An Enhanced Deep Learning Model for Automatic Face Mask Detection

The recent COVID-19 pandemic has had lasting and severe impacts on social gatherings and interaction among people. Local administrative bodies enforce standard operating procedures (SOPS) to combat the spread of COVID-19, with mandatory precautionary measures including use of face masks at social assembly points. In addition, the World Health Organization (WHO) strongly recommends people wear a face mask as a shield against the virus. The manual inspection of a large number of people for face mask enforcement is a challenge for law enforcement agencies. This work proposes an automatic face mask detection solution using an enhanced lightweight deep learning model. A surveillance camera is installed in a public place to detect the faces of people. We use MobileNetV2 as a lightweight feature extraction module since the current convolution neural network (CNN) architecture contains almost 62,378,344 parameters with 729 million floating operations (FLOPs) in the classification of a single object, and thus is computationally complex and unable to process a large number of face images in real time. The proposed model outperforms existing models on larger datasets of face images for automatic detection of face masks. This research implements a variety of classifiers for face mask detection: the random forest, logistic regression, K-nearest neighbor, neural network, support vector machine, and AdaBoost. Since MobileNetV2 is the lightest model, it is a realistic choice for real-time applications requiring inexpensive computation when processing large amounts of data.