PicScribe

Main Screen
Uploaded and Analyzed File

Inspiration

We all have lots of random notes from previous classes, that are useless on their own lying around in our homes.

What it does

Our app uses OCR technology and Pinata API to analyze written notes, and pictures of lectures to compile an organized pdf of all the information.

How we built it

We used a Tech Stack. For front end, we used React, and Tailwind CSS. For back end we used Node.js, Pinata SDK, Samba Nova Cloud, and Google Cloud Vision API.

Challenges we ran into

We ran into issues with our devices being unable to efficiently program onto the mobile app format, so we decided to convert to a web app.

Accomplishments that we're proud of

Implementing OCR was a very crucial step to our overall plan, and learning how to do so and then doing it was one of our greatest accomplishments.

What we learned

We learned how coordinate on GitHub and perform commands with our laptops in order for all of us to work on the project.

What's next for PicScribe

We hope to perfect our core mechanism of uploading files and converting with less restrictions. We also want to put more time and effort into making the web app design cleaner and more distinct, and providing more tools for the user.