Is there a way to figure out how does tesseract calculate confidence levels for characters or words. As of now if we observe we are getting higher confidence even though the text is wrong, lower confidence even though the text is correct. So it might be helpful if we know. And is there anyway to tweak the process and retrain it?
-- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/4e3382a8-364e-4d9f-9db7-6e28b5433eb3%40googlegroups.com.
