With the emergence of Covid-19, various measures have been implemented to reduce the risk of contracting the virus. For example, people are required to wear face masks in public spaces. However, many people do not comply with these policies. Specifically, many people do not wear face masks in a place where it is required. Although non-adherence to these policies attracts punishment, it is difficult to identify people without face masks in crowded places.

With the proliferation of Artificial Intelligence and computing technology, image processing and computer vision techniques can be implemented to aid authorities in identifying people who do not adhere to face mask-wearing policies.

This project introduces a neural network system, which can be trained to identify people’s

facial features even if half of their faces are covered by facemasks. The Convolutional Neural

The network (CNN) model using transfer learning technique has achieved remarkable accuracy. One large Face mask detection dataset was first used to train the model, while the original much smaller Face mask detector dataset was used to adapt and finetune this model that was previously generated. During the training and testing phases, network structures, and various parameters were adjusted to achieve the best accuracy results for the actual small dataset. Our adapted model was able to achieve a 97.1% accuracy.