Seeing how much paper is used in the government and the difficulty of transitioning to paperless.

What it does

Doc-Visual marks regions on a document that contain useful data (Name, Date, etc) and uses OCR (optical character recognition) to save all of the data that is found in a digital form

How we built it

We used Google's cloud vision API to read the text. Python and Flask were used to construct the server that provides the website.

Challenges we ran into

Finding the best way to determine whether a word exists within a certain region or not.

Accomplishments that we're proud of

Successfully setting up and using Google Cloud to extract text from a document

What we learned

How to use the Google Cloud platform and how to use Flask to build websites

What's next for Doc Visual

Adapting it to scan more types documents so it can digitize all documents into a digital form

Share this project: