Try tools to remove noise, distortions, artifacts, etc. from your images before OCR.
http://scantailor.sourceforge.net/ http://sourceforge.net/projects/bookscanwizard/ http://www.fmwconcepts.com/imagemagick/textcleaner/index.php On Friday, June 7, 2013 2:46:00 PM UTC-5, Sabin Flo wrote: > > Hello, I am trying to build an application that would detect dangerous > ingredients in food products. To do this I need an OCR application for > ingredients detection. This should have a very good output. So far I have > very poor results. Do I need some sort of pre-processing on images? On the > attached image I have obtained this result: > > gmš šn:e§§s%fs:?í: šzkefifa Grunšnš Gfwp Î `î > > üfiíîéê Hšedefáîzšm Gefmuny. > > mçzimtà še S i. (crisţum Bevewgl (n. S11, > lé. Bàuàaţeš 89, Pcmeîámsn, Hfov. Tei. 021 265 > > åàuîurü råzafitoafe necarbomîdă t! V > minimum 15% menţinut de fmd. « > > Weâieflfie; cpá, suc de fructe obţirmî «fm ai Î > > (we 8%, mcàzc negre 5%, mami “şi > > su: cancemret de iàmêi, uman wwfil. ţ fiŸÎ, > hamwrizut. Hu (same conscmnţi. Mbifi > > wmpwuepesmdfipfduiaçalukrium > > fasii de ĭngbaţ şi sum. > > -- -- 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.
