Face Identity for Face Mask Recognition System

Abstract

Facial recognition system analyzes and compares patterns based on the facial information of a person. The technology is widely implemented as a security mechanism in the area such as public surveillance and mobile communication to identify the identity of a person. Today, wearing a face mask is mandatory during COVID-19 pandemic. However, it has become challenging for facial recognition technology to recognize the identity of a person wearing a face mask. This preliminary study set out to develop and measure the effectiveness of a face recognition system to identify the identity of a person with a face mask. The system uses a deep learning model for face mask detection and Procrustes analysis to measure the face identity similarity. A combination of standard face recognition performance measures was used to measure the effectiveness of the system. A self-obtained dataset consists of 35 images of persons with a face mask from different identity background was investigated. The results indicate that the system effectively recognizes the identity of a person with a face mask up to 97.14% accuracy. Despite its exploratory nature, this study offers some insight into face masked identity recognition. A natural progression of this work is to explore other types of face mask detection and similarity methods.