ABSTRACT
COVID-19 is a disease that affects many aspects of life transmitted by verbal interaction. Nowadays the rapid growth of COVID-19 has become an international issue due to violation of the face mask rules. This research will provide a comparison of the deep learning class, Convolutional Neural Network (CNN) which is used as the basis of the face mask recognition system and to adapt it into a payment verification system. This research will use MobileNetv2 and YOLO-v4 with its pretrained model using group of images composed of person using face mask and person not using face mask. Each model successfully performs the detection task. The result shows that MobileNetv2 has achieved a better overall percentage compared to the YOLO-v4 algorithm. Hence, MobileNetv2 has been chosen as the algorithm used for the payment verification system. © ICIC International.