@TranslateScience @xldrkp i saw ocrmypdf:...

@TranslateScience @xldrkp i saw ocrmypdf: https://ocrmypdf.readthedocs.io/en/latest/index.html in my timeline, it uses the Tesseract framework and then puts the OCR back in the PDF.

Like 25 Jan 2022 at 20:16 | Wall-to-wall | Open on social.linux.pizza

2 comments

@amael
Tesseract works reasonably well with text, but not so much with equations, if I recall. It would need some manual cleanup.

Zotero-OCR plugin integrates with Tesseract.
@TranslateScience @xldrkp

26 Jan 2022 at 4:42 | Open on fediscience.org

Thanks for that hint, didn't know about this integration.

26 Jan 2022 at 8:08 | Open on scholar.social