In this screen-based game, everyone gets to act like a superhero-Spiderman, Ironman, and more! What could be better?! Everyone wishes they could be a superhero and this is their chance! With Comicall you can embody the spirit of your favorite characters by recreating their iconic poses. Get the whole group acting out the Marvel movie heroes and see who does it best. “Avengers, assemble!!!”

What it does

Comicall uses Teachable Machine Poses to create the machine learning code. We used machine learning to create a tool which recognizes the iconic poses of superheroes. In our current tool, users can pose in front of a webcam as heroes such as Hawkeye, Spiderman, Dr. Strange, and Iron Man and their poses will be identified with the respective superhero name. It recognizes four poses - so far, but we will add more Marvel characters in the future.

How we built it

For the front end we used HTML, CSS, JavaScript, and Bootstrap to create our website. Our backend database was created using MongoDB. We worked together to figure out what aesthetic and pictures we wanted to have our website showcase, and implemented everything with our front end tools. Our machine learning code is written in JavaScript and was trained used Google's Teachable Machine Poses.

Challenges we ran into

We tried to just use python, django, postgres, html/css and upload that code using heroku in our initial attempt. After spending a lot of time trying to configure our github to a heroku pipeline, we decided it would be easier to use MongoDB for our backend. Initially we wanted our machine learning code to be able to detect Marvel inspired hand signals and signs, but found out that it was easier to have our users show their full body poses for our ML to work.

Accomplishments that we're proud of

This was the first time we were able to combine the front end and back end successfully. We are also really proud of our machine-learning code, that was able to detect users, their poses and match them with their favorite Marvel characters.

What we learned

We spent a lot of time learning about pipelines for continuous integration and deployment of our code, and which tools would help us achieve it. In addition, we learned about the different types of databases. It was a lot to learn! Working with machine learning tools was also very interesting - we feel like we only reached the tip of the iceberg, and will definitely focus on learning more about ML after this hackathon.

What's next for Comicall

We would like to expand our website to include a mobile application, and to have additional features, like filters to allow users to take pictures of themselves in their Marvel gear. We would also like to eventually deploy our website.

Share this project: