Real Time Web-based Facemask Detection

ABSTRACT

The widespread spread of the Covid-19 virus in 2020-2021 is very worrying for all people around the world, coupled with the spread of a new variant of the Covid-19 virus, which is more aggressive and easily transmitted, causing public unrest about when this pandemic will end. The policy of using masks to reduce the spread of the virus has been made to minimize the spread. But even if there is a policy, there are still people who don't want to wear masks. Therefore, a mask detection system is needed to help differentiate whether someone uses a mask or not by displaying alerts in a form of web application. This research was conducted using several data augmentation techniques to increase the variation of the data to be used before training the algorithm model using the Convolutional Neural Network (CNN) algorithm with MobileNetV2 and VGG19 architectures. Both models are then evaluated where the architecture with the best performance will be implemented in the form of a web application. The accuracy of both models was compared, with the result of MobileNetV2 being 99% accurate and VGG19 being 98%. MobileNetV2 as the model that has the best accuracy value will be implemented in the form of a web application using the Haar Feature-Based Cascade to detect masks. The web application will be publicly accessed local at Universitas Multimedia Nusantara. © 2022 IEEE.