ABSTRACT
In this chapter, we intend to design a mask detector model that gives high accuracy compared to other models and runs efficiently run on the Raspberry Pi. To achieve this, we trained the model using various algorithms, and comparisons are made based on accuracy and precision values and how efficiently the system works. Continuous temperature monitoring is done using the temperature sensor. The entry system will open if the person wears the mask and has an average body temperature. In this chapter, we describe the deep learning model for face mask detection using InceptionV3 and MobileNetV2, which gave us an accuracy of 98.29% and 97.2%, which is better than other algorithms and performs efficiently on the Raspberry Pi. Both of these technologies can be implemented in various settings, including airports, schools, and hospitals, to help monitor and control the spread of COVID-19. However, it's important to note that these technologies have limitations and may not be 100% accurate. It's always recommended to follow other preventive measures, such as social distancing and handwashing hygiene, in addition to using technology-based solutions.
