Towards Facial Recognition Problem in COVID-19 Pandemic

Abstract

In epidemic situations such as the novel coronavirus (COVID-19) pandemic, face masks have become an essential part of daily routine life. The face mask is considered as a protective and preventive essential of everyday life against the coronavirus. Many organizations using a fingerprint or card-based attendance system had to switch towards a face-based attendance system to avoid direct contact with the attendance system. However, face mask adaptation brought a new challenge to already existing commercial biometric facial recognition techniques in applications such as facial recognition access control and facial security checks at public places. In this paper, we present a methodology that can enhance existing facial recognition technology capabilities with masked faces. We used a supervised learning approach to recognize masked faces together with in-depth neural network-based facial features. A dataset of masked faces was collected to train the Support Vector Machine classifier on state-of-the-art Facial Recognition Feature vector. Our proposed methodology gives recognition accuracy of up to 97% with masked faces. It performs better than exiting devices not trained to handle masked faces.