OpenCV Based Customer Screening System for Prevention of COVID-19 Transmission in Retail Stores

The COVID-19 pandemic has taken the world by a storm for over three years now. With new variants and developments constantly being brought to light, it has become imperative for citizens to get vaccinated and maintain social distancing in public places, such as retail stores, in order to curb the spread of the virus. Statistics suggest that being fully vaccinated can prove to be, on average, 81% effective against the COVID-19 virus. This project aims at developing a customer screening system that dynamically counts the number of customers inside a store at a particular point in time and allows conditional entry only if the customer is fully vaccinated and wearing a face mask. This system is developed using Open-CV and MobileNetV2 for detection of facial characteristics, and achieved 98% accuracy for face mask detection. Further, a QR Scanner has been employed in conjunction with the Indian government-authorized CoWIN portal for verification of vaccination details, and Flask for the development of a web server for implementation. Additionally, key demographic information pertaining to customers and entry logs have been automatically populated into an Excel-based database for predictive crowd analysis. In doing so, the manual labour required for the customer screening process has been reduced to zero whereas the health and safety of individuals is promoted, consequentially curbing the spread of the virus.