Actually for experiments I will need "ground truth" pairs: image (jpg) + true text (rtf or txt). A couple of book pages is enough for the start.
I'm not sure I understand about alphabets. What did you mean? Warm regards, Dmitri Silaev www.CustomOCR.com <http://www.customocr.com/> - Hide quoted text - On Mon, Sep 26, 2011 at 6:49 AM, Sriranga(78yrsold) <[email protected]> wrote: > Dear Dmitri, > congratulations. output was same as used in commandline of tesseract. for > your experiment to improve the accuracy, you have > requested for real Kannada text, I am in bit confusion whether you want > kannada in image format or edittable text format ? Also you want alphabets > in Kannada for experiment? > On receipt of your clarification, i shall forward as requested by you. > With Warmest Regards, > -sriranga(78yrs) > -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en
