Recyclicat

Technica Hack

Our submission to Technica 2018.

This was a 24hr hackathon where we built a web app called 'Recyclicat' that scans pictures of trash items and helps the user classify them as recyclable or non-recyclable.

Motivation

USA is a world leader in most fields, including waste generation. As one of the most developed countries, it is important that it makes conscious efforts towards reducing the same.

We took a shot at the problem with first educating people about recycling by heloing them easily classify their trash. We also demoed a mock-up of a possibly gamified set-up where where the user is motivated to be more environmentally conscious during their purchases.

Built With

Submitted to

Technica Fall 2018
- Winner Best use of Machine Learning - Booz Allen Hamilton
- Winner Best use of Google Cloud Platform - MLH

Created by

I worked on creating the dataset and training a convolutional neural network! I managed to download a dataset of close to 3000 images classified into recyclable and non-recyclable. I cleaned and preprocessed the dataset, and wrote the machine learning model and did preliminary tests to check if the models looked promising

Radhika Nikam
I worked on the user experience and user interface design of the mobile application.

Meng Shi
UX / UI Product Designer
I worked on ideation, gamification elements and designing the interaction of user interface

Lu Meng
Poornima Haridas
RebeccaHom

Updates

Poornima Haridas started this project — Nov 11, 2018 03:38 AM EST

Leave feedback in the comments!

Log in or sign up for Devpost to join the conversation.