I first had the idea when I acquired a lot of cool older stickers. I originally wanted to make a database for all stickers ever created. After that the idea morphed into a way for users to show what stickers they had and the amount they had, almost making it a Craigslist for stickers. Then the idea switched to encompass all swag for any type of events.
What it does
Unfortunately since we all had homework and tests due on Monday we couldn't actually do good work on the project. The only part that works as intended is the image classifier that was built to recognize stickers from hackathons. It can recognize 19 different stickers at the moment, but it should be able to handle much more.
How I built it
Instead of taking hundreds of pictures of each sticker I took one good picture of each one than ran it through a script that rotated it and distorted it to simulate different camera angles. It could generate upto 28,000 images from a single source image, but I only used 2,800 of each sticker to train.
Challenges I ran into
Using Google Cloud Deep Learning took a bit longer than it should've
Accomplishments that I'm proud of
We're able to take a picture of a sticker and identify it.
What I learned
More about the Google Cloud Platform and tensorflow.
What's next for swagOverflow
Probably actually create a website and mobile app. Also add more stickers to the model.