Emotional Intelligenze

This is the frontend once a valid url is supplied
This will be the photo downloaded alongside for reference of the ids.

Inspiration

We were inspired by the difficulties faced by teachers during the pandemic. Moving forward, online classes might become more frequent, thus requiring a more concrete solution. This was our main inspiration

What it does

Emotional Intelligenze takes in links(URL) of recorded zoom tutorials and analyzes the video to study the emotions of all students. It returns data in a number of beautiful and easy-to-understand bar charts which will help the teacher to monitor the students as time progresses during each class.

How we built it

We built the backend using Flask and Azure's face API to analyze each faces. The frontend was built using Reactjs.

Challenges we ran into

Since we had to work with the free-tier of Azure Face API, the number of API calls we could make per minute were limited. As a result, we had to come up with innovative ways to analyze just specific frames in a video so as to not exceed the maximum number of calls. We also had issues with rendering and sending images to the frontend, which we solved via various methods.

Accomplishments that we are proud of

Making the Face API work for the entire duration of video given all the limitations that we had was definitely the accomplishment we are most proud of. Performing analytics on this videos and rendering the huge number of graphs was also a tough task that we are proud of.

What we learned

We learned a lot about working with photos and videos on python. Also, the difficulties resulting from using different languages for the frontend and backend was apparent later in the project timeline. Such technical difficulties allowed us to learn a lot.