While brainstorming with our team, we discovered that all of us were extremely interested in learning and using Google Vision.
What it does
Our web application allows users to upload a photo of an animal - this may be an animal they found on the street, faced while hiking, or discovered while exploring. Our web application then uses the Google Vision API to detect the name and species of the particular animal and return it to the user. Additionally, our app will provide the user with names, addresses, and numbers on nearby animal centers.
How we built it
We built this by utilizing the Google Vision API, Google Maps API, and the Google Places API. With these tools, we were able to combine a few components to make a user-friendly web application. The backend is mostly designed in Python while the frontend design is built in HTML and CSS.
Challenges we ran into
Accomplishments that we're proud of
We are proud of the web application we have created. We're happy with the results of our backend and love the frontend design.
What we learned
For most of us, this is our first hackathon or the first time creating a project with a team. We learned a ton of new things. We became familiar with the Google Cloud API and its documentation and implementation. For one of our teammates, this is the first time ever using or working with an API. Google's detailed documentation allowed easier learning. Not only that but, we learned how to work in a team, compromise with ideas, and help each other along the way when we didn't understand things.
What's next for WhatIsThat?!
In the future, we would like to give information on what to do when you see an animal. For example, if the user snaps a shot of a poisonous snake, we want our app to give it what to do when they see this or how to respond in emergency situations. This web application has many paths and additions that can be made to make it even more useful. However, with the time constraint, we felt that we implemented everything we could.