• Register
  • Login

European Journal of Molecular & Clinical Medicine

  • Home
  • Browse
    • Current Issue
    • By Issue
    • By Subject
    • Keyword Index
    • Author Index
    • Indexing Databases XML
  • Journal Info
    • About Journal
    • Aims and Scope
    • Editorial Board
    • Publication Ethics
    • Indexing and Abstracting
    • Peer Review Process
    • News
  • Guide for Authors
  • Submit Manuscript
  • Contact Us
Advanced Search

Notice

As part of Open Journals’ initiatives, we create website for scholarly open access journals. If you are responsible for this journal and would like to know more about how to use the editorial system, please visit our website at https://ejournalplus.com or
send us an email to info@ejournalplus.com

We will contact you soon

  1. Home
  2. Volume 7, Issue 6
  3. Authors

Online ISSN: 2515-8260

Volume7, Issue6

A Novel Approach To Detect Face Mask To Control Covid Using Deep Learning

    T Subhamastan Rao S Anjali Devi P Dileep M Sitha Ram

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 6, Pages 658-668

  • Show Article
  • Download
  • Cite
  • Statistics
  • Share

Abstract

COVID-19 caused due to corona virus, this virus was first discovered in wuhan on Dec -2019 now it is a pandemic effecting almost every country in the world. This virus transmitting from one person to another person through droplets spawned when a covid patient sneezes, coughs or exhales. Even these droplets reaches ground soon because they are heavy and unable to hang in the air. One of the solution to prevent covid-19 is wearing the face masks, Many governments trying their best to educate citizens to wear masks in public places even they made it mandatory, but majority people are violating this rule. In current scenario police frequently check for face mask in public places and imposing fine on the people who are not wearing face mask. On other hand some governments introduced technology to detect people with out face mask and send their details to petrol team then they will catch them. In this paper we are proposing a model which detects public without facemask and thatdata can be used to identify the person who is not wearing the mask using facial detection system then that data is integrated with public identification data base to collect details of that person and fine amount will send to his mobile number and address. using CNN model we have detected persons with mask and without mask. CNN can able to identify pixel level data when compared to many algorithms available, CNN works more accurately. We implemented a model with two convolution layers with 100 filters in each and applied drop out 0.5% and used Relu, soft max as activation functions at hidden and fully connected layers respectively, Cross entropy used as loss function adam is optimizer and model trained over 1500 images consists of both classes with mask and without mask and cascade classifier is used to classify faces and it is working with 91.21 accuracy. This AI based mask detection system definitely creates fear in the minds of public and they will start wearing mask in public places so that the spreading of the disease can be controlled that intern useful for wellbeing of the society.
Keywords:
  • PDF (460 K)
  • XML
(2020). A Novel Approach To Detect Face Mask To Control Covid Using Deep Learning. European Journal of Molecular & Clinical Medicine, 7(6), 658-668.
T Subhamastan Rao; S Anjali Devi; P Dileep; M Sitha Ram. "A Novel Approach To Detect Face Mask To Control Covid Using Deep Learning". European Journal of Molecular & Clinical Medicine, 7, 6, 2020, 658-668.
(2020). 'A Novel Approach To Detect Face Mask To Control Covid Using Deep Learning', European Journal of Molecular & Clinical Medicine, 7(6), pp. 658-668.
A Novel Approach To Detect Face Mask To Control Covid Using Deep Learning. European Journal of Molecular & Clinical Medicine, 2020; 7(6): 658-668.
  • RIS
  • EndNote
  • BibTeX
  • APA
  • MLA
  • Harvard
  • Vancouver
  • Article View: 233
  • PDF Download: 318
  • LinkedIn
  • Twitter
  • Facebook
  • Google
  • Telegram
Journal Information

Publisher:

Email:  info@ejmcm.com

  • Home
  • Glossary
  • News
  • Aims and Scope
  • Privacy Policy
  • Sitemap

Editorial Team:  editor@ejmcm.com

For Special Issue Proposal : chiefeditor.ejmcm@gmail.com / info@ejmcm.com

This journal is licensed under a Creative Commons Attribution 4.0 International (CC-BY 4.0)

Powered by eJournalPlus