tesseract language setting

Tue, 04/13/2010 - 09:11 - augustin
Project:Linux software
Component:Miscellaneous
Category:support request
Priority:normal
Assigned:Unassigned
Status:closed
Related pages:#10: OCR - optical character recognition
Description

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....

Comments

#1

augustin - 04/13/2010 - 09:40
Related pages:+10: OCR - optical character recognition

wiki

#2

augustin - 04/13/2010 - 09:56

Maybe there are language settings or character sets to take into consideration...

#3

augustin - 05/31/2010 - 12:34
Title:How to train tesseract» tesseract language setting

I was simply missing the -l fra language setting.

#4

augustin - 05/31/2010 - 12:35
Status:active» fixed

#5

robot - 06/14/2010 - 17:10
Status:fixed» closed
Related pages:-10: OCR - optical character recognition

Automatically closed -- issue fixed for 2 weeks with no activity.