What it does
The bot extracts text and reads it from the last image sent where the bot is called.
It currently supports English and Arabic.
How I built it
- Used python discord.py package to build the bot
- OCR model is Google's tesseract 4
- Used pytesseract package to interact with the model
- Deployed using Heroku and github repository
What I learned
It's my first time creating and deploying a bot, but deploying it was a bit difficult due to the need of tesseract engine for the pytesseract package to use. It's also my first time using a trained model for a project of mine.
It's my first time to participate in a hackathon, which fostered my skill in technical communication
and I learned how the diversity in a community benefits a everyone filling knowledge gaps.
What's next?
There are many features with very promising potential like: detecting swear words in images,
supporting more languages and adding the ability to translate images.
Log in or sign up for Devpost to join the conversation.