ONOFFMASK

Mask mandates in Canada are still pretty much a thing — in hospitals, pharmacies, and airports. Why not implement a machine learning AI detector that helps keep people covid-safe?

Comment

What it does

This Project Mask Detector basically can detect and classify whether or not a person if wearing a mask. It also looks for whether they are wearing it correctly or not. It is also able to identify many people, allowing the model to distinguish people that are in a specific footage.

How I built it

This Face Mask Detector was built using Keras, Tensorflow, MobileNet and OpenCV. Implementing a database of images, I imported on to tensorflow, sent it in to its mobile net, processed max pooling, flattened it, and derived the output through a fully connected layer. Mobile net uses less parameters so I could efficiently apply this on a Live Video Camera. This model can be integrated with CCTV cameras to detect and identify people without masks.

Accomplishments that I'm proud of

The face mask detector didn't use any morphed masked images dataset. The model is accurate, and since the MobileNetV2 architecture is used, it’s also computationally efficient and thus making it easier to deploy the model to embedded systems (Raspberry Pi, Google Coral, etc.).

What's next for ONOFFMASK

This system can therefore be used in real-time applications which require face-mask detection for safety purposes due to the outbreak of Covid-19. This project can be integrated with embedded systems for application in airports, railway stations, offices, schools, and public places to ensure that public safety guidelines are followed.

Built With

  • keras
  • mobilenet
  • objectdetectionapi
  • opencv
  • pycharm
  • python
  • tensorflow
Share this project:

Updates