Feature Suggestion for OCR

Stirling-Tools / Stirling-PDF

#1 Locally hosted web application that allows you to perform various operations on PDF files

GNU General Public License v3.0

29.63k stars 2.17k forks source link

Open TheMattBin opened 1 month ago

TheMattBin commented 1 month ago

I think OCR feature is so far so good, some suggested PaddleOCR which is great as well. The following repo also do well for OCR, might consider as well, https://github.com/VikParuchuri/surya?tab=readme-ov-file

indigodelta commented 1 month ago

+1 from me. What we have now seems to be word recognition and , and make no sense of sentences or layout. Improving this would be great.