how did you do it? i am having the same problem On Sunday, September 23, 2018 at 12:32:32 AM UTC+8, Erikas Rudinskas wrote: > > Hi, > > I am trying to find a way on how to define my own words list for > tesseract. I want to use only my defined words and guess the most likely > one. > > So I have a small image with a single word in it. I process it with this > command in order to get pure "black on white" type of image: > > $ convert -colorspace gray -auto-level -threshold 60% -type bilevel -depth > 8 *image.png newimage.png* > > Then I try to extract a single word from that image: > > $ tesseract *newimage.png* -psm 8 stdout > > and it returns a single word (which is great), but slightly incorrect: > > *Expectation*: nieko > *Result*: flieko > > I've just spent like 5+ hours trying to find any documentation or tutorial > on how to set a whitelist dictionary for words recognition. Any tips on > that? >
-- 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/334e3a67-a6fa-4776-aa2d-c53fbbfdbe34%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
