2018-06-22 11:41 GMT+02:00 blues <blues...@gvdigital.com>: > thanks for your reply, Lorenzo > I will test more samples to see if it only happens with holes. > if so, probably just do a morph hole filling before ocr as workaround for > now. > > btw, I'm using version 3.x. Is there a chance 4.x handles this issue > better? >
I assumed you were using the 4.x version and that you attached your trained data file. Yes, I expect 4.x to be more robust on these things and maybe overall but I've never seen any side by side comparison (I'd like to see one). It's quite easy to try as see. You may also do custom fine tuning training on your data (if you have classified data). Lorenzo -- 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 post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAMgOLLx0gAu017b7EKUnQVEHFHkzo%3D_rh8hQwPwXK1rABAg_Yg%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
