Robust Face Mask Detection with Combined Frontal and Angled Viewed Faces

• Main Authors: Tarun, Ivan George, Lopez, Vidal Wyatt M, Abu, Patricia Angela R, Estuar, Ma. Regina Justina
• Format: text
• Published: Archīum Ateneo 2022
• Subjects: Face Mask Detection; Object Detection; Deep Learning; Computer Vision; Artificial Intelligence and Robotics; Computer Sciences; Medicine and Health Sciences; Physical Sciences and Mathematics; Public Health
• Online Access: https://archium.ateneo.edu/discs-faculty-pubs/345; https://doi.org/10.5220/0010986000003179
• Institution: Ateneo De Manila University

One such protocol currently enforced by the Philippine government to combat COVID-19 is the mandatory use of face masks in public places. The problem however is that ensuring people follow this protocol is difficult to monitor during a pandemic due to other conflicting health protocols like social distancing and workforce reduction. This study therefore explores on the creation of deep learning models that consider both frontal and side view images of the face for face mask detection. In doing so, improvements to robustness were found when compared to using models that were previously trained on purely frontal images. This was accomplished by first relabeling a subset of images from the FMLD dataset. These images were then split into train, validation, and test sets. Four deep learning models (YOLOv5 Small, YOLOv5 Medium, CenterNet Resnet50 V1 FPN 512x512, CenterNet HourGlass104 512x512) were later trained on the training set of images. These four models were compared with three models (MobileNetV1, ResNet50, VGG16) that were trained previously on purely frontal images. Results show that the four models trained on the relabeled FMLD dataset offer an approximately 20% increase in classification accuracy over the three models that were previously trained on purely frontal images.