Did you try the latest .traineddata versions -- fast or best? https://github.com/tesseract-ocr/tesseract/wiki/Data-Files
On Friday, November 17, 2017 at 1:49:04 PM UTC-6, Marcello Galvão wrote: > > Hi, i have de same problem.. > Did you have any solution? > Thank you!! > > Em quarta-feira, 16 de agosto de 2017 14:10:49 UTC-3, Paulo Scardine > escreveu: >> >> I have the following image: >> >> >> <https://lh3.googleusercontent.com/-swcbZqlCZFY/WZR3d0zabzI/AAAAAAAALfc/nbhbpyQ60TggekPndQrO30bJmtG7RdSJACLcBGAs/s1600/tag.png> >> For version 3.04 I get the correct result: "Declaração de Nascido Vivo". >> >> For 4.0 I get "Declªrªç㺠de Nªscidº Vivº". >> >> What I have tried so far: >> >> - everything on the Improving the Quality >> <https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality> wiki >> article >> - messing with `tessedit_char_whitelist` and `tessedit_char_blacklist` >> - custom user word and pattern files >> >> Nothing made difference, I starting to think this may be a bug. >> >> I would appreciate advice on how to improve the diagnostic. >> >> Thanks in advance, >> -- >> Paulo >> > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. 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/7f011e85-29b0-4b38-8013-2d1592c2155c%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
