Hi Mike, Training probably isn't the best way to spend your time. It's only really useful for different character sets or fonts that are weird - this is neither.
Other people can probably speak to good ways to do preprocessing better than me. One thing I would say is that you can restrict Tesseract to only numbers for the bottom section; see http://code.google.com/p/tesseract-ocr/wiki/FAQ#How_do_I_recognize_only_digits? Also if the sorts of text you're going to get is highly regular in format maybe try looking into using user patterns stuff (see Dmitri Silaev's May 3 2013 email). We should document that better sometime... Nick -- -- 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.
