Scan stuff, and examine the picture to find language and store that as usable text characters.
I could never get any of this working properly.
-
Optical Character Recognition
- https://github.com/tesseract-ocr/tesseract/wiki/User-Projects-%E2%80%93-3rdParty
- https://github.com/tesseract-ocr/tesseract
-
http://capture2text.sourceforge.net/
- 2019-04-10 - Seems to work quite well. Tested on printed text.