SlideShare uma empresa Scribd logo
1 de 4
Baixar para ler offline
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2942
FACE MASK DETECTION USING ML
Prof .V.O.Patil, Darshana Rajendra Javheri, Neha Vinod Patil, Aditi Sanjay Jaiswal
1Assistant Professor at Department of Computer Engineering, PSGVP Mandal’s D.N.Patel College of
Engineering, Shahada, Maharashtra, India
2Final Year Students of Department of Computer Engineering, PSGVP Mandal’s D.N.Patel College of
Engineering, Shahada, Maharashtra, India
------------------------------------------------------------------***---------------------------------------------------------------------------
Abstract- As we all know COVID-19 pandemic has rapidly affected our day-to-day life disrupting the world trade and movements.
So wearing a mask, wearing a protective face mask is become the new normal. However, still have few ways to control the
outbreak as instructed by the WHO (World Health Organization).Hence Using Face Mask Detection System, one can monitor if the
people are wearing masks or not. This project presents a simplified approach to achieve this purpose using some basic Machine
Learning packages like TensorFlow, Keras, Open, CV and Scikit-Learn. There are a few processes involved in achieving the
objective of the project that includes pre-processing, data augmentationn, training ,testing, and image segmentation. The method
attains accuracy up to 95.77 percent and 94.58 percent respectively on two different datasets.
Keywords- Tenserflow, openCV, Keras, Numpy, Scikit-Learn.
I. INTRODUCTION
COVID-19 pandemic has had an enduring effect in many nations global due to the fact that December 2019. It originated in
Wuhan, China. The World Health Organization (WHO) as of March 11, 2020, declared it a pandemic that received its roots
throughout the globe and critically affected 114 countries. Every clinical professional, healthcare organizations, clinical
practitioners, and researchers are searching for right vaccines and drugs to conquer this lethal disease, but no leap forward
has been stated until date. The virus spreads thru air channel whilst an inflamed man or woman sneezes or talk with the
alternative man or woman, the water droplets from their nostril or mouth disseminate thru the air and have an effect on
different peoples withinside the vicinity (Kumar et al., 2020). Face Mask detection has turn out to be a trending software
because of the Covid-19 pandemic, which needs someone to put on face masks, maintain social distancing, and use hand
sanitizers to scrub their hands. While different issues of social distancing and sanitization were addressed till now, the
problem of face masks detection has now no longer but been accurately addressed. Wearing a masks all through this pandemic
is a essential safety measure and is maximum crucial step in instances whilst social distancing is tough to maintain.
Face Mask detection has became as much as be an outstanding hassle withinside the area of photograph processing and pc
vision. Face detection has diverse use instances starting from face popularity to shooting facial motions, in which the latter
requires the face to be discovered with very excessive precision. Due to the speedy development withinside the area of device
gaining knowledge of algorithms, the jeopardies of face masks detection era appear to be properly addressed yet. This era is
extra applicable these days because it is used to detect faces not only in static images and videos but also in real-time
inspection and supervision.
II. LITURATURE SURVEY
In the latest past, diverse researchers and analysts specifically targeted on gray-scale face image. While a few had been
absolutely constructed on sample identity models, owning preliminary facts of the face version whilst others had been the use
of AdaBoost, which changed into an fantastic classifier for schooling purposes. Then got here the Viola-Jones Detector, which
supplied a leap forward in face detection technology, and real-time face detection were given possible. It confronted diverse
issues just like the orientation and brightness of the face, making it tough to intercept. So basically, it did not paintings in
stupid and dim light. Thus, researchers began out looking for a brand new opportunity version that might effortlessly discover
faces in addition to mask at the face.
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2943
III. METHODOLOGY
To are expecting whether or not someone has worn a masks correctly, the preliminary degree might be to educate the version
the usage of a right dataset. After education the classifier, an correct face detection version is needed to come across faces, in
order that the SSDMNV2 version can classify whether or not the man or woman is carrying a masks or not. The mission on this
paper is to elevate the accuracy of masks detection with out being too resource-heavy. For doing this mission, the DNN module
become used from OpenCV, which incorporates a ‘Single Shot Multibox Detector’ (SSD) item detection version with ResNet-10
as its spine architecture. This technique enables in detecting faces in real-time, even on embedded gadgets like Raspberry Pi.
The following classifier makes use of a pre-educated version MobileNetV2 to are expecting whether or not the man or woman
is carrying a masks or not.
IV. DATASET USED
There are just a few datasets to be had for the detection of face masks. Most of them are both artificially created, which doesn’t
constitute the actual international accurately, or the dataset is complete of noise and incorrect labels. So, selecting the proper
dataset which might paintings nice for the SSDMNV2 version required a bit effort. The dataset utilized in for schooling the
version in a given technique become a aggregate of numerous open-supply datasets and pictures, which blanketed information
from Kaggle’s Medical Mask Dataset through Mikolaj Witkowski and Prajna Bhandary dataset to be had at PyImage Search.
V. PRE-PROCESSING
There are just a few datasets to be had for the detection of face masks. Most of them are both artificially created, which doesn’t
constitute the actual global accurately, or the dataset is complete of noise and incorrect labels. So, selecting the proper dataset
which might paintings pleasant for the SSDMNV2 version required a touch effort. The dataset utilized in for education the
version in a given technique changed into a aggregate of diverse open-supply datasets and pictures, which blanketed
information from Kaggle’s Medical Mask Dataset with the aid of using Mikolaj Witkowski and Prajna Bhandary dataset to be
had at PyImage Search.
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2944
VI. DATA AUGUMENTATION
For the schooling of SSDMNV2 model, an large amount of facts is essential to carry out schooling efficaciously because of the
non availability of an ok quantity of facts for schooling the proposed model. The technique of facts augmentation is used to
resolve this issue. In this technique, strategies like rotation, zooming, shifting, shearing, and flipping the photo are used for
producing several variations of a comparable photo. In the proposed model, photograph augmentation is used for the facts
augmentation process. A characteristic photograph facts technology is created for photograph augmentation, which returns
take a look at and educate batches of facts.
VII. FACE DETECTION USING OPEN CV -DNN
This version is covered withinside the GitHub repository of OpenCV, beginning from the trendy version. It is installed on the
’Single Shot Multi-container Detector’ (SSD) and uses
‘ResNet-10’ structure because the base-version. The Single Shot Multi-container Detector is just like YOLO approach which
takes simplest one shot to come across a couple of gadgets found in an picture the usage of Multibox. It is appreciably quicker
in velocity and excessive accuracy item detection algorithm. The photos from which the version is traine have now no longer
been disclosed. Two variations of the version are made to be had through OpenCV: i.) Caffe Implementation (Floating factor
sixteen version) ii.) Original TensorFlow Implementation (8-bit quantized version)
VIII. IMPLEMENTATION LANGUAGE
Python is an interpreted, object-oriented, high-stage programming language with dynamic semantics. Its highstage
constructed in facts structures, blended with dynamic typing and dynamic binding, make it very appealing for Rapid
Application Development, in addition to to be used as a scripting or glue language to attach current additives together.
Python's simple, smooth to analyze syntax emphasizes clarity and consequently reduces the fee of application maintenance.
Python helps modules and packages, which inspires application modularity and code reuse. The Python interpreter and the
giant widespread library are to be had in supply or binary shape with out price for all most important platforms, and may be
freely distributed. Here we list basic features that make Python a powerful & popular programming language.
Easy to Code
- Python is very easy to code as compared to other popular languages like Java and C++.
- Anyone can learn Basic Python syntax in just a few hours. Thus, it is programmer-friendly.
Object Oriented
- A programming language that can model the real world is said to be object-oriented. It focuses on objects and
combines data and functions.
- Contrarily, a procedure-oriented language revolves around functions, which are codthat can be reused.
- Python supports both procedure-oriented and object-oriented programming which is one of the key python features.
- It also supports multiple inheritance, unlike Java.
- A class is a blueprint for such an object. It is an abstract data type and holds no values.
IX. TRAIN MODEL
To begin, the libraries needed for the implementation process were imported, including tensorflow, numpy, imutils, keras,
opencv, scipy, and matplotlib. Datasets were also imported using the import technique. Model’s directory has been created and
the path to the dataset folder in the directory. In this area, there is category. Within the category, there are two values: one
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2945
with mask and the other without. Through these two categories, a loop function has been applied.also demonstrates that the
program started with the initial learning rate and then switched to a lower learning rate. Because the learning rate has been
used less than the loss, the loss has been appropriately estimated. As a result, the level of accuracy was high.
X. TESTING
To run the model, the computer’s command prompt was opened and navigated to the location where the relevant training file
was located. The python keyword was typed, followed by the file name train_mask.py, and the enter key was hit to start it.
After that, the training phase of this model started. All the images had to be trained, which took a lengthy time. The “plot.png”
image of the findings was stored in the project folder after the mask detector model was trained. The accuracy and training
loss 29 were plotted. The accuracy and loss have been precisely conveyed. The model appeared to be in good form. The epochs
down were given up to 20 epochs. The model’s functioning performance was excellent, The “plot.png” and mask detector filles
have been saved on the local desk. Face detection was performed using two filles that were downloaded and saved in the face-
detector folder. For the camera operation, OpenCV was used.
XI. CONCLUSION
In the proposed face masks detection version named SSDMNV2, each the education and improvement of the photograph
dataset, which turned into divided into classes of human beings having mask and those now no longer having mask had been
performed effectively. The method of OpenCV deep neural networks used on this version generated fruitful results.
Classification of snap shots turned into performed correctly the use of the MobilenetV2 photograph classifier, that's one of the
specialty of the proposed approach. Many present researches confronted complicated results, whilst a few have been
capable of generate higher accuracy with their dataset. The hassle of numerous incorrect predictions had been effectively
eliminated from the version because the dataset used turned into accrued from numerous different reassets and snap shots
utilized in the Dataset turned into wiped clean manually to boom the accuracy of the results. Real-international programs are a
far greater hard trouble for the approaching future. The SSDMNV2 version ought to with any luck assist the involved
government on this first-rate pandemic scenario which had in large part received roots in maximum of the international;
different researchers can use the dataset supplied on this paper for in addition superior fashions together with the ones of face
recognition, facial landmarks, and facial element detection process.
REFERENCES
[1] D. Biber, S. Conrad, R. Reppen, Corpus Linguistics: Investigating Language Structure and Use, Cambridge University
Press, 1998.
[2] Zunera Jalil, “Copyright Protection of Plain Text Using Digital Watermarking”, submitted at FAST National University of
Computer and Emerging Sciences, Islamabad, Pakistan, 2010.
[3] Sonika Rathi, “Medical Image Authentication through Watermarking Preserving ROI”, submitted at College of
Engineering, Pune, India, 2012.
[4] I. Cox and M. L. Miller, “A review of watermarking and the importance of perceptual modeling”, in Proceedings of SPIE,
Human Vision and Electronic Imaging II, vol. 3016, no. 2, pp. 92-99, 1997.
[5] Ingemar J. Cox, Matt L. Miller and Jeffrey A. Bloom, “Watermarking applications and their properties”, Published in the
Int. Conf. on Information Technology, 2000.

Mais conteúdo relacionado

Semelhante a FACE MASK DETECTION USING ML

Intelligent System For Face Mask Detection
Intelligent System For Face Mask DetectionIntelligent System For Face Mask Detection
Intelligent System For Face Mask DetectionIRJET Journal
 
Face Mask Detection and Face Recognition Using Machine Learning
Face Mask Detection and Face Recognition Using Machine LearningFace Mask Detection and Face Recognition Using Machine Learning
Face Mask Detection and Face Recognition Using Machine LearningIRJET Journal
 
AI-based Mechanism to Authorise Beneficiaries at Covid Vaccination Camps usin...
AI-based Mechanism to Authorise Beneficiaries at Covid Vaccination Camps usin...AI-based Mechanism to Authorise Beneficiaries at Covid Vaccination Camps usin...
AI-based Mechanism to Authorise Beneficiaries at Covid Vaccination Camps usin...IRJET Journal
 
IRJET - Design and Development of Android Application for Face Detection and ...
IRJET - Design and Development of Android Application for Face Detection and ...IRJET - Design and Development of Android Application for Face Detection and ...
IRJET - Design and Development of Android Application for Face Detection and ...IRJET Journal
 
Face Mask Detection using CNN and OpenCV
Face Mask Detection using CNN and OpenCVFace Mask Detection using CNN and OpenCV
Face Mask Detection using CNN and OpenCVIRJET Journal
 
Motion capture for Animation
Motion capture for AnimationMotion capture for Animation
Motion capture for AnimationIRJET Journal
 
ATTENDANCE BY FACE RECOGNITION USING AI
ATTENDANCE BY FACE RECOGNITION USING AIATTENDANCE BY FACE RECOGNITION USING AI
ATTENDANCE BY FACE RECOGNITION USING AIIRJET Journal
 
Review on Arduino-Based Face Mask Detection System
Review on Arduino-Based Face Mask Detection SystemReview on Arduino-Based Face Mask Detection System
Review on Arduino-Based Face Mask Detection SystemIRJET Journal
 
Face Mask Detection utilizing Tensorflow, OpenCV and Keras
Face Mask Detection utilizing Tensorflow, OpenCV and KerasFace Mask Detection utilizing Tensorflow, OpenCV and Keras
Face Mask Detection utilizing Tensorflow, OpenCV and KerasIRJET Journal
 
RETINAL IMAGE CLASSIFICATION USING NEURAL NETWORK BASED ON A CNN METHODS
RETINAL IMAGE CLASSIFICATION USING NEURAL NETWORK BASED ON A CNN METHODSRETINAL IMAGE CLASSIFICATION USING NEURAL NETWORK BASED ON A CNN METHODS
RETINAL IMAGE CLASSIFICATION USING NEURAL NETWORK BASED ON A CNN METHODSIRJET Journal
 
A SURVEY ON DEEPFAKES CREATION AND DETECTION
A SURVEY ON DEEPFAKES CREATION AND DETECTIONA SURVEY ON DEEPFAKES CREATION AND DETECTION
A SURVEY ON DEEPFAKES CREATION AND DETECTIONIRJET Journal
 
Survey on Face Mask Detection with Door Locking and Alert System using Raspbe...
Survey on Face Mask Detection with Door Locking and Alert System using Raspbe...Survey on Face Mask Detection with Door Locking and Alert System using Raspbe...
Survey on Face Mask Detection with Door Locking and Alert System using Raspbe...IRJET Journal
 
A VISUAL ATTENDANCE SYSTEM USING FACE RECOGNITION
A VISUAL ATTENDANCE SYSTEM USING FACE RECOGNITIONA VISUAL ATTENDANCE SYSTEM USING FACE RECOGNITION
A VISUAL ATTENDANCE SYSTEM USING FACE RECOGNITIONIRJET Journal
 
A Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question AnsweringA Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question AnsweringIRJET Journal
 
IRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET Journal
 
IRJET- Face Recognition using Landmark Estimation and Convolution Neural Network
IRJET- Face Recognition using Landmark Estimation and Convolution Neural NetworkIRJET- Face Recognition using Landmark Estimation and Convolution Neural Network
IRJET- Face Recognition using Landmark Estimation and Convolution Neural NetworkIRJET Journal
 
Realtime Face mask Detector using YoloV4
Realtime Face mask Detector using YoloV4Realtime Face mask Detector using YoloV4
Realtime Face mask Detector using YoloV4IRJET Journal
 
Facial Recognition Based Attendance System
Facial Recognition Based Attendance SystemFacial Recognition Based Attendance System
Facial Recognition Based Attendance SystemIRJET Journal
 
FACE MASK DETECTION USING MACHINE LEARNING AND IMAGE PROCESSING
FACE MASK DETECTION USING MACHINE LEARNING AND IMAGE PROCESSINGFACE MASK DETECTION USING MACHINE LEARNING AND IMAGE PROCESSING
FACE MASK DETECTION USING MACHINE LEARNING AND IMAGE PROCESSINGIRJET Journal
 
ML for blind people.pptx
ML for blind people.pptxML for blind people.pptx
ML for blind people.pptxJAYKUMARKABRA
 

Semelhante a FACE MASK DETECTION USING ML (20)

Intelligent System For Face Mask Detection
Intelligent System For Face Mask DetectionIntelligent System For Face Mask Detection
Intelligent System For Face Mask Detection
 
Face Mask Detection and Face Recognition Using Machine Learning
Face Mask Detection and Face Recognition Using Machine LearningFace Mask Detection and Face Recognition Using Machine Learning
Face Mask Detection and Face Recognition Using Machine Learning
 
AI-based Mechanism to Authorise Beneficiaries at Covid Vaccination Camps usin...
AI-based Mechanism to Authorise Beneficiaries at Covid Vaccination Camps usin...AI-based Mechanism to Authorise Beneficiaries at Covid Vaccination Camps usin...
AI-based Mechanism to Authorise Beneficiaries at Covid Vaccination Camps usin...
 
IRJET - Design and Development of Android Application for Face Detection and ...
IRJET - Design and Development of Android Application for Face Detection and ...IRJET - Design and Development of Android Application for Face Detection and ...
IRJET - Design and Development of Android Application for Face Detection and ...
 
Face Mask Detection using CNN and OpenCV
Face Mask Detection using CNN and OpenCVFace Mask Detection using CNN and OpenCV
Face Mask Detection using CNN and OpenCV
 
Motion capture for Animation
Motion capture for AnimationMotion capture for Animation
Motion capture for Animation
 
ATTENDANCE BY FACE RECOGNITION USING AI
ATTENDANCE BY FACE RECOGNITION USING AIATTENDANCE BY FACE RECOGNITION USING AI
ATTENDANCE BY FACE RECOGNITION USING AI
 
Review on Arduino-Based Face Mask Detection System
Review on Arduino-Based Face Mask Detection SystemReview on Arduino-Based Face Mask Detection System
Review on Arduino-Based Face Mask Detection System
 
Face Mask Detection utilizing Tensorflow, OpenCV and Keras
Face Mask Detection utilizing Tensorflow, OpenCV and KerasFace Mask Detection utilizing Tensorflow, OpenCV and Keras
Face Mask Detection utilizing Tensorflow, OpenCV and Keras
 
RETINAL IMAGE CLASSIFICATION USING NEURAL NETWORK BASED ON A CNN METHODS
RETINAL IMAGE CLASSIFICATION USING NEURAL NETWORK BASED ON A CNN METHODSRETINAL IMAGE CLASSIFICATION USING NEURAL NETWORK BASED ON A CNN METHODS
RETINAL IMAGE CLASSIFICATION USING NEURAL NETWORK BASED ON A CNN METHODS
 
A SURVEY ON DEEPFAKES CREATION AND DETECTION
A SURVEY ON DEEPFAKES CREATION AND DETECTIONA SURVEY ON DEEPFAKES CREATION AND DETECTION
A SURVEY ON DEEPFAKES CREATION AND DETECTION
 
Survey on Face Mask Detection with Door Locking and Alert System using Raspbe...
Survey on Face Mask Detection with Door Locking and Alert System using Raspbe...Survey on Face Mask Detection with Door Locking and Alert System using Raspbe...
Survey on Face Mask Detection with Door Locking and Alert System using Raspbe...
 
A VISUAL ATTENDANCE SYSTEM USING FACE RECOGNITION
A VISUAL ATTENDANCE SYSTEM USING FACE RECOGNITIONA VISUAL ATTENDANCE SYSTEM USING FACE RECOGNITION
A VISUAL ATTENDANCE SYSTEM USING FACE RECOGNITION
 
A Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question AnsweringA Literature Survey on Image Linguistic Visual Question Answering
A Literature Survey on Image Linguistic Visual Question Answering
 
IRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric LearningIRJET-Human Face Detection and Identification using Deep Metric Learning
IRJET-Human Face Detection and Identification using Deep Metric Learning
 
IRJET- Face Recognition using Landmark Estimation and Convolution Neural Network
IRJET- Face Recognition using Landmark Estimation and Convolution Neural NetworkIRJET- Face Recognition using Landmark Estimation and Convolution Neural Network
IRJET- Face Recognition using Landmark Estimation and Convolution Neural Network
 
Realtime Face mask Detector using YoloV4
Realtime Face mask Detector using YoloV4Realtime Face mask Detector using YoloV4
Realtime Face mask Detector using YoloV4
 
Facial Recognition Based Attendance System
Facial Recognition Based Attendance SystemFacial Recognition Based Attendance System
Facial Recognition Based Attendance System
 
FACE MASK DETECTION USING MACHINE LEARNING AND IMAGE PROCESSING
FACE MASK DETECTION USING MACHINE LEARNING AND IMAGE PROCESSINGFACE MASK DETECTION USING MACHINE LEARNING AND IMAGE PROCESSING
FACE MASK DETECTION USING MACHINE LEARNING AND IMAGE PROCESSING
 
ML for blind people.pptx
ML for blind people.pptxML for blind people.pptx
ML for blind people.pptx
 

Mais de IRJET Journal

TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...IRJET Journal
 
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURESTUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTUREIRJET Journal
 
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...IRJET Journal
 
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsEffect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsIRJET Journal
 
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...IRJET Journal
 
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...IRJET Journal
 
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...IRJET Journal
 
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...IRJET Journal
 
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASA REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASIRJET Journal
 
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...IRJET Journal
 
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProP.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProIRJET Journal
 
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemSurvey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemIRJET Journal
 
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesReview on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesIRJET Journal
 
React based fullstack edtech web application
React based fullstack edtech web applicationReact based fullstack edtech web application
React based fullstack edtech web applicationIRJET Journal
 
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...IRJET Journal
 
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.IRJET Journal
 
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...IRJET Journal
 
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignMultistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignIRJET Journal
 
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...IRJET Journal
 
Solving Linear Differential Equations with Constant Coefficients
Solving Linear Differential Equations with Constant CoefficientsSolving Linear Differential Equations with Constant Coefficients
Solving Linear Differential Equations with Constant CoefficientsIRJET Journal
 

Mais de IRJET Journal (20)

TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
 
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURESTUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
 
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
 
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsEffect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil Characteristics
 
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
 
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
 
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
 
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
 
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASA REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADAS
 
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
 
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProP.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
 
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemSurvey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare System
 
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesReview on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridges
 
React based fullstack edtech web application
React based fullstack edtech web applicationReact based fullstack edtech web application
React based fullstack edtech web application
 
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
 
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
 
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
 
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignMultistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
 
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
 
Solving Linear Differential Equations with Constant Coefficients
Solving Linear Differential Equations with Constant CoefficientsSolving Linear Differential Equations with Constant Coefficients
Solving Linear Differential Equations with Constant Coefficients
 

Último

UNIT4_ESD_wfffffggggggggggggith_ARM.pptx
UNIT4_ESD_wfffffggggggggggggith_ARM.pptxUNIT4_ESD_wfffffggggggggggggith_ARM.pptx
UNIT4_ESD_wfffffggggggggggggith_ARM.pptxrealme6igamerr
 
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...Sean Meyn
 
IT3401-WEB ESSENTIALS PRESENTATIONS.pptx
IT3401-WEB ESSENTIALS PRESENTATIONS.pptxIT3401-WEB ESSENTIALS PRESENTATIONS.pptx
IT3401-WEB ESSENTIALS PRESENTATIONS.pptxSAJITHABANUS
 
Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Bahzad5
 
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdfRenewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdfodunowoeminence2019
 
Power System electrical and electronics .pptx
Power System electrical and electronics .pptxPower System electrical and electronics .pptx
Power System electrical and electronics .pptxMUKULKUMAR210
 
Dev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingDev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingMarian Marinov
 
Engineering Mechanics Chapter 5 Equilibrium of a Rigid Body
Engineering Mechanics  Chapter 5  Equilibrium of a Rigid BodyEngineering Mechanics  Chapter 5  Equilibrium of a Rigid Body
Engineering Mechanics Chapter 5 Equilibrium of a Rigid BodyAhmadHajasad2
 
Nodal seismic construction requirements.pptx
Nodal seismic construction requirements.pptxNodal seismic construction requirements.pptx
Nodal seismic construction requirements.pptxwendy cai
 
ChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai searchChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai searchrohitcse52
 
Design of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxDesign of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxYogeshKumarKJMIT
 
Phase noise transfer functions.pptx
Phase noise transfer      functions.pptxPhase noise transfer      functions.pptx
Phase noise transfer functions.pptxSaiGouthamSunkara
 
How to Write a Good Scientific Paper.pdf
How to Write a Good Scientific Paper.pdfHow to Write a Good Scientific Paper.pdf
How to Write a Good Scientific Paper.pdfRedhwan Qasem Shaddad
 
Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...sahb78428
 
ASME BPVC 2023 Section I para leer y entender
ASME BPVC 2023 Section I para leer y entenderASME BPVC 2023 Section I para leer y entender
ASME BPVC 2023 Section I para leer y entenderjuancarlos286641
 
GENERAL CONDITIONS FOR CONTRACTS OF CIVIL ENGINEERING WORKS
GENERAL CONDITIONS  FOR  CONTRACTS OF CIVIL ENGINEERING WORKS GENERAL CONDITIONS  FOR  CONTRACTS OF CIVIL ENGINEERING WORKS
GENERAL CONDITIONS FOR CONTRACTS OF CIVIL ENGINEERING WORKS Bahzad5
 
Mohs Scale of Hardness, Hardness Scale.pptx
Mohs Scale of Hardness, Hardness Scale.pptxMohs Scale of Hardness, Hardness Scale.pptx
Mohs Scale of Hardness, Hardness Scale.pptxKISHAN KUMAR
 
Modelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsModelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsYusuf Yıldız
 

Último (20)

UNIT4_ESD_wfffffggggggggggggith_ARM.pptx
UNIT4_ESD_wfffffggggggggggggith_ARM.pptxUNIT4_ESD_wfffffggggggggggggith_ARM.pptx
UNIT4_ESD_wfffffggggggggggggith_ARM.pptx
 
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
Quasi-Stochastic Approximation: Algorithm Design Principles with Applications...
 
IT3401-WEB ESSENTIALS PRESENTATIONS.pptx
IT3401-WEB ESSENTIALS PRESENTATIONS.pptxIT3401-WEB ESSENTIALS PRESENTATIONS.pptx
IT3401-WEB ESSENTIALS PRESENTATIONS.pptx
 
Lecture 4 .pdf
Lecture 4                              .pdfLecture 4                              .pdf
Lecture 4 .pdf
 
Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)Lecture 1: Basics of trigonometry (surveying)
Lecture 1: Basics of trigonometry (surveying)
 
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdfRenewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
Renewable Energy & Entrepreneurship Workshop_21Feb2024.pdf
 
Power System electrical and electronics .pptx
Power System electrical and electronics .pptxPower System electrical and electronics .pptx
Power System electrical and electronics .pptx
 
Dev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & LoggingDev.bg DevOps March 2024 Monitoring & Logging
Dev.bg DevOps March 2024 Monitoring & Logging
 
Engineering Mechanics Chapter 5 Equilibrium of a Rigid Body
Engineering Mechanics  Chapter 5  Equilibrium of a Rigid BodyEngineering Mechanics  Chapter 5  Equilibrium of a Rigid Body
Engineering Mechanics Chapter 5 Equilibrium of a Rigid Body
 
Nodal seismic construction requirements.pptx
Nodal seismic construction requirements.pptxNodal seismic construction requirements.pptx
Nodal seismic construction requirements.pptx
 
ChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai searchChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai search
 
Design of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptxDesign of Clutches and Brakes in Design of Machine Elements.pptx
Design of Clutches and Brakes in Design of Machine Elements.pptx
 
Phase noise transfer functions.pptx
Phase noise transfer      functions.pptxPhase noise transfer      functions.pptx
Phase noise transfer functions.pptx
 
How to Write a Good Scientific Paper.pdf
How to Write a Good Scientific Paper.pdfHow to Write a Good Scientific Paper.pdf
How to Write a Good Scientific Paper.pdf
 
Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...Clutches and brkesSelect any 3 position random motion out of real world and d...
Clutches and brkesSelect any 3 position random motion out of real world and d...
 
ASME BPVC 2023 Section I para leer y entender
ASME BPVC 2023 Section I para leer y entenderASME BPVC 2023 Section I para leer y entender
ASME BPVC 2023 Section I para leer y entender
 
計劃趕得上變化
計劃趕得上變化計劃趕得上變化
計劃趕得上變化
 
GENERAL CONDITIONS FOR CONTRACTS OF CIVIL ENGINEERING WORKS
GENERAL CONDITIONS  FOR  CONTRACTS OF CIVIL ENGINEERING WORKS GENERAL CONDITIONS  FOR  CONTRACTS OF CIVIL ENGINEERING WORKS
GENERAL CONDITIONS FOR CONTRACTS OF CIVIL ENGINEERING WORKS
 
Mohs Scale of Hardness, Hardness Scale.pptx
Mohs Scale of Hardness, Hardness Scale.pptxMohs Scale of Hardness, Hardness Scale.pptx
Mohs Scale of Hardness, Hardness Scale.pptx
 
Modelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovationsModelling Guide for Timber Structures - FPInnovations
Modelling Guide for Timber Structures - FPInnovations
 

FACE MASK DETECTION USING ML

  • 1. © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2942 FACE MASK DETECTION USING ML Prof .V.O.Patil, Darshana Rajendra Javheri, Neha Vinod Patil, Aditi Sanjay Jaiswal 1Assistant Professor at Department of Computer Engineering, PSGVP Mandal’s D.N.Patel College of Engineering, Shahada, Maharashtra, India 2Final Year Students of Department of Computer Engineering, PSGVP Mandal’s D.N.Patel College of Engineering, Shahada, Maharashtra, India ------------------------------------------------------------------***--------------------------------------------------------------------------- Abstract- As we all know COVID-19 pandemic has rapidly affected our day-to-day life disrupting the world trade and movements. So wearing a mask, wearing a protective face mask is become the new normal. However, still have few ways to control the outbreak as instructed by the WHO (World Health Organization).Hence Using Face Mask Detection System, one can monitor if the people are wearing masks or not. This project presents a simplified approach to achieve this purpose using some basic Machine Learning packages like TensorFlow, Keras, Open, CV and Scikit-Learn. There are a few processes involved in achieving the objective of the project that includes pre-processing, data augmentationn, training ,testing, and image segmentation. The method attains accuracy up to 95.77 percent and 94.58 percent respectively on two different datasets. Keywords- Tenserflow, openCV, Keras, Numpy, Scikit-Learn. I. INTRODUCTION COVID-19 pandemic has had an enduring effect in many nations global due to the fact that December 2019. It originated in Wuhan, China. The World Health Organization (WHO) as of March 11, 2020, declared it a pandemic that received its roots throughout the globe and critically affected 114 countries. Every clinical professional, healthcare organizations, clinical practitioners, and researchers are searching for right vaccines and drugs to conquer this lethal disease, but no leap forward has been stated until date. The virus spreads thru air channel whilst an inflamed man or woman sneezes or talk with the alternative man or woman, the water droplets from their nostril or mouth disseminate thru the air and have an effect on different peoples withinside the vicinity (Kumar et al., 2020). Face Mask detection has turn out to be a trending software because of the Covid-19 pandemic, which needs someone to put on face masks, maintain social distancing, and use hand sanitizers to scrub their hands. While different issues of social distancing and sanitization were addressed till now, the problem of face masks detection has now no longer but been accurately addressed. Wearing a masks all through this pandemic is a essential safety measure and is maximum crucial step in instances whilst social distancing is tough to maintain. Face Mask detection has became as much as be an outstanding hassle withinside the area of photograph processing and pc vision. Face detection has diverse use instances starting from face popularity to shooting facial motions, in which the latter requires the face to be discovered with very excessive precision. Due to the speedy development withinside the area of device gaining knowledge of algorithms, the jeopardies of face masks detection era appear to be properly addressed yet. This era is extra applicable these days because it is used to detect faces not only in static images and videos but also in real-time inspection and supervision. II. LITURATURE SURVEY In the latest past, diverse researchers and analysts specifically targeted on gray-scale face image. While a few had been absolutely constructed on sample identity models, owning preliminary facts of the face version whilst others had been the use of AdaBoost, which changed into an fantastic classifier for schooling purposes. Then got here the Viola-Jones Detector, which supplied a leap forward in face detection technology, and real-time face detection were given possible. It confronted diverse issues just like the orientation and brightness of the face, making it tough to intercept. So basically, it did not paintings in stupid and dim light. Thus, researchers began out looking for a brand new opportunity version that might effortlessly discover faces in addition to mask at the face. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072
  • 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2943 III. METHODOLOGY To are expecting whether or not someone has worn a masks correctly, the preliminary degree might be to educate the version the usage of a right dataset. After education the classifier, an correct face detection version is needed to come across faces, in order that the SSDMNV2 version can classify whether or not the man or woman is carrying a masks or not. The mission on this paper is to elevate the accuracy of masks detection with out being too resource-heavy. For doing this mission, the DNN module become used from OpenCV, which incorporates a ‘Single Shot Multibox Detector’ (SSD) item detection version with ResNet-10 as its spine architecture. This technique enables in detecting faces in real-time, even on embedded gadgets like Raspberry Pi. The following classifier makes use of a pre-educated version MobileNetV2 to are expecting whether or not the man or woman is carrying a masks or not. IV. DATASET USED There are just a few datasets to be had for the detection of face masks. Most of them are both artificially created, which doesn’t constitute the actual international accurately, or the dataset is complete of noise and incorrect labels. So, selecting the proper dataset which might paintings nice for the SSDMNV2 version required a bit effort. The dataset utilized in for schooling the version in a given technique become a aggregate of numerous open-supply datasets and pictures, which blanketed information from Kaggle’s Medical Mask Dataset through Mikolaj Witkowski and Prajna Bhandary dataset to be had at PyImage Search. V. PRE-PROCESSING There are just a few datasets to be had for the detection of face masks. Most of them are both artificially created, which doesn’t constitute the actual global accurately, or the dataset is complete of noise and incorrect labels. So, selecting the proper dataset which might paintings pleasant for the SSDMNV2 version required a touch effort. The dataset utilized in for education the version in a given technique changed into a aggregate of diverse open-supply datasets and pictures, which blanketed information from Kaggle’s Medical Mask Dataset with the aid of using Mikolaj Witkowski and Prajna Bhandary dataset to be had at PyImage Search.
  • 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2944 VI. DATA AUGUMENTATION For the schooling of SSDMNV2 model, an large amount of facts is essential to carry out schooling efficaciously because of the non availability of an ok quantity of facts for schooling the proposed model. The technique of facts augmentation is used to resolve this issue. In this technique, strategies like rotation, zooming, shifting, shearing, and flipping the photo are used for producing several variations of a comparable photo. In the proposed model, photograph augmentation is used for the facts augmentation process. A characteristic photograph facts technology is created for photograph augmentation, which returns take a look at and educate batches of facts. VII. FACE DETECTION USING OPEN CV -DNN This version is covered withinside the GitHub repository of OpenCV, beginning from the trendy version. It is installed on the ’Single Shot Multi-container Detector’ (SSD) and uses ‘ResNet-10’ structure because the base-version. The Single Shot Multi-container Detector is just like YOLO approach which takes simplest one shot to come across a couple of gadgets found in an picture the usage of Multibox. It is appreciably quicker in velocity and excessive accuracy item detection algorithm. The photos from which the version is traine have now no longer been disclosed. Two variations of the version are made to be had through OpenCV: i.) Caffe Implementation (Floating factor sixteen version) ii.) Original TensorFlow Implementation (8-bit quantized version) VIII. IMPLEMENTATION LANGUAGE Python is an interpreted, object-oriented, high-stage programming language with dynamic semantics. Its highstage constructed in facts structures, blended with dynamic typing and dynamic binding, make it very appealing for Rapid Application Development, in addition to to be used as a scripting or glue language to attach current additives together. Python's simple, smooth to analyze syntax emphasizes clarity and consequently reduces the fee of application maintenance. Python helps modules and packages, which inspires application modularity and code reuse. The Python interpreter and the giant widespread library are to be had in supply or binary shape with out price for all most important platforms, and may be freely distributed. Here we list basic features that make Python a powerful & popular programming language. Easy to Code - Python is very easy to code as compared to other popular languages like Java and C++. - Anyone can learn Basic Python syntax in just a few hours. Thus, it is programmer-friendly. Object Oriented - A programming language that can model the real world is said to be object-oriented. It focuses on objects and combines data and functions. - Contrarily, a procedure-oriented language revolves around functions, which are codthat can be reused. - Python supports both procedure-oriented and object-oriented programming which is one of the key python features. - It also supports multiple inheritance, unlike Java. - A class is a blueprint for such an object. It is an abstract data type and holds no values. IX. TRAIN MODEL To begin, the libraries needed for the implementation process were imported, including tensorflow, numpy, imutils, keras, opencv, scipy, and matplotlib. Datasets were also imported using the import technique. Model’s directory has been created and the path to the dataset folder in the directory. In this area, there is category. Within the category, there are two values: one
  • 4. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 06 | June 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2945 with mask and the other without. Through these two categories, a loop function has been applied.also demonstrates that the program started with the initial learning rate and then switched to a lower learning rate. Because the learning rate has been used less than the loss, the loss has been appropriately estimated. As a result, the level of accuracy was high. X. TESTING To run the model, the computer’s command prompt was opened and navigated to the location where the relevant training file was located. The python keyword was typed, followed by the file name train_mask.py, and the enter key was hit to start it. After that, the training phase of this model started. All the images had to be trained, which took a lengthy time. The “plot.png” image of the findings was stored in the project folder after the mask detector model was trained. The accuracy and training loss 29 were plotted. The accuracy and loss have been precisely conveyed. The model appeared to be in good form. The epochs down were given up to 20 epochs. The model’s functioning performance was excellent, The “plot.png” and mask detector filles have been saved on the local desk. Face detection was performed using two filles that were downloaded and saved in the face- detector folder. For the camera operation, OpenCV was used. XI. CONCLUSION In the proposed face masks detection version named SSDMNV2, each the education and improvement of the photograph dataset, which turned into divided into classes of human beings having mask and those now no longer having mask had been performed effectively. The method of OpenCV deep neural networks used on this version generated fruitful results. Classification of snap shots turned into performed correctly the use of the MobilenetV2 photograph classifier, that's one of the specialty of the proposed approach. Many present researches confronted complicated results, whilst a few have been capable of generate higher accuracy with their dataset. The hassle of numerous incorrect predictions had been effectively eliminated from the version because the dataset used turned into accrued from numerous different reassets and snap shots utilized in the Dataset turned into wiped clean manually to boom the accuracy of the results. Real-international programs are a far greater hard trouble for the approaching future. The SSDMNV2 version ought to with any luck assist the involved government on this first-rate pandemic scenario which had in large part received roots in maximum of the international; different researchers can use the dataset supplied on this paper for in addition superior fashions together with the ones of face recognition, facial landmarks, and facial element detection process. REFERENCES [1] D. Biber, S. Conrad, R. Reppen, Corpus Linguistics: Investigating Language Structure and Use, Cambridge University Press, 1998. [2] Zunera Jalil, “Copyright Protection of Plain Text Using Digital Watermarking”, submitted at FAST National University of Computer and Emerging Sciences, Islamabad, Pakistan, 2010. [3] Sonika Rathi, “Medical Image Authentication through Watermarking Preserving ROI”, submitted at College of Engineering, Pune, India, 2012. [4] I. Cox and M. L. Miller, “A review of watermarking and the importance of perceptual modeling”, in Proceedings of SPIE, Human Vision and Electronic Imaging II, vol. 3016, no. 2, pp. 92-99, 1997. [5] Ingemar J. Cox, Matt L. Miller and Jeffrey A. Bloom, “Watermarking applications and their properties”, Published in the Int. Conf. on Information Technology, 2000.