Hello I am currently trying to improve tesseracts recognition rate by messing with the traineddata files. I have two questions:
1. I have to read many different fonts, is it useful to train tesseract in as many fonts as possible or is there a limit to what is useful? 2. I have read that the training text shouldn't just be "ABCDEFG...", that it should be more realistic. In my case, I have to read Adress lists. Would tesseract be better if my training text is also an adress list or is "The big brown fox..." enough? thanks for the help! -- -- 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/d/optout.
