In general, I wouldn't advise to always use the latest SVN revision, for stability reasons. My results were obtained by running an executable built from revision 580. You should try it too.
Warm regards, Dmitri Silaev www.CustomOCR.com On Thu, Jun 23, 2011 at 9:17 AM, ogorman <[email protected]> wrote: > >> I used the following command line: >> tesseract test_osd_cr.tif test_osd -psm 1 >> >> "-psm 1" stands for "Use automatic page segmentation with orientation >> and script detection. (OSD)" >> >> I used a copy of "eng.traineddata" as "osd.traineddata" >> > Thanks Dmitri for the advice. I had seen this as well and tested > cropping the image to not include the fax page number. I also just > tried moving the osd data around like you suggested. Either way when > i run the tesseract command on the image it just comes back with > garbage, where as if i rotate it 180 degrees with imagemagick i get > 99% success rate. I am using a version I pulled out of svn 3 days ago > it reports back tesseract-3.01 is there anything I am missing to get > the results you did? Once again thanks for your help. > > Matt > > -- > 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 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
