Enhancing Pandemic Safety with MobileNetV2: Real-Time Facemask Detection

People throughout the world have experienced significant disruptions to their daily routines as a result of the recent pandemic caused by widespread COVID-19. One proposal to combat the outbreak was to have people wear facemasks in public locations. However, due to a lack of understanding and public behavior, it was difficult to track down everyone and force them to wear a facemask. To force people to utilize the mask, robust computers and effective facial detecting technologies are required. MobileNetV2 is used in this study to construct this complex system. Because of the light version of the deep learning model, MobileNetV2, the system is incredibly light and can be integrated into any sort of device. The system is designed in such a way that it can determine whether a person is wearing a mask based on the image collection. The algorithm has been trained and tested on a dataset of 6369 photos. To conduct the trials, a pre-trained model, MobileNetV2, was used, and the accuracy achieved was around 98%. Compared to VGG-16 and Inception-V3, the proposed system is quite efficient and lightweight. For current or future use, this work can be used as a digital checking device in schools, hospitals, banks, airports, railway stations, and many other public or business settings.