This project was inspired by the npm library is-thirteen

What it does

Processes any type of input (image, speech, text) and determines whether it is CMU.

How we built it

Built on Node.js with image recognition through Google reverse image search and speech recognition through Microsoft Azure, as well as with in order to facilitate real time communication between the client and server.

Challenges we ran into

Getting the correct output from speech to text, accounting for statement negation, as well as accounting for large variety in inputs.

Accomplishments that we're proud of

Implementing a large variety of input recognition in a short time, as well as displaying real-time status updates to the user.

What we learned

How to use Microsoft Azure for development, as well as more complex topics in asynchronity..

What's next for is-cmu

Applications in detecting copyright infringement.

Share this project: