I am not sure how it works myself. I got the best results when I made a dawg list (See https://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3 under Dictionary Data). Pretty much, if you have a list of words to use, Do wordlist2dawg frequent_words_list lang.freq-dawg lang.unicharset , and include this file when you do your combine_tessdata.
On Thursday, May 23, 2013 5:34:02 PM UTC+2, newbie wrote: > > Hello all, > > I have a concern about the user word list in Tesseract (eng.user-words). I > have no idea how to know if it is working or not. Could anyone advise me > how to test the user words is working properly? I would like to use this > user words, but don't see it works, then it confuses me. > > One more concern,in Tesseract 3.02, it allows to set multiple language > when Tesseract init i.e. I can set eng+deu. But when I would like to init > Tesseract with eng.user-words, the Tesseract seems to require for deu also. > Am I correct? If so, how we can init just specified user-words list? > > Thanks. > -- -- 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 --- 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]. For more options, visit https://groups.google.com/groups/opt_out.
