Hello David, Yesterday, a colleague of mine figured out that when a Tesseract variable called classify_enable_learning is disabled, it no longer gives different results.
I think these variables are stated here with their descriptions --> http://www.sk-spell.sk.cx/tesseract-ocr-parameters-in-302-version Regards On Thursday, September 28, 2017 at 6:20:50 PM UTC+3, David Sixela wrote: > > I had the same problem, getting different outputs between 3.04 and 3.05, > the only solution i've found was to upgrade to tesseract 4.0 > > Le jeudi 28 septembre 2017 16:47:06 UTC+2, Canberk Ozdemir a écrit : >> >> Hello all, >> >> I couldn't find any post related to the subject. Is it possible that >> Tesseract can -slightly- give different outputs running on the same image >> in different runs (with same configurations.) >> >> In some scanned documents having some noises, I get some different >> characters in outputs. I can say %95 of characters are the same. >> >> Regards, >> >> Canberk >> > -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/099b4830-1fe3-4aa7-93fd-43a7c4b8f05e%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
