Hello All, I'm trying to do a very simple OCR of a static set of images, the issue im having is its not getting the top row. Here is the image in question http://i.imgur.com/SQbmGQe.jpg
I'm using tesseract-ocr with the command -c preserve_interword_spaces=1 and sometimes -psm 6 The results are (hope the formatting works) Ina LEVEL GAMERTAG PLAYER NAME CLASS CR MIN 6 A OFF DEF TEA LW 14 MCDONALD |19| Brodie McDonald TDNG 480 58 2 3 100% 52% 64% RW 2 izChalupaBatman Chalupa Batman SNP 485 58 1 1 77% 63% 63% LD 5 1 xHelleury Niklas Lidstrom PMD 502 53 0 1 66% 28% 72% RD 5 1 Bmexx Jamal Bieber TWD 500 59 1 1 80% 41% 70% IIIH LEVEL GAMERTAG PLAYER NAME CLASS CR MIN SV SV% SAV POS TEA G 4 Netflixx n Phil Philip Payne HYB 450 60 8 0.530 17% 74% 55% IIIH LEVEL GAMERTAG PLAYER NAME CLASS CR MIN G A OFF DEF TEA C 11 LetsGoFlyersSB Ryan Clay PWF 582 60 5 2 100% 84% 100% LW 2 SnipechGriff Snipez McGriff TDNG 513 60 1 2 89% 67% 73% RW 9 Johnny Coombs Johnny Coombs PWF 555 60 0 2 79% 53% 95% LD 9 CRUSHED LOLIPOP Nathan Hall EFD 602 48 1 1 74% 46% 82% RD 6 franklow99 FRANK LOW TWD 446 57 O 2 78% 81% 51% IIIH LEVEL GAMERTAG PLAYER NAME CLASS CR MIN SV SV% SAV POS TEA G 12 cup4b|ues lm CheeseBurger HYB 604 60 12 0.710 42% 67% 65% The issue is the first column header is that yellow and the value should be "POS", now the issue is that yellow column could be any of the columns depending on what the user has highlighted. I've tried doing a lot of pre-processing of the image using imagemagick like convert to grey scale and even playing with the threshold but none seem to work I'm sure it should just be a setting or two in tesseract, Can anyone help? -- 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/f202203e-ea06-47ea-b0ce-1d747f9b9163%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
