Hi, I've been experimenting with tesseract for some months now and for someone who still does not need/want to go into changing the source code, I have a fundamental question about Tesseract's character recognition:
What are the conditions that lead Tesseract to fail the recognition of a single character? In other words: Does it fail only if the input is not graphically perfect? I don't think so. It has to do with fonts also. Does it fail when the scale of the input character is unexpected (there should be a pre-scaling, I guess)? How does Tesseract mix H with X, for instance? I'm not complaining about Tesseract, I'm just really interested in knowing exactly why it fails so that I can improve my OCR setting. Thanks. -- -- 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.
