Science in Information Technology Letters Vol. 4., No. 1, May 2023, pp. 22-39 ISSN 2722-4139 http://pubs2.ascee.org/index.php/sitech http://doi.org/10.31763/sitech.v4i1.1199 sitech@ascee.org YOLOv3 and YOLOv5-based automated facial mask detection and recognition systems to prevent COVID-19 outbreaks Md Asifuzzaman Jishan a,1 ,* , Ananna Islam Bedushe b,2 , Md Ataullah Khan Rifat a,3 , Bijan Paul c,3 , Khan Raqib Mahmud c,5 a Faculty of Statistics, Technische Universität Dortmund, Germany b Department of Computer Science, Hofstra University, United States of America c Department of Computer Science and Engineering, University of Liberal Arts Bangladesh, Bangladesh 1 md-asifuzzaman.jishan@tu-dortmund.de; 2 abedushe1@pride.hofstra.edu; 3 khan.rifat@tu-dortmund.de; 4 bijan.paul@ulab.edu.bd; 5 raqib.mahmud@ulab.edu.bd * Corresponding Author 1. Introduction In 2019, the COVID-19 Coronavirus outbreak was discovered for the first time in Wuhan, China. Since then, it has spread across the globe and mutated into the fifth pandemic recorded since the 1918 influenza pandemic. Almost 200 million people were infected with the COVID-19 virus, resulting in over 4.6 million deaths. This happened approximately two years after the initial discovery of the COVID- ARTICLE INFO ABSTRACT Article history Received April 09, 2023 Revised April 12, 2023 Accepted May 01, 2023 Object detection system in light of deep learning have been monstrously effective in complex item identification task images and have shown likely in an extensive variety of genuine applications counting the Coronavirus pandemic. Ensuring and enforcing the proper use of face masks is one of the main obstacles in containing and reducing the spread of the infection among the population. This paper aims to find out how the urban population of a megacity uses facial masks correctly. Using YOLOv3 and YOLOv5, we trained and validated a brand-new dataset to identify images as "with mask", "without mask", and "mask not in position". In the YOLOv3 we carried out three pre-trained models which are: YOLOv3, YOLOv3-tiny, and SPP-YOLOv3. In addition, we utilized five pre-trained models in the YOLOv5: YOLOv5n, YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x. The dataset is included 6550 pictures with three classes. On mAP, the dataset achieved a commendable 95% performance accuracy. This research can be used to monitor the proper use of face masks in various public spaces through automated scanning. This is an open access article under the CC–BY-SA license. Keywords Facial mask detection Classification of image YOLOv3 YOLOv5 COVID-19 pandemic