Implementation Details 12

5.1 Software Requirements 12
5.2 Hardware Requirements 12
5.3 Technology Details 12
Chapter 6 Result 20
6.1 Snapshots 20

Chapter 7 Limitation 21

Chapter 8 Future Prospects 22

Chapter 9 Conclusion 23
 FIGURE INDEX

Figure No. Name

1 SYSTEM DIAGRAM
2 SEQUENCE DIAGRAM
3 USE CASE DIAGRAM
4 ACTIVITY DIAGRAM
5 CLASS DIAGRAM
6 HAAR-CASCADE DIAGRAM
7 FEATURE DIAGRAM
8 CONVOLUTIONAL NEURAL NETWORK
 MASK DETECTOR

CHAPTER 1 - Introduction

The COVID-19 pandemic has drastically transformed the way we live, work,
and interact with one another. In order to mitigate the spread of the virus, wearing
face masks has become an essential practice in public spaces. However, ensuring
compliance with mask-wearing guidelines can be challenging, especially in
crowded areas or places where monitoring is difficult.

To address this challenge, the face mask detection project aims to develop a
computer vision-based system that can automatically detect whether individuals
are wearing face masks or not. This system can assist in enforcing mask-wearing
policies, improve public health safety, and streamline monitoring efforts.

The goal of the project is to leverage the power of deep learning and
computer vision algorithms to accurately identify and classify faces as either
wearing masks or not.

1.1. Background

COVID 19 pandemic is causing a global health epidemic. The most powerful

safety tool is wearing a face mask in public places and everywhere else. The habit
of wearing face masks while stepping out is rising due to the COVID- 19 corona
virus epidemic. Before Covid-19, masks were worn by people to protect their health
from air pollution. Scientists have concluded that wearing face masks works on
decreasing COVID-19 transmission. In 2020, the rapid spread of COVID-19 led the
World Health Organization to declare COVID- 19 as a global pandemic. The virus
spreads through close contact of humans and in crowded/overcrowded places.
Among them cleaning hands, maintaining a safe distance, wearing a mask,
refraining from touching eyes, nose, and mouth are the main, where wearing a mask
is the simplest one. Unfortunately, people are not following these rules properly
which is resulting in speeding the spread of this virus. The solution can be to detect
the people not wearing mask and informing their authorities. the face mask detection

Department of Computer Engineering 2022-23 1|Page

 MASK DETECTOR

is a technique to find out whether the person is wearing a mask or not. In medical
applications Deep learning techniques are highly used as it allows researchers to
study and evaluate large quantities of data. Deep learning models have shown great
role in object detection. These models and architectures can be used in detecting the
mask on a face. Here we introduce a face mask detection model which is based on
computer vision and deep learning

1.2. Need for Mask Detection

Wearing face masks has been recognized as an effective measure in reducing the
transmission of respiratory droplets, which can carry infectious diseases like
COVID-19. By detecting individuals who are not wearing masks in public spaces,
face mask detection systems contribute to maintaining public health safety and
preventing the spread of contagious diseases.
Ensuring compliance with mask-wearing guidelines is crucial in controlling the
spread of infectious diseases. However, manual monitoring of mask-wearing in
crowded areas or public spaces can be challenging, time-consuming, and prone to
errors.
Resource Optimization: Human resources dedicated to monitoring mask-
wearing compliance could be deployed more effectively for other critical tasks if
face mask detection systems are employed. By automating the detection process,
authorities can optimize resource allocation, directing personnel to areas where non-
compliance is detected or assisting individuals who require guidance on mask usage.
Face mask detection systems provide real-time insights into the adherence to
mask-wearing guidelines. This information can be used by authorities to identify
patterns, hotspots, or areas of concern, enabling them to implement targeted
interventions, enforce regulations, and educate the public about the importance of
mask-wearing.

Department of Computer Engineering 2022-23 2|Page

 MASK DETECTOR

1.3. Scope

The system is easy to operate and it can be used in crowded areas. It also
ensures the compliance for wearing mask and the system provides accurate
assessment of the individual in public areas weather the person is wearing a mask
or not.

1.4. Overview

The main purpose the system is to detect the face with mask or without mask,
if without mask the system informs to authorities and beep alert generated.

Department of Computer Engineering 2022-23 3|Page

 MASK DETECTOR

CHAPTER 2 - Software Requirement

2.1. Python IDE:

A Python Integrated Development Environment (IDE) is a software

application that provides a comprehensive set of tools and features to facilitate the
development, testing, and debugging of Python code. IDEs are designed to enhance
the productivity and efficiency of developers by offering a unified environment for
coding, managing projects, and interacting with various development resources.
Here are some key components and features commonly found in Python IDEs:
Code Editor: The code editor is the primary component of an IDE. It provides
features like syntax highlighting, code completion, code suggestion, and automatic
formatting to help write clean and error-free code. The editor often supports multiple
file editing, allowing you to work on multiple code files simultaneously.
Project Management: IDEs typically include project management features, allowing
you to organize your code files, dependencies, and resources. This can involve
creating and managing project structures, setting up virtual environments, and
integrating with version control systems like Git for code collaboration and tracking
changes.
Debugging Tools: IDEs provide debugging capabilities, allowing you to find and fix
errors in your code. They typically offer features like breakpoints, step-by-step code
execution, variable inspection, and the ability to analyze the call stack. Debugging
tools help identify and resolve issues, improving code quality and efficiency.

Department of Computer Engineering 2022-23 4|Page

 MASK DETECTOR

CHAPTER 3 - Literature Review

The Literature Survey is used to provide a brief overview and explanation about
the reference papers. Literature survey conveys the technical details related to the
project in a prop under and detailed manner.

• Title: Face Mask Detection using Transfer Learning of InceptionV3

• Author: G. Jignesh Chowdary, Narinder Singh Puny, Sanjay Kumar
Sonbhadra and Sonali Agarwal
• Description: In the paper, a transfer learning model is proposed to automate
the process of identifying the people who are not wearing masks. The model
uses deep learning algorithm Inception V3 to detect face masks. The
Simulated Masked Face Dataset is used for training and testing. Due to the
limited availability, image augmentation technique is used for better training
and testing of the model. The model achieved an accuracy of 99.9% during
training and 100% during testing.

• Title: Detection of Face Mask using Convolutional Neural Network

• Author: Riya Chiragkumar Shah and Rutva Jignesh Shah
• Description: The model proposed here is designed and modeled using
python• libraries namely tensorflow, keras and opencv. The model used is
the MobileNetV2 of convolutional neural networks. In this paper, a model
is developed using the above mentioned libraries. The model is tested for
different conditions with different hyper parameters. First dataset is fed in
the model, run the training program, which trains the model on the given
dataset. Then the detection program is run, which turns on the video stream,
captures the frames continuously from the video stream with an anchor box
using object detection process. The output is then passed through
MobileNetV2 layers where it is classified into people wearing a mask
surrounded by green boxes and people not wearing a box surrounded by red
boxes. Face Mask detection using ML and DL

Department of Computer Engineering 2022-23 5|Page

 MASK DETECTOR

• Title: 2nd International Conference on advance research in Science,

Engineering and Technology (COVID-19 Face Mask Detection
• Author: Parul Mourya,Sejal Nayak
• Description: This proposed system very simple and basic Convolutional
Neural Network (CNN) model using TensorFlow with Keras library and
OpenCV to detect if you are wearing a face mask to protect yourself. It is
an object detection and classification problem with two different classes
(Mask and Without Mask). A hybrid model using deep and classical
machine learning for detecting face mask will be presented. A dataset is
used to build this face mask detector using Python, OpenCV, and
TensorFlow and Keras. While entering the place everyone should scan
their face and then enter ensuring they have a mask with them. If anyone is
found to be without a face mask, beep alert will be generated. As all the
workplaces are opening. The number of cases of COVID-19 are still
getting registered throughout the country. If everyone follows the safety
measures, then it can come to an end. Hence to ensure that people wear
masks while coming to work we hope this module will help in detecting it.

Department of Computer Engineering 2022-23 6|Page

 MASK DETECTOR

CHAPTER 4 - Design Methodology

4.1 System Design

System Design is the process of designing the architecture, components, and

interfaces for asystem so that it meets the end-user requirements.

Department of Computer Engineering 2022-23 7|Page

 MASK DETECTOR

4.2 Sequence Diagram

A sequence diagram is a type of interaction diagram because it describes how

and in what ordera group of objects works together. These diagrams are used by
software developers and business professionals to understand requirements for a
new system or to document an existing process. Sequence diagrams are sometimes
known as event diagrams or event scenarios.

Department of Computer Engineering 2022-23 8|Page

 MASK DETECTOR

4.3 Use Case Diagram

In the Unified Modelling Language (UML), a use case diagram can summarize
the details ofyour system's users (also known as actors) and their interactions with
the system. To build one, you'll use a set of specialized symbols and connectors.

Department of Computer Engineering 2022-23 9|Page

 MASK DETECTOR

4.4 Activity Diagram

An activity diagram is a behavioral diagram i.e., it depicts the behavior of a

system. An activity diagram portrays the control flow from a start point to a finish
point showing the various decision paths that exist while the activity is being
executed.

Department of Computer Engineering 2022-23 10 | P a g e

 MASK DETECTOR

4.5 Class Diagram

A class diagram is a type of structural diagram in UML (Unified Modelling

Language) that represents the static structure and relationships among classes in a
system. It provides an overview of the classes, their attributes, methods, and the
associations between them.

Department of Computer Engineering 2022-23 11 | P a g e

 MASK DETECTOR

CHAPTER 5 - Implementation Details

5.1 SOFTWARE USED

• Python IDE
• VS Code

5.2 HARDWARE USED

• Working webcam
• 4 GB RAM and above
• Processor

5.3 Technology Details

OPENCV

It is a cross-platform library using which we can develop real-time computer

vision applications. .It mainly focuses on image processing, video capture and
analysis including feature like face detection and object detection. OpenCV (Open-
Source Computer Vision Library) is an opensource computer vision and machine
learning software library. OpenCV was built to provide a common infrastructure for
computer vision applications and to accelerate the use of machine perception in the
commercial products. Being a BSD-licensed product, OpenCV makes it easy for
businesses to utilize and modify the code. The library has more than 2500optimized
algorithms, which includes a comprehensive set of both classic and state-of -the-art
computer vision and machine learning algorithms.

Department of Computer Engineering 2022-23 12 | P a g e

 MASK DETECTOR

NUMPY

NumPy is a library for the Python programming language, adding support for large,
multidimensional arrays and matrices, along with a large collection of highlevel
mathematical functions to operate on these arrays. The ancestor of NumPy,
Numeric, was originally created by Jim Hugunin with contributions from several
other developers. In 2005, Travis Oliphant created NumPy by incorporating features
of the competing Num array into Numeric, with extensive modifications. NumPy is
opensource software and has many contributors. MATPLOT Mat plot is a plotting
library for the Python programming language and its numerical mathematics
extension NumPy. It provides an object-oriented API for embedding plots into
applications using general-purpose GUI toolkits like Tkinter, WX Python, Qt, or
GTK+. There is also a procedural "Pylab" interface based on a state machine (like
OpenGL), designed to closely

resemble that of MATLAB, though its use is discouraged SciPy makes use of
Matplotlib.

Department of Computer Engineering 2022-23 13 | P a g e

 MASK DETECTOR

Machine Learning

Machine learning is a field of study and application within artificial intelligence (AI)
that focuses on the development of algorithms and models that allow computers to
learn and make predictions or decisions without being explicitly programmed. It is
based on the idea that machines can learn from and adapt to data, enabling them to
improve their performance over time.

In traditional programming, a programmer writes explicit instructions for a

computer to follow. However, in machine learning, the computer learns patterns and
relationships directly from data, allowing it to make predictions, classifications, or
decisions.

There are several types of machine learning algorithms, including:

Supervised Learning: The model learns from labeled examples where the input data
is paired with the corresponding correct output or target values. It then makes
predictions or classifications on new, unseen data.

Unsupervised Learning: The model learns from unlabeled data and aims to discover
patterns, relationships, or structures within the data. It does not have explicit target
values to learn from.

Semi-Supervised Learning: This type of learning is a combination of supervised and

unsupervised learning. It uses a small amount of labeled data along with a larger
amount of unlabeled data.

Reinforcement Learning: The model learns through interactions with an

environment and receives feedback in the form of rewards or penalties. It aims to
find the optimal actions or policies that maximize the cumulative reward.

Department of Computer Engineering 2022-23 14 | P a g e

 MASK DETECTOR

HAAR Feature-Based Cascade Classifiers

It is an Object Detection Algorithm used to identify faces in an image or a

real time video. Dense grid of uniformly spaced cells and uses overlapping local
contrast normalization for improved accuracy. It is an effective way for object
detection. In this approach, lot of positive and negative images are used to train the
classifier. In this, a model is pre-trained with frontal features is developed and used
in this experiment to detect the faces in real-time.

Fig. Haar-Cascade Classifier

Here we will work with face detection. Initially, the algorithm needs a lot of
positive images (images of faces) and negative images (images without faces) to
train the classifier. Then we need to extract features from it. For this, haar features
shown in below image are used. They are just like our convolutional kernel. Each
feature is a single value obtained by subtracting sum of pixels under white rectangle
from sum of pixels under black rectangle.
Now all possible sizes and locations of each kernel is used to calculate plenty
of features. For each feature calculation, we need to find sum of pixels under white
and black rectangles. To solve this, they introduced the integral images. It simplifies
calculation of sum of pixels, how large may be the number of pixels, to an operation
Department of Computer Engineering 2022-23 15 | P a g e
 MASK DETECTOR

involving just four pixels. It makes things super-fast.

But among all these features we calculated, most of them are irrelevant. For
example, consider the image below. Top row shows two good features. The first
feature selected seems to focus on the property that the region of the eyes is often
darker than the region of the nose and cheeks.The second feature selected relies on
the property that the eyes are darker than the bridge of the nose. But the same
windows applying on cheeks or any other place is irrelevant.

Now all possible sizes and locations of each kernel is used to calculate plenty
of features. For each feature calculation, we need to find sum of pixels under white
and black rectangles. To solve this, they introduced the integral images. It simplifies
calculation of sum of pixels, how large may be the number of pixels, to an operation
involving just four pixels. It makes things super-fast.

But among all these features we calculated, most of them are irrelevant. For
example, consider the image below. Top row shows two good features. The first
feature selected seems to focus on the property that the region of the eyes is often
darker than the region of the nose and cheeks.The second feature selected relies on
the property that the eyes are darker than the bridge of the nose. But the same
windows applying on cheeks or any other place is irrelevant.

Department of Computer Engineering 2022-23 16 | P a g e

 MASK DETECTOR

For this, we apply each and every feature on all the training images. For each
feature, it finds the best threshold which will classify the faces to positive and
negative. But obviously, there will be errors or misclassifications. We select the
features with minimum error rate, which means they are the features that best
classifies the face and non-face images. (The process is not as simple as this. Each
image is given an equal weight in the beginning. After each classification, weights
of misclassified images are increased. Then again same process is done. New error
rates are calculated. Also new weights. The process is continued until required
accuracy or error rate is achieved or required number of features are found).

Department of Computer Engineering 2022-23 17 | P a g e

 MASK DETECTOR

CONVOLUTIONAL NEURAL NETWORK

A convolution neural network is a special architecture of artificial neural network

proposed by yann lecun in 1988. One of the most popular uses of the architecture is
image classification. CNNs, like neural networks, are made up of neurons with
learnable weights and biases. Each neuron receives several inputs, takes a weighted
sum over them, pass it through an activation function and responds with an output.
The whole network has a loss function and all the tips and tricks that we developed
for neural networks still apply on CNNs.

Fig. Convolutional Neural Network

A convolutional neural network consists of an input layer, hidden layers and

an output layer. In any feed-forward neural network, any middle layers are called
hidden because their inputs and outputs are masked by the activation function and
final convolution. In a convolutional neural network, the hidden layers include
layers that perform convolutions.

Convolutional layers
In a CNN, the input is a tensor with a shape: (number of inputs) x (input height) x
(input width) x(input channels). After passing through a convolutional layer, the
image becomes abstracted to a feature map, also called an activation map, with
shape: (number of inputs) x (feature map height)x (feature map width) x (feature
Department of Computer Engineering 2022-23 18 | P a g e
 MASK DETECTOR

map channels).Convolutional layers convolve the input and passits result to the next
layer. This is similar to the response of a neuron in the visual cortex to a specific
stimulus. Each convolutional neuron processes data only for its receptive field.
Although fully connected feedforward neural networks can be used to learn features
and classify data, this architecture is generally impractical for larger inputs such as
high-resolution images.
Pooling layers
Convolutional networks may include local and/or global pooling layers along with
traditional convolutional layers. Pooling layers reduce the dimensions of data by
combining the outputs of neuron clusters at one layer into a single neuron in the next
layer. Local pooling combines small clusters, tiling sizes such as 2 x 2 are commonly
used. Global pooling acts on all the neurons of the feature map. There are two
common types of pooling in popular use: max and average. Max pooling uses the
maximum value of each local cluster of neurons in the feature map, while
average pooling takes the average value.
Fully connected layers
Fully connected layers connect every neuron in one layer to every neuron in another
layer. It is the same as a traditional multilayer perceptron neural network (MLP).
The flattened matrix goes through a fully connected layer to classify the images.
Weights
Each neuron in a neural network computes an output value by applying a specific
function to the input values received from the receptive field in the previous layer.
The function that is appliedto the input values is determined by a vector of weights
and a bias (typically real numbers). Learning consists of iteratively adjusting these
biases and weights.The vector of weights and the bias are called filters and represent
particular features of the input (e.g., a particular shape). A distinguishing feature of
CNNs is that many neurons can share the same filter. This reducesthe memory
footprint because a single bias and a single vector of weights are used across all
receptive fields that share that filter, as opposed to each receptive field having its
own bias and vector weighting.

Department of Computer Engineering 2022-23 19 | P a g e

 MASK DETECTOR

CHAPTER 6 - Result

6.1. Snapshots

Fig. With Mask

Fig. Without Mask

Department of Computer Engineering 2022-23 20 | P a g e

 MASK DETECTOR

CHAPTER 7 Limitation

Limitation:

There were not many challenges faced but the two problems that were time
consuming and made the tasks tedious are discussed as follows. One was the
excessive data collecting real time imagesfor dataset and second is when detecting
person in came for capturing we need to maintain specific distance from camera.

Department of Computer Engineering 2022-23 21 | P a g e

 MASK DETECTOR

CHAPTER 8- Future Prospects

Future Prospects:

More than fifty countries around the world have recently initiated wearing
face masks compulsory. People have to cover their faces in public, supermarkets,
public transports, offices, and stores. Retail companies often use software to count
the number of people entering their stores. They may also like to measure
impressions on digital displays and promotional screens. Our software can be
equated to any existing cameras to detect people without a mask. This detection live
video feed can be implemented in web applications so that the operator can see
notice messages. . In scenarios such as community access, campus governance, and
enterprise resumption, the algorithm will provide contactless facial authentication.

Department of Computer Engineering 2022-23 22 | P a g e

 MASK DETECTOR

CHAPTER 9- Conclusion

Conclusion:

As the technology is booming with emerging trends therefore the

novel face mask detector which can possibly contribute to public
healthcare. The model is trained on an authentic dataset. We used
OpenCV and CNN to detect whether people werewearing face masks or
not. The models were tested with images and real-time video. The
accuracy of the model is achieved and, the optimization of the model is
a continuous process and we are building an accurate solution by tuning
the hyper parameters. This specific model could be used as a use case
for edge analytics. By the developing this system, we can detect if the
person is wearing a face mask and allow their entry would be of great
help to the society

Department of Computer Engineering 2022-23 23 | P a g e

 MASK DETECTOR

Bibliography

Bibilography:

• www.wikipedia.com
• https://pypi.org/project/opencv-python/
• https://www.python.org/downloads/
• https://matplotlib.org/
• https://pypi.org/project/gTTS/

1. G. Jignesh Chowdary, Narinder Singh Punn, Sanjay Kumar Sonbhadraand

Sonali Agarwal, Face Mask Detection using Transfer Learning of
InceptionV3, IEEE Access, 20, pp. 456-665, 2021
2. Riya Chiragkumar Shah and Rutva Jignesh Shah., Detection of Face Mask
using Convolutional Neural Network, Mobile Information System, 43,
pp.382-487, 2019.
3. 2nd International Conference on advance research in Science, Engineering
and Technology (COVID-19 Face Mask Detection –Parul Mourya,Sejal
Nayak).

Department of Computer Engineering 2022-23 24 | P a g e

 MASK DETECTOR

Achivements:

Department of Computer Engineering 2022-23 25 | P a g e

 MASK DETECTOR

Department of Computer Engineering 2022-23 26 | P a g e

 MASK DETECTOR

Department of Computer Engineering 2022-23 27 | P a g e