I just saw something strange. When I use Tesseract 3.01 on a Excel array in one orientation (landscape), It gets what I told you. When I use an other array in the other orientation (portrait), It works differently. In the second case, I have: 1-1 # FRAC38185_1543-1550_GG_000001_0001 (Here the title is good on raw 1) 003 PO 0026 00036 00036 -60247 (Here the first 6 boxes are good on raw 2) 70846 (This data should be in the second raw) NB (This data should be in the second raw) NA (This data should be in the second raw) 200 (This data should be in the second raw) etc.... Then, sometimes It works well by writting just with a \t and sometimes it makes a shift enter.
To answer you question, in configuration file "unlv" I have "tessedit_pageseg_mode 6". However, I don't use it. My command is just: 'tesseract.exe picture.png outText' With my second observation, I think now that you had right and that it is not a configuration problem but just a bad performance of Tesseract in my case... -- 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
