In the present scenario due to Covid-19, there are no efficient face mask detection applications which are now in high demand for transportation means, densely populated areas, residential districts, large-scale manufacturers and other enterprises to ensure safety.
What it does
This system takes as the input the real time video streams as well as images, in order to detect the presence of face masks in static images as well as in real-time video streams. The output is in the form of images and video streams with score alert boundaries demarcated around human faces. This gives a confidence measure and helps determine whether the person is wearing the mask properly or not. This is further facilitated by a simple and intuitive UI interface.
How we built it
Our Face Mask Detection system is built with OpenCV, Keras/TensorFlow using Deep Learning and Computer Vision concepts. It uses Transfer Learning and OpenCV caffemodel for face detection along with MobileNetV2 architecture.
Challenges we ran into
The absence of large datasets of ‘with_mask’ images made this task more cumbersome and challenging.
Accomplishments that we're proud of
This project has been a part of many open source challenges such as Student Code-In, Script Winter of Code, DevScript Winter of Code. It is one of the most visited face mask detection projects on GitHub.
What we learned
We learnt the deep learning technique for efficient object detection and also how to process images in an efficient fashion.We also learnt to extract images via search API Python script.
What's next for Face mask detection
The next step is to detect the person who is not wearing a mask and send an alerting mechanism. Also to make the dataset elaborate.
All the setup and installation guides are present in the README.md of the repository. We certainly welcome many and more community contributions to our repository under the Open Innovation Model!