Abstract
January 27 2020, a day that will be remembered by the Indian people for a few decades, where a deadly virus peeped into a life of a young lady and till now it has been so threatening as it took up the life of 3.26 lakh people just in India. With the start of the virus government has made mandatory to wear masks when we go out in to crowded or public areas such as markets, malls, private gatherings and etc. So, it will be difficult for a person in the entrance to check whether everyone one are entering with a mask, in this paper we have designed a smart door face mask detection to check whether who are wearing or not wearing mask. By using different technologies such as Open CV, MTCNN, CNN, IFTTT, ThingSpeak we have designed this face mask detection. We use python to program the code. MTCNN using Viola- Jones algorithm detects the human faces present in the screen The Viola-Jones algorithm first detects the face on the grayscale image and then finds the location on the colored image. In this algorithm MTCNN first detects the face in grayscale image locates it and then finds this location on colored image. CNN for detecting masks in the human face is constructed using sample datasets and MobileNetV2 which acts as an object detector in our case the object is mask. ThingSpeak is an open-source Internet of things application used to display the information we get form the smart door. This deployed application can also detect when people are moving. So, with this face mask detection, as a part to stop the spread of the virus, we ensure that with this smart door we can prevent the virus from spreading and can regain our happy life.
Highlights
A few nations around the globe have utilized face masks obligatory out in the open to help control the spread of COVID-19, the sickness brought about by the novel coronavirus
A month ago, the WHO refreshed its direction on masks, suggesting that they be worn in open regions where there is a danger of boundless network transmission and Physical separating is troublesome, for example, on open vehicle, in shops or other shut settings.so we thought bringing a smart door into the market which detects if a person wearing a mask or not is crucial for the society
[4] This paper proposed a Face mask detection system using the three main concepts, they are Deep learning with FPN to detect the Human, Multi-Task Convolutional Neural Networks (MT-Convolution Neural Network (CNN)) to detect human faces and convolutional neural network classifier to recognize masked and unmasked people
Summary
A few nations around the globe have utilized face masks obligatory out in the open to help control the spread of COVID-19, the sickness brought about by the novel coronavirus. A month ago, the WHO refreshed its direction on masks, suggesting that they be worn in open regions where there is a danger of boundless network transmission and Physical separating is troublesome, for example, on open vehicle, in shops or other shut settings.so we thought bringing a smart door into the market which detects if a person wearing a mask or not is crucial for the society. To do that we need to stop the spread of virus, to make that possible everyone should wear mask. We are implementing this face mask detection using CNN and MTCNN algorithms. MTCNN – Multi-task Cascade Convolutional Neural Network, used to detect a human face in an image and used to localize the face in that image
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 Innovative Technology and Exploring Engineering
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.
