Thanks, Zdenko, because tesseract has not "yet" a well working well trained Fraktur version around, ...not even the version form the university of Mannheim
...that's why I said to myself i need to learn this and do it myself... I come from 30 years of graphical background, and studied Physics before,.... which will help here for sure,..... but I need a massive amount fo guidance and pointers to start this... naturally I will read through your links,.... Thanks for those !! On Wednesday, October 2, 2019 at 4:54:08 PM UTC+2, zdenop wrote: > > If you are novice, that most stupid way is to start (and waste time) with > training. > Spend some time with research - maybe you will find tesseract if already > trained for Fraktur. Did you try to use deu_frak.traineddata[1]? > > If you got still bad result please read wiki [2] , or post example image. > There are some known[3] issues, not sure how critical it will be for you. > > [1] > https://github.com/tesseract-ocr/tessdata/blob/master/deu_frak.traineddata > [2] https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality > [3] > https://github.com/tesseract-ocr/tessdata/issues?utf8=%E2%9C%93&q=is%3Aissue+is%3Aopen+Fraktur > > Zdenko > > > st 2. 10. 2019 o 11:58 Akos Simon <phot...@gmail.com <javascript:>> > napísal(a): > >> training tesseract ........ >> >> Tesseract it is an OCR TEXT recognition software that can be trained. >> I have gotten as far as installing Tesseract on my iMac with a GUI, but >> there are no options after I launch and look at a scanned image with >> Fraktur Type/fonts, on that GUI, to train Tesseract, and to >> make TesseractOCR better in recognizing this very difficult, very very old >> European font, which was used in the last 1000 years, but mostly before >> 1900. >> >> So I wonder how can one now train that software.... as I mentioned, i am >> a novice,... only started 3 days ago ,.... and am myself very confused >> here, >> >> hopefully, this will change with your help ? .. ;) >> >> Thanks, Zdenko !! >> >> >> >> >> On Wednesday, October 2, 2019 at 7:38:08 AM UTC+2, zdenop wrote: >>> >>> Why do you think training will help you? What other option you have >>> tried? >>> >>> Zdenko >>> >>> >>> st 2. 10. 2019 o 7:26 Akos Simon <phot...@gmail.com> napísal(a): >>> >>>> Fraktur Fonts OCR recognition with Tesseract OCR is what I am looking >>>> for,.... I installed VietOCR v5.5.2 and Tesseract 4.1.0 on my mac, and now >>>> I am trying to find help on how to train it better.... there are too many >>>> OCR errors... >>>> >>>> How would I go about training the software? Can anyone help? >>>> >>>> I am a total retard, ...sadly,.... and I do not even know how I was >>>> able to install the two components so far..... and this training step is >>>> nowhere explained >>>> >>>> Any help into the right direction would greatly be appreciated >>>> >>>> -- >>>> 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 tesser...@googlegroups.com. >>>> To view this discussion on the web visit >>>> https://groups.google.com/d/msgid/tesseract-ocr/cb69ba1b-7539-4157-9b0f-698b82466f1b%40googlegroups.com >>>> >>>> <https://groups.google.com/d/msgid/tesseract-ocr/cb69ba1b-7539-4157-9b0f-698b82466f1b%40googlegroups.com?utm_medium=email&utm_source=footer> >>>> . >>>> >>> -- >> 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 tesser...@googlegroups.com <javascript:>. >> To view this discussion on the web visit >> https://groups.google.com/d/msgid/tesseract-ocr/de4235ca-a19d-49f1-99b3-f756bdae6fb2%40googlegroups.com >> >> <https://groups.google.com/d/msgid/tesseract-ocr/de4235ca-a19d-49f1-99b3-f756bdae6fb2%40googlegroups.com?utm_medium=email&utm_source=footer> >> . >> > -- 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/725db09f-1f5f-4bdc-a810-1792b30c2f07%40googlegroups.com.
