Hello,
We are trying to train Tesseract 3.02 with jTessBoxEditor on Windows Server 2012 R2 to improve recognition of identity cards. You can see how images look on this link http://www.mup.hr/71.aspx. This is just an example image, our scanned images are 300DPI, 1010x635, B&W. We have tried to train Tesseract with jTessBoxEditor and manually using Tesseract training tools. What we would like is to OCR only upper case letters. First we have created box files and then we have gone through all boxes and corrected all errors and managed to produce traineddata file. But, when we try to OCR the same images that we have used for training the result is far from good. Is it possible to train Tesseract to improve OCR of identity cards? Any suggestions on how to train tesseract to improve OCR of identity cards. Thanks -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/2f7cd719-30b3-4336-8b26-b3103dd89002%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
