On Tue, Oct 15, 2013 at 04:52:16PM -0700, David Goodwin wrote: > The out file is just totally empty. Here is my input image > > I did some pre-processing on the image - cropped to just the numbers, inverted > them so they are black, blanked out most the background.
Is the image you attached *after* pre-processing? I'm afraid the amount of background colour and variation around the letters is way higher than Tesseract can deal with. I think there are other tools designed to work with CAPTCHAS, it may be worth looking at them instead of Tesseract (or using them to properly clean the image before turning to Tesseract). 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.
