The main inspiration for our project is the trouble students have to go through everytime they forget a book at school. Whether it's by dealing with images of bad quality or by having to constantly change between pictures sent by a peer.

What it does

Our project brings a unique solution by converting many images of a book into a beautiful, easily readible PDF for the user.

How we built it

Our frontend sends pictures to our backend, then detecting the text through Google Cloud Vision, we convert the total text into PDF.

Challenges we ran into

Backend blob/base64 implementation.

Accomplishments that we're proud of

It works!

What we learned

How to use blobs and base64.

What's next for Image-2-PDF

The next step for our program is audio recording. We would like for users to be able to read parts of their book aloud. Other users could then rate the audio snippets and the site could eventually offer open-source audiobooks.

Built With

Share this project: