Social Distance Monitoring and Face Mask Detection System

Abstract

The Covid-19 pandemic has caused a devastating effect toward society, economy and even education system. To prevent the Covid-19 outspread, lock-down seems to be one of the most popular solutions being carried out by governments including Malaysia. In the long run, schools will be reopening anytime when the pandemic is under control. However, the attention towards control measures in school should be paid to prevent the pandemic resurgence. Manual monitoring of the SOP is impractical towards a large population with only limited resources and task forces. To mitigate the issues, the social distancing monitoring and face mask detection system – EyeSpy has been proposed. The proposed system aims to assist teachers in monitoring SOP compliances performed by students in school, thus lowering the risk for Covid- 19 outspread. This paper also provides a comparative study of different face detections, CNN architecture on facemask classifiers. Apart from that, this research employed Rapid Application Development as the system development methodology for the development of EyeSpy. Other than that, interview and questionnaire are used as requirement gathering methods to study the feasibility of the project. A system has been developed to act as a proof of concept to underline the implementation of EyeSpy mobile application in restraining the spreading of Covid-19 in schools.