During the Covid-19 pandemic, it was compulsory to wear a mask. Even in the current situation, when the pandemic is not over. A mask is essential and can be mandated from time to time for specific purposes and conditions. Manually monitoring the masks for large numbers of visitors or attendees for an event or at any public place is challenging and requires much manual work. It is time-consuming, and we cannot completely monitor it. Machine learning based approaches and automated monitoring using security cameras can be a possible solution to minimize the need for large manpower. Many models have been proposed for mask detection using machine learning but still there is a chance for improving the accuracy. Further the training time is high in these cases were normally the train and test ratio for dataset is 80:20 that takes a good chunk of time in training. This study proposes a machine learning-based face detection mechanism using MobileNet_v2 transfer learning techniques to provide very high accuracy in detecting the people not wearing masks or not wearing them properly. Further this study proposes to minimize the training time for speedy and real-time analysis by selecting an optimal combination of train and test dataset ratio. Finally, the model has been implemented using the webcam tool to recognize mask wearers in real time with high accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.