When I generate a TIFF from text file with jTessBoxEditor, in the TIFF image all complex conjunct letters in my language (oriya) are broken down into component letters. Here is a screenshot ! http://imgur.com/GTY7wt7
The one on left is how it should be and the one on right is the output from jTessBoxEditor. Each one correspond with their counterpart on right. The box file generated has the correct character but incorrect image data as the TIFF is wrong. So when I use the generated traineddata file, the simple letters get detected fine but the complex letters screw up. Any suggestions? -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/03d1c465-ba59-482d-8348-cd5a95c934aa%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
