Did you try to merge them into one box, as the training Wiki suggests? http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3
On Sunday, August 4, 2013 1:59:10 AM UTC-5, mama wrote: > > Sir, > I have found the box files for bangla language for tesseract version 2 > from the site > * > http://code.google.com/p/banglaocr/downloads/detail?name=Files%20for%20training%20tesseract.zip > > > * > It uses two box entries for one character in the tif file, such as *যা* > য 92 2584 121 2628 > া 130 2583 142 2628 > Also 3 box entries for one character. > > However I use *Tesseract-3.01* > My language also contain this type of characters. So I use 3 box entries > for single character > େ 350 3173 373 3210 0 > କ 375 3173 407 3209 0 > ା 412 3172 416 3207 0 > > and generate .tr, .txt, unicharset, pffmtable, inttemp, noromproto > But it recognize the character as େକା > > So please provide detail of training Bangla language > Because Even though I use this concept, not success for my language. -- -- 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 --- 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]. For more options, visit https://groups.google.com/groups/opt_out.
