Please see https://github.com/tesseract-ocr/tesseract/issues/654#issuecomment-274574951 for more details about LSTM training.
ShreeDevi ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Mon, Mar 13, 2017 at 8:35 PM, Martin Fadrhons <martin.fadrh...@gmail.com> wrote: > Hi, > > I was trying to train tesseract 4 to recognize trademark symbol ™. I was > following examples on wiki: > https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00--- > Replacing-Top-Layer-Example > https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00--- > Replace-Top-Layer > > I use German language for testing. With the traineddata from repository > the trademark symbol is usually recognized as '" or some other variation of > quotes. So I created training text that includes trademark symbol and > started the training process. I replaced only the top layer as it is in the > example, however the trademark symbol is still not recognized properly. > With the newly generated traineddata the symbol is recognized as TM. I have > several questions. > > 1. Is it needed to replace more layers? > 2. How large should be the training text? (mine is based on the one that > is in langdata/deu directory) > 3. I noticed that there are symbols © and ®. Why is trademark symbol > missing? > > Any other hints would be appreciated. > > Thank you for your time, > Martin > > P.S. Also thanks for the great work on the tesseract OCR. > > -- > 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/8c1c548b-3c39-4622-99be-0bfbe5f486cb% > 40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/8c1c548b-3c39-4622-99be-0bfbe5f486cb%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- 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/CAG2NduWpppKHEU%2BEiudoZgiKbEo-qd%2BZUvpB1zPN2TwEGVPgFg%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
