Inspiration
We all understand how easy it should be to take a few seconds to correctly separate our trash, but sometimes we still don't know what goes where after a few minutes. Improper waste disposal leads to pollution, affecting our health, but also affects our wallets, given fines when we incorrectly dispose of trash. We came up with Safe Garbage to make it easier for people to properly dispose of their waste.
What it does
Safe Garbage takes a picture of your item and is trained to determine what material it is.
How we built it
We used Figma to make our own icons/visualizations and made a basic template to follow for our website. We used JavaScript and React to build the frontend, and trained our data using a Kaggle dataset and Jupyter Notebook.
Challenges we ran into
This was a project full of firsts! It was the first time we trained using images, and also incorporating features like webcam and its functions. However, one challenge that remained was being able to tie the two parts together. We needed to use the trained model behaviour in our web application to work with the webcam in order to do the functions we wanted to do.
Accomplishments that we're proud of
We're proud that we were able to submit something!
What we learned
We learned more about convolutional networks and became more familiar with JavaScript and React in general.
What's next for Safe Garbage
Safe Garbage's next steps are to combine the two parts (trained model and web app), then train it to be able to also distinguish paper, and compost, and then flesh out the design!
Log in or sign up for Devpost to join the conversation.