W dniu piątek, 18 stycznia 2013 05:08:31 UTC+1 użytkownik Quan Nguyen napisał: > > Confidence may already be low, or even wrong -- that's why you need > training. Use a box editor to help you visually inspect and correct errors. > > I am assuming situation in which I have e.g. old German document which has a few characters different than modern German. I will generate boxes using modern German profile thanks to this most of the character will be recognized correctly, only a few old once will require correction. If I would have confidence in box file I could automatically filter out those which require more attention than the rest.
When you train FineReader you are only correcting characters with poor confidence. Is there a flag to get confidence into box file? regards, Adam -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en
