You will need to perform some kind of pre-processing before sending it to Tesseract.
For instance, if you always knew the ticket was a certain size and the image was always straight, you could first crop out the rectangular areas for each row (I'm assuming you are looking for row numbers here but the same applies to other areas). Once you have done that, I ran Tesseract on the first row ... 1.8 27 29 3(2) 37 50 Nearly, but not quite. I then created a thresholded image of the cropped image that made the black lines bolder. 18 27 29 30 37 50 Perfect. Cheers On Thursday, 13 November 2014 02:51:07 UTC, Danilo Tuler wrote: > > Hi, > > I'm trying to scan the attached lottery tickets. (not winning tickets > unfortunately :-) > Those scans are grayscale 300dpi TIFF's. > > I tried with the standard english language with little success. > Then I tried to create a new language, with one or two fonts, and train it. > The results were even worse. > > What do you think? > > Thanks, > Danilo > > -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/abd5987b-6321-4fcf-8dad-ef30d5cff2d3%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
