We are a group of meme-lovers. We realized that many memes are in image format and that people who are visually impaired may not be able to enjoy them as we do. Thus, we decided to build a tool to help those people enjoy the same memes that we know and love.
What it does
Meme Reader is a Chrome extension that reads aloud the text in images found on websites. While the user is browsing websites, Meme Reader will look for images on the page and read out any text associated with it.
How we built it
Back-end: We used Java with the Spring Boot framework to communicate with the front-end and receive image URLs, as well as the Google Cloud Vision API to produce text from the images.
Challenges we ran into
We had difficulties setting up Spring Boot and Google Cloud Vision API. We also ran into problems with passing information back and forth between the front-end and back-end.
Accomplishments that we're proud of
Learning to use new tools in a limited amount of time, as well as collaborating with others to build a project together.
What we learned
On the technical side, we learned how to use Google Cloud API in our project. Teamwork-wise, we progressively got better at communicating our goals and progress to each other. Sometimes if your program doesn't run, compile it again and maybe it'll be nicer. plz no mad ty O(no), O(my)
What's next for Meme Reader
The next step for Meme Reader is to train our model, such that images, which are categorized as memes, are properly filtered out from the websites and described with more precision.