Tesseract requires an image to be of minimum of 300 X 300 dpi for good results. I would suggest to resize the image and apply a filter for improvement in detection. I generally use imagemagick for this purpose.
On Thursday, August 25, 2016 at 3:28:33 PM UTC+5:30, Mikey wrote: > > I write java code to execute tesseract.exe. > > How to make tesseract to recognize those numbers better? > > > > <https://lh3.googleusercontent.com/-CQj4U-6eBYg/V76939oSVlI/AAAAAAAACQQ/trmKseUAGxU3jERm2qS0kPlCbXC5XXcygCLcB/s1600/QQ%25E6%2588%25AA%25E5%259B%25BE20160825174342.jpg> > > You can see, my result is not so good: > > 297 20 32 33 34 35 36 734 > > 37 37 38 .38 39 39 40 41 4124 > > 443 443 > > > What can I do to improve it? > -- 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]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/237d2f59-1326-4a3c-9e8c-3d111d3e1c34%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
