Abstract—The COVID-19 pandemic has wreaked havoc on people all across the world. Even though the number of verified COVID-19 cases is steadily decreasing, the danger persists. Only societal awareness and preventative measures can assist to minimize the number of impacted patients in the work environment. People often forget to wear masks before entering the work premises or are not careful enough to wear masks correctly. Keeping this in mind, this paper proposes an IoT-based architecture for taking all essential steps to combat the COVID-19 pandemic. The proposed low-cost architecture is divided into three components: one to detect face masks by using deep learning technologies, another to monitor contactless body temperature and the other to dispense disinfectants to the visitors. At first, we review all the existing state-of-the-art technologies, then we design and develop a working prototype. Here, we present our results with the accuracy of 97.43% using a deep Convolutional Neural Network (CNN) and 99.88% accuracy using MobileNetV2 deep learning architecture for automatic face mask detection.
 

Keywords—Artificial Intelligence (AI), Convolutional Neural Network (CNN), Deep Learning (DL), Computer Vision, Intelligent Automation (IA), MobileNetV2

Cite: Ahsanul Akib, Kamruddin Nur, Suman Saha, Jannatul Ferdous Srabonee, and M. F. Mridha, "Computer Vision-Based IoT Architecture for Post COVID-19 Preventive Measures," Journal of Advances in Information Technology, Vol. 14, No. 1, pp. 7-19, February 2023.

Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.