Hi, I have searched a lot about --user-words option in the internet to know more about it, but unsuccessfully.
I'am treating a simple case with spanish trained data doing : api/tesseract -l spa --psm 6 test.png output tessdata/configs/unlv; I expect the following output from my image : numero de documento but instead, i'm getting mumsro ne odcumento It's a little bit frustrating because that words don't exist in spanish. So i define a spa.user-words file like : documento numero and run the following command line : api/tesseract --user-words spa.user_words -l spa --psm 6 test.png output tessdata/configs/unlv; But i still got bad ocr numero de documento Am I using --user-words option in the right way? Can i get wanted results using this option? Many thanks PS : I have also uncombine spa.traineddata , add 'documento' and 'numero' to the spa.freq-dawg, and recombine but without any improvment. -- 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/17ea03e9-60a1-401b-969e-3e9eac13dbf6%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
