We thought about how subway ticketing works, through automated systems that let people through. We thought it would be a good idea to have this for masks, since it could be used to make sure each person in a building is entering safely.
What it does
This program detects whether the person standing in front of the camera is wearing a mask or not.
How we built it
The image recognition api is from IBM, and we trained it with many pictures of each of us. We used opencv to get a video stream from our webcam.
Challenges we ran into
Different lighting conditions affected the accuracy of our program, and we had difficulties training the image recognition models when we tried using TensorFlow, so we switched to IBM Watson, which trains the image recognition software in a cloud server, making it feasible for us to build this program within 4 hours.
Accomplishments that we're proud of
We are proud of successfully creating this program within the time limit, considering we had to give up on our previous ideas multiple times due to various problems.
What we learned
We should research all of our ideas thoroughly before attempting them.
What's next for Wear mask?
We plan to install our software on every school in the United States, and we will become billionaires.