Image-Text Recognition

Inspiration

We found it very frustrating when I could not copy text from some PDFs. So we decided to create this web app that could recognize text in images.

What it does

This web app allows the user to either upload an image, or draw images on a canvas. It will then try to extract text from the image or the canvas

How we built it

We used ReactJS and Chakra-UI for the front-end. We used tesseract for the text recognition and react-canvas-draw to help us out with the canvas.

Challenges we ran into

The text recognition did not work very well, so we had to try many different frameworks and compared them to each other.

Accomplishments that we're proud of

For most of us, this was our first time using GitHub with multiple people. But we managed to work well together.

What we learned

How to use tesseract, and basic handwriting recognition concepts.

What's next for Text Recognition

Creating a more advanced model using python, which can be linked to the front-end using a Django API.

Authors

👤 Hugo

• Github: @Hugo-WB
• Discord: @hugo71#7309
• Skill: Intermediate 🐘

👤 Justin

• Github: @Justanhy
• Discord: @justanhy#0209
• Skill: Beginner 🐭

👤 Alek

• Github: @aleksanderdukaczewski
• Discord: @alek.d1#9439
• Skill: Beginner 🐭

More information is available in our repo's readme.md

Built With

• chakraui
• react
• tesseractjs