Open AccessBehind the Mask: Detection and Recognition Based-on Deep Learning
Author(s) -
Ade Nurhopipah,
Irfan Rifai Azziz,
Jali Suhaman
Publication year - 2022
Publication title -
indonesian journal of computing and cybernetics systems
Language(s) - English
Resource type - Journals
eISSN - 2460-7258
pISSN - 1978-1520
DOI - 10.22146/ijccs.72075
Subject(s) - computer science , minimum bounding box , artificial intelligence , deep learning , face (sociological concept) , facial recognition system , bounding overwatch , task (project management) , computer vision , face detection , detector , pixel , pattern recognition (psychology) , class (philosophy) , image (mathematics) , engineering , telecommunications , social science , systems engineering , sociology
COVID-19 prevention procedures are executed to support public services and business continuity in a pandemic situation. Manual mask use monitoring is not efficient as it requires resources to monitor people at all times. Therefore, this task can be supported by automated surveillance systems based on Deep Learning. We performed mask detection and face recognition for a real-environment dataset. YOLOV3 as a one-stage detector was implemented to simultaneously generate a bounding box of the face area and class prediction. In face recognition, we compared the performance of three pre-trained models, namely ResNet152V2, InceptionV3, and Xception. The mask detection showed promising results with MAP=0.8960 on training and MAP=0.8957 on validation. We chose the Xception model for face recognition because it has equal quality as ResNet152V2 but has fewer parameters. Xception achieved a minimal loss value in the validation of 0.09157 with perfect accuracy on facial images larger than 100 pixels. Overall the system delivers promising results and can identify faces, even those behind the mask.