Document Type


Publication Date



Mask-wearing remains to be one of the primary protective measures against COVID-19. To address the difficulty of manual compliance monitoring, face mask detection models considerate of both frontal and angled faces were developed. This study aimed to test the performance of the said models in classifying multi-face images and upon running on a Raspberry Pi device. The accuracies and inference speeds were measured and compared when inferencing images with one, two, and three faces and on the desktop and the Raspberry Pi. With an increasing number of faces in an image, the models’ accuracies were observed to decline, while their speeds were not significantly affected. Moreover, the YOLOv5 Small model was regarded to be potentially the best model for use on lower resource platforms, as it experienced a 3.33% increase in accuracy and recorded the least inference time of two seconds per image among the models.