Real Time Face Mask Detection and Alert System Using Convolutional Neural Network

Abstract

We all know how Covid-19 pandemic has affected our lives. During this time of constant fear and uncertainty it is important that all individuals wear a protective face mask to prevent ourselves from the exposure to the deadly virus. Therefore, face mask detection has become a crucial task to avoid spreading of virus and to help the global society. This paper presents a real time face mask detection system which detects if a person is wearing a face mask or not and gives an alert to the authorities if he/she fails to wear a face mask, which can be implemented in places where public gather frequently such as entrance and exit gates of shopping malls, offices, hotels, hospitals, railway stations and other public places. The methodology that we haveimplemented involves collection of data set which includes two kinds of data, one is jpeg images of faces with mask and another jpeg images of faces without mask, preprocessing the collected dataset, training the processed data using Convolutional Neural Network (CNN) model and also by using some Machine learning packages like KERAS, Tensor flow, Open CV and Scikit-learn. Finally, a real time detection is done and an alert message is sent to the authorities via e-mail if a person is detected not wearing a face mask.