In addition to Macrons, I will also request addition of other accented letters for Indic text transliterations.
Ray, Will using -l eng+<new training> be the best way to handle these? I tried to do an add layer training, but the recognition is worse, since I did not use many fonts for the test training. I am attaching the training sample I used. Thanks. Please see the following links for the transliteration schemes showing the letters to be included. https://en.wikipedia.org/wiki/National_Library_at_Kolkata_romanisation https://en.wikipedia.org/wiki/International_Alphabet_of_Sanskrit_Transliteration https://en.wikipedia.org/wiki/ISO_15919 Here are various sites that have Sanskrit corpus in transliteration. https://github.com/cltk/sanskrit_text_dcs http://sarit.indology.info/exist/apps/sarit/works/ (IAST) You can see http://gretil.sub.uni-goettingen.de/gretil_elib/Suk9441__Sukthankar_MemorialEd_1_CritStud_Mbh_1944.pdf eg. pages 87-91 - showing use of both devanagari script as well as trasliterated sanskrit as part of mainly English text ShreeDevi ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Fri, Jan 20, 2017 at 10:52 AM, <[email protected]> wrote: > Dear all, > I frequently use Tesseract (3.04) and it’s great. > Still, I can’t find a way to get Tesseract recognize macrons (āĀēĒīĪōŌūŪ). > There was a discussion > <https://groups.google.com/forum/#!searchin/tesseract-ocr/macron$20tesseract/tesseract-ocr/ZlQ3xlz_4As/XpnhTSlV3n8J> > here about it 5 years ago but at the time, there wasn’t much of a solution. > Things may have changed since then and I’m wondering if somebody would > have some hints. > Macrons are used among other things when doing recognition from japanese > transcribed in latin alphabet (rōmaji). > Thanks in advance for all possible ideas. > For now, using fra or deu as one of the language, I get ô or ö… > Best, > Nicolas > > -- > 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 [email protected]. > To post to this group, send email to [email protected]. > 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/74805b35-b70b-47f8-b287-ddcd34d216e2% > 40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/74805b35-b70b-47f8-b287-ddcd34d216e2%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 [email protected]. To post to this group, send email to [email protected]. 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/CAG2NduWBmmbBLEUBST3j%3DbgwZZnKa_GeceOjPfOhC5%2B70htdbg%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
san_latn.training_text
Description: Binary data
