An AI Tool to record expressions of users as they watch a video and then visualize the funniest parts of it!
APACHE-2.0 License
Hemeur is an AI Tool to record facial expressions of users as they watch a video and then visualize the most funny parts of it!
It watches users as they watch a video, and logs when the users smile.
Insights can be gathered from collected data!
​ face-api.js with TensorflowJS detects the expressions, sends a POST to the backend.
​ NodeJS writes the expressions to RabbitMQ
​ Data from the MQ is now moved over to the database for storage and popped off the queue.
​ The expressions and their positions in the video are noted down, and visualized in the UI.
Screen jiggles when you giggle!
Chat Panel, pops every time someone laughs (or talks)
Links above the messages, allow to skip to the funny bits
Facial Recognition is done in the browser itself. No video ever leaves your device.
Hemuer, is powered by RabbitMQ, this adds real-time chat support! Transactions go to the MQ first, then are stored in the database.
This keeps things up and running even during high traffic!
The Stats page displays Smiles vs their Position in Video. This can be used to find, seek and skip to the funniest bits of the video.
This is where I nag you for stars... 😪 Can I get a star?
docker-compose up --build
Deploy the NodeJS App on Heroku
This should work right out of the box, if you follow the current repo struct.
Create a MQ on CloudAMQP and add the as an environment variable. AMQ_URL
Create a MongoDB add on for the App
Boom! Done
This project is licensed under the Apache License - see the LICENSE.md file for details