ABSTRACT
Recent advancements in the growth of classification tasks and deep learning have culminated in the worldwide success of numerous practical applications. With the onset of COVID-19 pandemic, it becomes very important to use technology to help us control the infectious nature of the virus. Deep learning and image classification can help us detect face mask from a crowd of people. However, choosing the correct deep learning architecture can be crucial in the success of such an idea. This study presents a model for extracting features from face masks utilizing pre-trained models ConvNet, InceptionV3, MobileNet, DenseNet, ResNet50, and VGG19, as well as stacking a fully connected layer to solve the issue. On the face mask 12 k dataset, the study assesses the effectiveness of the suggested deep learning approaches for the task of facemask detection. The performance metrics used for analysis are loss, accuracy, validation loss, and validation accuracy. The maximum accuracy is achieved by DenseNet and MobileNet. Both the models gave a comparable and good accuracies in terms of training and validation (99.89% and 99.79%), respectively. Further, the paper also demonstrates the deployment of deep learning architecture in the real-world using Raspberry Pi 2B (1 GB RAM). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.