Open AccessConvolutional neural network architecture based automatic face mask detection
Author(s) -
Sagar Agarwal,
J. P. Patra,
Suman Kumar Swarnkar
Publication year - 2022
Publication title -
international journal of health sciences (ijhs) (en línea)
Language(s) - English
Resource type - Journals
eISSN - 2550-6978
pISSN - 2550-696X
DOI - 10.53730/ijhs.v6ns3.5401
Subject(s) - convolutional neural network , face (sociological concept) , artificial intelligence , computer science , computer vision , architecture , covid-19 , face detection , facial recognition system , pattern recognition (psychology) , medicine , art , social science , disease , pathology , sociology , infectious disease (medical specialty) , visual arts
The pandemic of COVID – 19 has affected the whole world very badly. It has rapidly affected the way of living as wearing a protective or surgical face mask is new normal. It is necessary to wear a mask before entering a shop or any public place to avail of their services. Therefore, there is a need for face mask detection to help society. In this paper, we are presenting a simplified technique that detects whether a person is wearing a mask or not automatically with percentage accuracy of the fitment of the mask over the face. This technology can be used to stop the entry or warn the person to wear a mask properly before or while entering a shop or any public place. This purpose is achieved using OpenCV, Keras packages and convolutional neural network architecture (MobileNetV2). The accuracy of the face mask detection system is 96.07%.