Our teams' inspiration was that in so many retail stores in Canada, there are always people who are standing at the entrance making sure that people are wearing masks. We think that this is a task that can be easily automated with Cameras and Computer Vision Algorithms. So, those workers can spend their time working on more important tasks.
What it does
Our Project Mask Detector basically can detect and classify whether or not a person is wearing a mask. It also looks for whether they are wearing it correctly or not. It is also able to classify the people themselves, which allows the model to count the number of people that are in specific footage.
How I built it
We used Tensorflow and Keras to make a Machine Learning model that is able to classify and detect masks. We also used Flask which is a Python Framework to make the Backend and Frontend of the WebApp. On this app, we have a page where we can give a live demo of how our Machine Learning Model works.
Challenges I ran into
We ran into many challenges during the course of the building, we had trouble with building the Machine Learning Model, some of the data were repetitive. This is why we had to come up with solutions like Data Augmentation to generate new images to make the model train accurately. On the WebApp we have lots of errors with different parts of code not working, and some files not linking with others. One big problem was that it took us very long to find out how to solve the linking issue with the CSS folder.
Log in or sign up for Devpost to join the conversation.