On Thu, Apr 11, 2013 at 02:23:50PM +0100, Nick White wrote: > I remember someone else mentioning running recognition multiple > times to increase accuracy. > > As a newcomer to the API, it isn't obvious how to do this. Can > someone give me some advice? Running GetUTF8Text() didn't appear to > make any difference.
OK, I found the answer, Recognize() is the thing to call multiple times (it's called by GetUTF8Text() if it hasn't been called yet, which is why my test code wasn't using it initially). However I found the results to be marginally worse running Recognize 10 times compared to once. Does anybody have any experience or advice on when and how best to make use of multiple recognition steps? 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.
