On Wed, Apr 17, 2013 at 10:36 PM, Robert Komar <rko...@telus.net> wrote:
> On Wed, 17 Apr 2013, Sven Pedersen wrote: > > This is covered in theFAQ:https://code.google.** >> com/p/tesseract-ocr/wiki/FAQ#**How_<https://code.google.com/p/tesseract-ocr/wiki/FAQ#How_> >> do_I_add_just_one_character_**or_one_font_to_my_favourite_l >> >> ang >> >> which links to the training WIKI >> https://code.google.com/p/**tesseract-ocr/wiki/**TrainingTess<https://code.google.com/p/tesseract-ocr/wiki/TrainingTess> >> eract3 >> >> --Sven >> > > I've often wondered about this lack of being able to add > trained data to an existing set. Is there some fundamental > reason for it, or is it just that the provided tools don't > handle it? If the latter, how hard would it be to come > up with some new tools for doing so? It seems like a > worthy endeavour for someone. > > ;-) I learned that if I want something I need to do it by myself and not wait that "someone" will do it. > On the other hand, I can't count the number of people > who want to add new trained data in the hopes of > improving recognition, when it's their images that > are the cause of the problems. Not having such tools > at least saves them from wasting their effort ;). > > I remember one user post, that he wasted a lot of time with effort to create better data that (already) provided by Google. Than he found out that he just need to preprocess input image to get great result ;-) I am not able to say whether this is general truth (there are open issues for several language e.g. because of missing symbols), but I would not encourage people for training of new font (at least not common font) for existing language data. Rob Komar > > > -- > -- > You received this message because you are subscribed to the Google > Groups "tesseract-ocr" group. > To post to this group, send email to tesseract-ocr@googlegroups.com > To unsubscribe from this group, send email to > tesseract-ocr+unsubscribe@**googlegroups.com<tesseract-ocr%2bunsubscr...@googlegroups.com> > For more options, visit this group at > http://groups.google.com/**group/tesseract-ocr?hl=en<http://groups.google.com/group/tesseract-ocr?hl=en> > > --- 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+unsubscribe@**googlegroups.com<tesseract-ocr%2bunsubscr...@googlegroups.com> > . > For more options, visit > https://groups.google.com/**groups/opt_out<https://groups.google.com/groups/opt_out> > . > > > -- -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to tesseract-ocr@googlegroups.com To unsubscribe from this group, send email to tesseract-ocr+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- 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. For more options, visit https://groups.google.com/groups/opt_out.