With the training code out, interest should really pick up as languages other than English as supported. There are some interesting projects out there - people probing tess'es capabilities and operations to see where it can be used to fill a void.
Cheers,
Fil
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi, I'm a Informatics Engineering student from Portugal and I'm about to start a work around Tesseract/Gnome Scan. Since Tesseract, has I heard, doesn't support any other language than English, I was thinking about developing the Portuguese support.
The problem is that I don't know how/where to start... could indicate me some direction? ;)
Thanx,
Jay
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Thank you Thank you Thank you!
With the training code out, interest should really pick up as languages other than English as supported. There are some interesting projects out there - people probing tess'es capabilities and operations to see where it can be used to fill a void.
Cheers,
Fil
Hi, I'm a Informatics Engineering student from Portugal and I'm about to start a work around Tesseract/Gnome Scan. Since Tesseract, has I heard, doesn't support any other language than English, I was thinking about developing the Portuguese support.
The problem is that I don't know how/where to start... could indicate me some direction? ;)
Thanx,
Jay
See http://tesseract-ocr.repairfaq.org/ and then Ray Smith's comments on this matter at http://sourceforge.net/forum/message.php?msg_id=4023187 Basically, V1.03 offers the training code back in the release (it was not in 1.02) but the documentation is all in Ray's head :-)
That means that it will take some time for other languages to be supported.
You are not the only one looking into uniting Tess with Gnome AND also adding another language, these folks are also working on this:
* http://209.85.165.104/search?q=cache:XJ5Q_1SlCUwJ:mail.gnome.org/archives/desktop-devel-list/2006-November/msg00158.html+%2Btesseract+%2Bocr&hl=en&ct=clnk&cd=67&gl=us&client=firefox-a
* http://lists.arabeyes.org/archives/developer/2006/September/msg00013.html
and
* http://article.gmane.org/gmane.comp.gnome.desktop/31239/match=
Cheers,
Fil