A Comparative Analysis of Machine Learning Approaches for Automated Face Mask Detection During COVID-19

TL;DR

This study compares deep learning models for automated face mask detection during COVID-19, highlighting the effectiveness of transfer learning but also its limitations in real-world, cross-domain scenarios.

Contribution

It evaluates multiple deep learning models and transfer learning approaches for face mask detection, providing insights into their performance and robustness.

Findings

Transfer learning models outperform others in accuracy.

Performance improves by 0.10-0.40% with 30% less training time.

Models lose 47% accuracy in cross-domain tests without fine-tuning.

Abstract

The World Health Organization (WHO) has recommended wearing face masks as one of the most effective measures to prevent COVID-19 transmission. In many countries, it is now mandatory to wear face masks, specially in public places. Since manual monitoring of face masks is often infeasible in the middle of the crowd, automatic detection can be beneficial. To facilitate that, we explored a number of deep learning models (i.e., VGG1, VGG19, ResNet50) for face-mask detection and evaluated them on two benchmark datasets. We also evaluated transfer learning (i.e., VGG19, ResNet50 pre-trained on ImageNet) in this context. We find that while the performances of all the models are quite good, transfer learning models achieve the best performance. Transfer learning improves the performance by 0.10\%--0.40\% with 30\% less training time. Our experiment also shows these high-performing models are not quite robust for real-world cases where the test dataset comes from a different distribution. Without any fine-tuning, the performance of these models drops by 47\% in cross-domain settings.