Hi there, So far I've been using https://github.com/Shreeshrii/tessdata_shreetest/blob/master/digits_comma.traineddata. Generally speaking, with very good results, much better than when using eng-best or eng-fast from standard tesseract repo. But, unfortunately, recently I came across some unrecognized characters when ocr-ing my data sets and it seems it's blocking further development of my software.
I tried to fine tune it myself, but unfortunately the results got worse :( So I'm looking for somebody willing to create a specialized traineddata for me. It would require a few additional characters added along to digits_comma.traineddata. I would want to achieve the same accuracy as when using digits_comma.traineddata. I'd be more than happy to pay premium for such work. Best Regards, Karol -- 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/551facd9-4126-4010-a2e2-20dca06211e7n%40googlegroups.com.
