OCR text recognition from images

dimonier / tg2obsidian

This script pulls new messages from a Telegram group and puts them into Obsidian vault on a local machine

MIT License

94 stars 22 forks source link

OCR text recognition from images #13

Open mikkovedru opened 1 year ago

mikkovedru commented 1 year ago

We already have voice recognition from audio messages.

It would also be useful to have text in images automatically recognized.

Does anyone know any good free OCR libraries?

dimonier commented 1 year ago

@mikkovedru I've heard about an OCR module for Python, but... do you really have such a necessity?

mikkovedru commented 1 year ago

@dimonier Yes. I save a lot of images (memes, screenshots with quotes, screenshots of messages, screenshots of articles) with text in them and would like to search that text (however imperfect the recognition).

I researched options and it seems that https://github.com/tesseract-ocr/tesseract is the way to go.

An example library:

https://pypi.org/project/pytesseract/
https://www.geeksforgeeks.org/text-localization-detection-and-recognition-using-pytesseract/ Seems easy enough.