of Application for Detection of Face Mask and Social Distancing During Covid-19 using CNN and Yolo v3
Studycomprisesof3modules facedetection,maskdetection, and social distance detection. YOLO (You Only Look Once) algorithm is used for Object Detection as well as Object Tracking, because of its highest accuracy and precision achieved to date amongst prevalent techniques. It detects the people and their faces in the frame for counting the objects and keeps a record of those objects in the next frame using Object Tracking.
Thepandemichasbroughtusalotofchallenges,especially in the working patterns.[1] Along with Covid 19, several otherlarge scale,seriousrespiratorydiseases,suchasSARS andMERS,emerged,addingtothepandemic'schaos.
Using Deep learning and OpenCV, a CNN model will be generatedformaskdetection[5] Facemaskswillbedetected usingpredictiveanalysisonbothstaticimagesandvideos. Asaresult,thissystemwillautomatetheprocessofchecking uponcitizens,assistingthegovernmentinenforcingCOVID 19 rules and regulations which will significantly reduce numberofCovidcases 1.1 YOLO v3 YolostandsforYouonlylookonce.Itdetectsobjectsusing CNN.Itcandetectnumerousobjectsinanimage. Itpredicts not only the class of the object but also its location in the image.Fortheobjectdetectiontask,Yoloversion3employs aneuralnetworkof53CNN's(Darknet 53)andanadditional 53layers,totaling106layers.
Designing
Gaurav Garje1, Rasika Lande2, Shardul Shinde3, Nishant Inamdar4 , Prof. A.S.Deokar5 1,2,3,4Undergraduate Students, Dept. of Computer Engineering, AISSMS COE, Pune, Maharashtra, India 5Professor, Dept. of Computer Engineering, AISSMS COE, Pune, Maharashtra, India ***
Abstract
The custom MAFA dataset is used to understand facemasks
Key Words: Covid-19, Object Detection, Object Tracking, Distance Estimation, MAFA, CNN, YOLO v3, Open CV
1.INTRODUCTION
International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056 Volume: 09 Issue: 01 | Jan 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page1352
In2020,theWorldHealthOrganizationrecommendedthat people must wear masks to avoid infection by a novel coronavirus and maintain a social distance of at least 3 meters between themselves to prevent the virus's proliferationandspread.
Current work presents the study of machine learning algorithms for a face mask and social distance detection at crowded places during the pandemic. It suggests a system architecture that supports functions like detecting whether people are wearing masks (partially/completely) and identifying whether they are following social distancing.
People are more conscious about their wellbeing, and governments are placing a greater emphasis on public health. The virus's next wave has begun, but people have continuedtocongregateincrowdedplaceswithoutwearing amask.Thegovernmenthasbeenunabletomaintaincontrol over the situation, triggering the need for artificial intelligenceandcomputertechnologytosolvethisproblem. Distancingoneselffromothersandwearingmaskshelpto slow the disease transmission. Theresearchers believe in developingasurveillancesystemthatmakesuseofexisting IPandCCTVcameras,aswellasComputerVisionandObject Detection algorithms, to identify people who are violating Covid Currentnorms.[5]research work comprises of 2 stages, namely designingaframeworkfordetectionoffacemaskandsocial distancingwiththehelpofCNNandYolov3andinthenext partapplicationwillbedeveloped. Thisresearchunderstandsvariousaspectsoftheimageor videos basedonframesthosewould be madeavailable as inputstothealgorithms.[3]TheObjectDetectionalgorithm YOLOv3willbeusedtofindpeopleinaframe. Thedistancebetweenpeopleintheimagewillbecalculated by the system using the Euclidean distance between the centroids of the detected boxes around the faces in the images. The six most important characteristics of masked faces are face locations, face orientation, eyes, masks, occlusiondegree,andmasktype.Thesewillbeconsidered whilecreatingthemodel.
The CNN (Convolutional neural network) Algorithm will be usedtotrainthe modelonthosedatasetsforclassificationand detection. Implementation of the application will be done in python and efficiency and accuracy are calculated. A unmasked,isnotificationissentiftheseparationbetweenthetwoentitiesbelowthestandardspecifications.Faces,bothmaskedandarelabelledappropriately.
The aftermath of the Covid 19 pandemic has ushered in a new normal, forcing numerous unavoidable changes in social life around the world. Wearing a face mask and maintaining social distance, especially in crowded settings, was made compulsory by the government, some disobeyed the orders, resulting in a rise in covid cases.
Yoloversion3usesninedefaultanchorboxesateachofthe threenetworklocationstopredictboundingboxes.Yolov3 calculatesoffsetstopredefinedanchorsandpredictscenter coordinates by passing the output through the sigmoid functiontopredicttherealwidthandheightofthebounding box. Finally, the final output is determined by the 'intersectionoverunion'ofthesethreeboundingboxes.
Thenetworkreceivesinputintheformofabatchofimages withtheshape(n,w,h,3),wherenisthenumberofimages,w andharetheimage'swidthandheight(multiplesof32),and 3istheRGBchannel.
Yolo version 3 is a three scale detection algorithm, with detection occurring at three different layers of the CNN: layer 82, layer 94, and layer 106. The network down samples the input image by 32,16, and 8 strides of the networkateachofthesepoints. Ateachoftheselocations,1by1convolutionisappliedto downsampledoutputs.(seeFig 1)
2. RELATED WORK
ObjectfromanimageisidentifiedbyCNN.First,theimage's pixelsarefedasinput,andthentheinputlayeracceptsthe image'spixelsasinput Hidden layers extract features by conducting specific calculationsandtransformations.Todetectpatternsinthe image, this layer employs a matrix filter and convolution operations.Finally,theobjectintheimageisidentifiedbya fully connected layer. Convolutional neural network is a feed forwardneuralnetworkthatprocessesdatainagrid liketopologytoanalysesvisualimages.Convolutionlayers, ReLulayers,thefullyconnectedlayer,andthePoolinglayer are the four Hidden Layers. Convolution is the process of coilingortwistingdataandalteringittofindanewpattern. Convolutionoperationsarecarriedoutbyseveralfiltersin theconvolutionlayer.Thenextstepistomovethemapsand featurestotheReLulayeraftertheyhavebeenextracted. MultipleconvolutionsandaRelulayerareusedtoscanthe real image and locate features. The rectified feature map nowtravelsviaapoolinglayer(vastinformationisreduced to a single response).Pooling is a down sampling process thatdecreasesthefeaturemap’sdimensionality.Thepooling layeremploysmanyfilterstoidentifyvariousaspectsofan image,suchasborders,corners,body,andsoon. From a parallel pooled featured map, a single long continuous linear vector is generated by flattening the resulting2Darrays.Thefullyconnectedlayerreceivesthe flattenedmatrixfromthepoolinglayerasinputtoidentify theimage.(SeeFig 2)[15]
[1]“AutomatedevaluationofCOVID 19riskfactorscoupled with real time, indoor, personal localization data for potential disease identification, prevention and smart quarantining” by J. Barabas, R.Zalman and M. Kochlan. To lowerCOVID 19spread,automatedsystemswithsanitary, temperaturemeasurement,individualizedpersontracking, andexaminingisnecessary.Thisisimportantnotonlyfor disease surveillance but also for disease intervention. A system is proposed that incorporates all the component’s functionalitybasedoneasilyavailablecomponentsincluding temperature and mask detection module further strengthened with preliminary RTLS (hardware and Thissoftware).helps in data collection, allowing for post symptom detectionandidentificationofpersoninteractionstoassess theriskofinfectionvectorsandtakefurtherprecautions.
[2]"Multi angleHeadPoseClassificationwhenWearingthe MaskforFaceRecognitionundertheCOVID 19Coronavirus Epidemic,” by Shuang Li, Xin Ning, Lina Yu, Liping Zhang, XiaoliDong,YuanShi,WeiHe.Headposeclassificationisa preprocessing technique applied prior to the face recognitionbecauseitrequiresa frontfacinginputimage. Hence, a new method called HGL is proposed which combines H channel of HSV (Hue Saturation Vue) with grayscaleimageofface.CNNisusedtotrainthismodelfor featureextraction.Thisapproachisadvantageoustoothers intermsofaccuracy.
Yoloversion3calculatesthreeboundingboxesforeachcell of these feature maps, with variousattributes for each boundingbox.Thecentercoordinates(abscissa,ordinate), boundingboxdimensions(width,height),objectnessscore, and a list of confidence classes to which the object may belongareamongtheseattributes.
Thisneuralnetworkdividesimagesintoregionsandassigns cellprobabilitiestoeachofthem. Yolo estimates the number of bounding boxes needed to coverspecificareasoftheimageandchoosesthebestones basedonprobabilities.
[3] “A review of the prevalent ICT techniques used for COVID 19SOPviolationdetection"byTalhaIkram,Abdullah Saeed, Noor Ul Ayn, Muhammad Ali Tahir, Rafia Mumtaz. Thissurveypaperaddressesthemostcommonmethodsfor detecting violations of government mandated covid 19 standardoperatingprocedures.Itusescomputervisionand deeplearningalgorithmsforobjectdetectionanddistance estimation. The research provides a new method for operating the system on non GPU based machines while keepingtheframeraterespectable.
[4]"CNN Based COVID 19 Prevention System" by Deepalaxmi R Shenvi, Krishnananda Shet. The Artificial
1.2 CNN Neuralnetworkssimulatethebehaviorofthehumanbrain in the application areas of Artificial Intelligence, machine learning,anddeeplearning,allowingcomputerprogramsto recognizepatternsandsolvecommonproblems.
Certified Journal | Page1353
International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056 Volume: 09 Issue: 01 | Jan 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008
ThevulnerabilityofexistingDLapplicationstoAEattacks has been realized, necessitating additional research, attention, and installation of proper security mechanisms, safeguards, and controls before these applications are employedinreal worldhealthcaresettings.
[9] "Diagnosing COVID 19: The Disease and Tools for Detection" by Buddhisha Udugama, Pranav Kadhiresan, HannahN.Kozlowski,AydenMalekjahani,MatthewOsborne, VanessaY.C.Li,HongminChen,SamiraMubareka,Jonathan B.Gubbay,andWarrenC.W.Chan. This survey paper proposes the plug and play design of COVD 19 diagnostics. To screen and identify covid 19, an integration of computed tomography imaging, whole genomesequencing,andelectronmicroscopywasinitially used.Thegeneralintentofthisstudyistoeducatethereader ondiagnosticandsurveillancetechnologiesforcovid 19,as wellastheirperformancecharacteristics. The proposed study describes upcoming point of care diagnostics and encourages academics to take theirtechnologiesbeyond conception. Creating plug and playscreeningteststomanagetheCOVIDoutbreakwouldbe beneficialinpreventingfutureoutbreaks.
[8]"DetectionofRespiratoryInfectionsusingRGB infrared sensors on Portable Device" by Zheng Jiang, Menghan Hu, Zhongpai Gao, Lei Fan, Ranran Dai, Yaling Pan, Wei Tang, GuangtaoZhai,andYongLu. This study proposes a portable non contact method for examiningthehealthofpeoplewearingprotectivemasksby assessing respiratory characteristics from RGB infrared sensors.Thesystemusesfacerecognitiontocapturethose whoarewearingmasks.
[11] “Explainable AI and Mass Surveillance System based HealthcareFrameworktoCombatCOVID 19likePandemics” by Nadra Guzeni, M. Shamim Hussain and Ghulam Mohammad.
International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056 Volume: 09 Issue: 01 | Jan 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page1354
[7] "AdversarialExamples SecurityThreatstoCOVID 19 Deep Learning Systems in Medical IoT Devices" by Md. AbdurRahman,M.ShamimHossain,NabilA.Alrajeh,Fawaz TheAlsolami.study
[10]“ExperimentalInvestigationsonParticleContamination of Masks Without Protective Pellicles During Vibration or Shipping of Mask Carriers” by Se Jin Yook, Heinz Fissan, ChristofAsbach,JungHyeunKim,DabrinaD.Dutcher,Pei YangYan,andDavidY.H.Pui.
COVID 19 using Smartphone Embedded Sensors: Design Study" by Halgurd S. Maghdid, Kayhan Zrar Ghafoor, Ali Safaa Sadiq, Kevin Curran, Danda B. Rawat, Khaled Rabie. TheresearchersofferanewmethodfordetectingCOVID 19 usingsmartphonesensorsinthisstudy.
SincepelliclescannotbeusedtoprotectEUVCmasksdueto highEUVabsorption,particle freehandlingisachallengein EUVlithography.Here,toholdamask,twoshippingmask carriermodelswith16supportsareused.Onlineandoffline particledetectionmethodswereimplemented. For detection of Particles, Surface particle detection and toandprotectiveforairborneparticledetectionmethodsareused.Somemethodstestingparticlecontaminationofmaskswithoutpelliclesincludemanualshaking,realshipping,controlledvibration.Theparticlesizeinthispaperisup60nmPSLequivalentsize.
looked at nine COVID 19 deep learning applicationsthatcandiagnosethevirusquickly.Theyputsix open sourceapplicationstothetestandwatchedthemodels closelytocreateadversarialcasesforeachtypeandpinpoint theflawsinmodel.
Intelligent IoT system proposed in the research paper includestemperaturemonitoring,autosanitizing,andmask detection.ARaspberryPi4modelwith2GBofRAMhasbeen used in the proposed system. Face recognition has been performed using the RMFRD Dataset. Keras is a Python librarythatmakesartificialneuralnetworkseasiertouse. This system detects masks with a 98 % accuracy rate. A comparisonoftheaforementionedprocesseswithprevious researchisalsoincludedinthepaper.
[5] “Study of Masked Face Detection Approach in Video Analytics” by Gayatri Deore, Ramakrishna Bodhula, Dr. Vishwas Udpikar, Prof. Vidya More. This paper focuses mainly on security using video analytics which improves video surveillance systems and hence it saves human resources and performance of such systems is also improved.Calculatingdistancefromcamera,linedetection, facialpartdetection,andeyedetectionarethefourstepsin the masked face detection technique used in this paper. These steps are useful in finding if a person is wearing a maskornot.Herelinedetectionandeyedetectioncangive somefalsedetectionsastheirdetectionisnotthataccurate inpoorresolutionimages.
[6]"ANovelAI enabledFrameworktoDiagnoseCoronavirus
When compared to other clinical methods of COVID 19 detection, such as CT scans and blood tests, the proposed method is more convenient and cost effective. These hardware devices like fingerprint sensor, microphone, camera and inertial sensor are employed to analyze the patient'scondition To assess whether a patient is COVID 19 positive or negative, the proposed approach uses machine learning techniques,RNNandCNN.
TheinformationpassesthroughabidirectionalGRUneural networkwithanattentionmechanism.Theaccuracyofthe proposedmethodis83.69percent,withasensitivityof90.23 percentandaspecificityof76.31percent.
The MAFA dataset is utilized to identify masked faces. Benchmark datasets are a grouping of datasets of varying sizesthatrepresentreal worlddatasciencescenarios.
Maskedfaceimagesalsodifferinfaceanglesanddegreesof Theocclusion.significantidentifiedfeaturesofmaskedfacesconsistof faceorientation,eyes,facelocation,occlusiondegree,masks, andmasktypes
4. ARCHITECTURE
With the help of 5Gtechnologyand a network of wireless connectivityCOVID19canbemanagedeasily.Thiscanbe done via hierarchical edge computing which enables scalability,verylowlatency.Furthermore,thedeeplearning algorithm has two drawbacks: one is the need for a large amount of dataset, and the other is the need for acknowledgementandclarificationbythehealthcaresector inorderfortheresultstobeaccepted.
Notableofferingsbytwodistinctcontributors,thecurrent activitystatusofMAFAdatasetconsistsof7150views,1239 downloads,anda0.17downloadperviewratio
ThesystemwillusecontinuousvideofootagefromtheIPor CCTVcameraasinput.Imagesarecreatedbyprocessingthis videofootageframebyframe. The system will identify the persons’ faces, masks, and variousattributes.TheEuclideandistancebetweenthefaces will be calculated using the centroid of a rectangular box formedaroundeachoftheface.Iftherearemorethanthree faces in that detection and the calculated distance is less than the prescribed standards, a notification is sent indicatingabsenceofsocialdistance.(SeeFig 3)
Fig 3: ProposedSystemArchitecture Featureswillbeextractedfromthoseimages,regardlessof theiranglesorscales.TheYolov3algorithmwouldbeused toaccomplishthis.
International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056 Volume: 09 Issue: 01 | Jan 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified 1355
This paper proposes B5G tech which can detect COVID symptomsusingCTscanandchestX rayimages.Also,deep learning models like ResNet, Deep tree and Inception v3 along with blockchain technology are analyzed to provide securityofdata.
Fig 1:YoloV3architecture Fig 2:ConvolutionalNeuralNetwork
3. MAFADATASETSDATA:
Mafahas35,806disguisedfacesand30,811photos.
Journal | Page
[12]“MASKR CNNforPedestrianCrosswalkDetectionand InstanceSegmentation”byMonArjayMalbog.MaskR CNN, whichisbasedondeepconvolutionalnetworks(CNN)isan object detection model which is used for pedestrian Incrosswalk.thispaper,forvalidationpurposealmost500pedestrian crosswalkimageswereused.Inthis,80%oftheimagesare usedforthetrainingsetwhile20%isusedforthevalidation set. Mask R CNN is a two step process that begins with (RPN)RegionProposalNetworkandendswithclassandbox offsetprediction.Itincludesdatagathering,Annotationand Construction of data set, Training the Model and Mask R CNNdetectionmodel.
5. EVALUATION METHODS
7. FUTURE SCOPE
Infurtherresearch,anapplicationwillbedevelopedthatwill detect whether someone is wearing a mask and will also identifywhetherpeoplearemaintainingsocialdistance.Ifa personisrecognizedtobewithoutmask,alertwillbesent. Theprojectedsystemarchitecturecanbefurthermodified usinghardware,sensorstoaccommodatethermalscanning Tfeatures.heproposed
1.ytrue:Thetruthlabels. 2.ypred:Predictedlabels. 2] Accuracy: Accuracyisasuccessmetricthatsumsuphowwellamodel performsthroughoutalltheclasses.It'shelpfulwhenallof theclassesareequallyimportant.(seeFig 4) Fig 4:Accuracy
9. REFERENCES
International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056
Volume: 09 Issue: 01 | Jan 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page1356
Currentresearchwork is helpful innewnormal social life andindustriallife.Theresearcherscouldstudyprominent MLalgorithmsandsuggesteduseabilityofCNNandYolov3 as the simplest and appropriate methods to build an applicationon.Duetostronglibrarysupportandbeingapt languageformachinelearning,Pythoncanbeusedfor the Theimplementation.proposedsystem
6. CONCLUSIONS
3] Precision: Precision of the model is the ratio of True Positives to all positivepredictions. The lower the number of false positives predicted by the model,thehighertheprecision.(seeFig 5) Fig 5:Precision
architectureidentifiedsiximportant characteristicsofcustomMAFAdatasettoidentifytheface mask. Model is trained on this MAFA dataset. Research suggests Yolo v3 can be successfully used to check social distancing.
8. ACKNOWLEDGEMENT Researchers would like to convey gratefulness to their projectmentor,Prof.AnuradhaS.Deokarforhercompetent assistance and advice throughout the survey and implementationprocessof thisproject.
[1] J. Barabas, R. Zalman and M. Kochlan, "Automated evaluationofCOVID 19riskfactorscoupledwithreal time, indoor, personal localization data for potential disease identification, prevention and smart quarantining,"202043rdInternationalConferenceon TelecommunicationsandSignalProcessing(TSP),2020, pp.645 648,doi:10.1109/TSP49548.2020.9163461.M.
4] Recall: TheratioofTruePositivestoallpositivesinyourdatasetis knownasrecall.Itisalsoknownassensitivity.
1] Confusion Matrix: ThemetricsmoduleinPython'spopularScikit learnlibrary canbeusedtodeterminetheperformancemeasuresinthe confusion matrix. Determination of worn mask is binary classproblemwhichcanbesolvedusingconfusionmatrix. Weemploytwoofitsacceptedparameters:
ThelowerthenumberofFalseNegativespredictedbythe model,thehighertherecall.(seeFig 6) Fig-6:Recall
frameworkisnotlimitedtomaskandsocial distancing detection but ,it can be integrated into a high resolutionvideosurveillancedevice.Thesystemcanalsobe implemented and expanded in biometric face recognition systemstodetectfeaturesoffaceswithfacemasks. This application can be used in any work context where predictiveperformanceisneeded,suchasapublicplace,a station, an industrial environment, streets, commercial buildings,andexaminationcenters. This method can be applied to smart city innovation, that would help many developing countries ramp up their development. The current research work with actual applicationdevelopmentcanthusbecomeapartandparcel ofnewnormalandbeintegratedatallcrowdyplaces.
The mask localizer,a convolutional neural network based classification model, receives the processed image. The MAFAdatasetwillbeusedtotrainthemodelandwillhelp withimageanalysis.Thesystemwilldetectifthepersonis notwearingamaskandnotify.
[7] A.Rahman,M.S.Hossain,N.A.AlrajehandF.Alsolami, "AdversarialExamples SecurityThreatstoCOVID 19 DeepLearningSystemsinMedicalIoTDevices,"inIEEE InternetofThingsJournal,vol.8,no.12,pp.9603 9610, 15June15,2021,doi:10.1109/JIOT.2020.3013710.
[10] S. J.Yooketal.,"ExperimentalInvestigationsonParticle Contamination of Masks Without Protective Pellicles DuringVibrationorShippingofMaskCarriers,"inIEEE TransactionsonSemiconductorManufacturing,vol.20, no. 4, pp. 578 584,Nov.2007,doi: 10.1109/TSM.2007.907635.
Page
[8] Z.Jiangetal.,"DetectionofRespiratoryInfectionsUsing RGB Infrared Sensors on Portable Device," in IEEE Sensors Journal, vol. 20, no. 22, pp. 13674 10.1109/JSEN.2020.3004568.13681,15Nov.15,2020,doi:
[3] T.Ikram,A.Saeed,N.Ayn,M.A.TahirandR.Mumtaz,"A reviewoftheprevalentICTtechniquesusedforCOVID 19 SOP violation detection," 2020 IEEE 17th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET), 2020, pp. 194 198, doi: 10.1109/HONET50430.2020.9322821.
[9] Buddhisha Udugama, Pranav Kadhiresan, Hannah N. Kozlowski, Ayden Malekjahani, Matthew Osborne, Vanessa Y. C. Li, Hongmin Chen, Samira Mubareka, Jonathan B. Gubbay, and Warren C. W. Chan* “Diagnosing COVID 19: The Disease and Tools for Detection”,AmericanChemicalSociety,year2020,doi: 10.1021/acsnano.0c02624.
[4] D. R. Shenvi and K. Shet, "CNN Based COVID 19 PreventionSystem,"2021InternationalConferenceon Artificial Intelligence and Smart Systems (ICAIS),2021,pp.873 10.1109/ICAIS50930.2021.9396004.878,doi:
[6] H.S.Maghded,K.Z.Ghafoor,A.S.Sadiq,K.Curran,D.B. RawatandK.Rabie,"ANovelAI enabledFrameworkto Diagnose Coronavirus COVID 19 using Smartphone Embedded Sensors: Design Study," 2020 IEEE 21st International Conference on Information Reuse and IntegrationforDataScience(IRI),2020,pp.180 187,doi: 10.1109/IRI49571.2020.00033.
[5] G.Deore,R.Bodhula,V.UdpikarandV.More,"Studyof masked face detection approach in video analytics," 2016 Conference on Advances in Signal Processing(CASP),2016,pp.196 200,doi: 10.1109/CASP.2016.7746164.
International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056 Volume: 09 Issue: 01 | Jan 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | 1357
[12] M.A.Malbog,"MASKR CNNforPedestrian Crosswalk Detection andInstance Segmentation,"2019IEEE 6th InternationalConferenceonEngineeringTechnologies and Applied Sciences (ICETAS),2019,pp.1 5,doi: 10.1109/ICETAS48360.2019.9117217.
[14] https://livebook.manning.com/book/grokking deep learning for computer vision/chapter 7/v 8/
Young, The Technical Writer’s Handbook. Mill Valley, CA:UniversityScience,1989.
[15] A High Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets Scientific Figure on ResearchGate. Available architecturediagramhttps://www.researchgate.net/figure/Schematicfrom:ofabasicconvolutionalneuralnetworkCNN26_fig1_336805909
10. BIOGRAPHIES GAURAV GARJE BE AISSMSCOECOMPUTER,PUNE RASIKA LANDE BE AISSMSCOECOMPUTER,PUNE SHARDUL SHINDE BE AISSMSCOECOMPUTER,PUNE
[13] Q. C. Mao, H. M. Sun, Y. B. Liu and R. S. Jia, "Mini YOLOv3: Real Time Object Detector for Embedded Applications," in IEEE Access, vol. 7, pp. 133529 133538,2019,doi:10.1109/ACCESS.2019.2941547
[2] S.Lietal.,"Multi angleHeadPoseClassificationwhen Wearing the Mask for Face Recognition under the COVID 19 Coronavirus Epidemic," 2020 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS), 2020, pp. 1 5, doi: 10.1109/HPBDIS49115.2020.9130585.K.Elissa,“Titleof paperifknown,”unpublished.
[11] M. S. Hossain, G. Muhammad and N. Guizani, "Explainable AI and Mass Surveillance System Based Healthcare Framework to Combat COVID I9 Like Pandemics,"inIEEENetwork,vol.34,no.4,pp.126 132, July/August2020,doi:10.1109/MNET.011.2000458.
International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056 Volume: 09 Issue: 01 | Jan 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page1358 NISHANT INAMDAR BE AISSMSCOECOMPUTER,PUNE PROF. ANURADHA DEOKAR AISSMSCOE,PUNE
