Hello. To my knowledge there's nothing language-specific in it, so it ought to. I'll be happy to test it for you, you can send your files to my e-mail address.
On Apr 9, 4:43 am, 74yrs old <withblessi...@gmail.com> wrote: > Dear Michael Reimer, > I like to know whether your "DangAmbigs Generator" will work for Kannada > Language > On hearing from you, I shall forward sample kannada text(correct and > generated) for testing/evaluation at your end. > With regards, > -sriranga(76yrsold) > > On Wed, Apr 8, 2009 at 10:46 PM, Michael Reimer > <michael.rei...@gmail.com>wrote: > > > > > As part of my attempt to improve Tesseract's accuracy with a language > > model, I needed a better DangAmbigs file. To get one I made a utility > > that generates them empirically from any collection of correct and > > generated texts (such as the UNLV test set and Tesseract's output from > > the tests). I believe this should be useful to other Tesseract > > users. You can find it here, with a more detailed description: > > >http://www.cs.toronto.edu/~mreimer/tesseract.html<http://www.cs.toronto.edu/%7Emreimer/tesseract.html> > > > To the project owners: I'm willing to support this long-term, and > > would be pleased to see it put on the external add-ons page or > > included in the training files. --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
