Abstract
COVID-19 has made mankind see unprecedented and unbelievable times with millions of people being affected due to it. Multiple countries have started vaccinating their populations in the hope that it will end the pandemic. Given the inequitable access to vaccines across the world and the highly mutating coronavirus it remains to be seen when will everyone get access to vaccines and how effective the vaccines might prove over the virus variants. Therefore, standard COVID behaviour is here to stay for some time. Wearing face masks is one such etiquette which greatly reduces risk of getting infected. Employing public face mask detection systems has helped multiple countries to bring the pandemic under control. In this paper we have done a quantitative analysis of different object detection algorithms namely ResNet,MobileNetV2 and CNN on face mask detection on accuracy and recall parameters using an unbiased, large and diverse dataset in order the algorithm which can be applied on a mass scale.
Highlights
COVID-19 is the disease caused by a new coronavirus called SARS-CoV-2
The performance of MobileNet, ResNet SSD and Custom CNN models was compared in order to assess which model performs better in both low light as well as well lit conditions and it was found that MobileNet achieved higher confidence values than both the other models in both poorly lit as well as well lit conditions
The confidence values achieved by the respective models along with the recall values are depicted in the graphs given below
Summary
COVID-19 is the disease caused by a new coronavirus called SARS-CoV-2. The disease is highly contagious and can spread from person to person through small droplets from the nose or mouth when a healthy person inhales the droplets from a COVID infected person. Wearing face masks greatly reduces the spread of infection. Japan the country with world’s oldest population which are most susceptible towards the virus was able to control the pandemic through the mask culture prevalent in the country for many years now. General public have not adhered to wearing face masks in many countries despite government guidelines. Once the worst affected COVID-19 hit country China was able to successfully combat COVID19 due to deployment of public face mask detection systems which helped it identify people not wearing masks and penalise them. Object detection is a technology that deals with detecting and locating instances of semantic objects of a certain class like humans, buildings etc. in digital images and videos
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Engineering and Advanced Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
