Seems like this is the parameter to add if you do not want the dictionary: -c load_system_dawg=0
On Tuesday, December 8, 2015 at 7:33:07 PM UTC+6, Pedro Moreira wrote: > Hello i am trying to recognize some text codes and i'm having some > problems. > One example: > i have a paper sheet with the string: > "5XqaLB" > when showing it all or some part to the camera the results are: > (original -> result) > > "5XqaLB" -> "5anLB" > "XqaLB" -> "anLB" > "qaLB" -> "qaLB" > "5Xq" -> "5Xq" > "5Xqa" -> "5an" > > The API replaces "Xqa" by "an" > > I found this problem with this string but there may be others with similar > results. > i assume this is somehow related to the API trying to guess the word. > So, my question is: how do i prevent tesseract from replace the chars it > detects? > > Thanks > -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/0db11d1a-f65d-416f-aa6c-0b07929d092f%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
