tesseract language setting
|Related pages:||#10: OCR - optical character recognition|
I did a first test scan of a page of a French book.
The result was about 95% correct, the mistakes being with the same accented characters.
I read somewhere that tesseract could be trained, but I have not found out how, yet....
Maybe there are language settings or character sets to take into consideration...
I was simply missing the
-l fralanguage setting.
Automatically closed -- issue fixed for 2 weeks with no activity.