We want to help everyone to be able to communicate with each other.
What it does
Translates sign-language into American-English audio
How we built it
We use the camera to record the movements of the hands. Then we use machine learning and computer vision to match the patterns with English words.
Challenges we ran into
Limited time and hardware resources
Accomplishments that we're proud of
Most of us are new to computer vision and machine learning and with time and technology limit, we could still be able to reach our goal
What we learned
Through trials and errors, we've learned how different kinds of computer vision and machine learning algorithms work and successfully apply those algorithms to our project.
What's next for MagicHand
We will continue in this research project to increase the number of words in the dictionary and make the recognition more stable. Our goal is to help as many people as possible.