Hacker News Reader

Comment by Nimsical | Hacker News Reader

This is cool!

Wondering what you're using for OCR?

  For developers: Copyfish is published under the
  GPL open-source license. As OCR software, it uses
  the free OCR API from https://ocr.space/

So, to answer the question mentioned above, the document storing the text is sent to an off-site server (https://ocr.space/) which does the OCR and returns the results.

And what lib is using ocr.space for OCR?

I suspect they're using Tesseract as they've written a gui for it ( https://ocr.space/blog/p/free-ocr-windows.html ) but there's no way to find more.

https://github.com/A9T9/Free-OCR-Software

Based on this github they might be using the microsoft ocr library.

I guess it auto defaults to English then? Running Tesseract on Scandinavian texts gives AAO instead of ÅÄÖ in my experience if you don't supply the correct language training set. That's quite the hen and the egg problem. Can't language identify without the text can't get the text without the right language identified.

Reply on news.ycombinator.com