Thanks for answer. I forgot to say that I do not use API but just command line. Regards
Debian 4.0 Tesseract 2.03 On Mar 17, 7:32 pm, "Albert Law" <[email protected]> wrote: > Hi, > > I would look through each letter in your word to get the word's confidence. > So something like this: > > ETEXT_DESC* results = tess->Recognize_all_Words(); > for (int iter = 0; iter < results->count; iter++) { > const EANYCODE_CHAR* ch = &results->text[iter]; > if (255 > ch->confidence) { > // TODO: reject the letter and thus the whole word associated with it > } > > } > > - > Albert > > -----Original Message----- > From: [email protected] [mailto:[email protected]] > On Behalf Of bergheil > Sent: Tuesday, March 17, 2009 13:23 > To: tesseract-ocr > Subject: How to set Confidence in tesseract > > Dear Tesser-Expert, > in the forum I found some information about confidence value for a > recognized word as integer between 1 to 255 (1 is the best). > Is it possibile to select that value running tesseract? > I building a training for Micr-CMC7 number and I would like the 100% > accurancy, so I prefer that tesseract reject a word instead recognize > with a low confidence. > Thanks in advice. Saluti a tutti --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en -~----------~----~----~----~------~----~------~--~---
