Inspiration
We were inspired by the United Nations' goals for sustainable development while working on this project. One goal in particular stood out to us. This was SDG 12 "responsible consumption and production." We knew that we wanted to build something that would help the individual user and as a result, we came upon the idea of making those annoying clothing tags easier to understand.
What it does
Our project allows users to upload their clothing tags and provides an AI-generated summary of the clothing tag symbols and corresponding care instructions on each uploaded tag.
How we built it
We used a Nodejs frontend with a Python/Flask backend to implement our project. We also used Google's Gemini API to create concise summaries and for icon recognition on the tags.
Challenges we ran into
There were a few hurdles during the implementation process. Initially, we used Google's AutoML alongside cloud vision to train an algorithm on a dataset of care symbols however it proved to be challenging since the trained algorithm was good at recognizing individual icons but not a collection as is present on most clothing tags. So we decided to pivot to just using Gemini.
Accomplishments that we're proud of
We're proud of the fact that each one of us was working with a framework that we hadn't worked extensively with and this became a good learning opportunity for us. We are also proud of the potential social impact a program like TagScan can have since overconsumption of limited resources is detrimental to the planet and doing as little as making sure our clothes are taken care of can help them last longer and in turn have an impact on our overall carbon footprint.
What we learned
We learned how to build with Node on this project which was a framework foreign to most of us. We also explored the numerous Google APIs available to developers and learned that there are a lot of projects we could bring to life with Google's software.
What's next for TagScan
The next step for TagScan is to build a user database to store user information so that their scans are available to them whenever it's time to load the washer.
Log in or sign up for Devpost to join the conversation.