Hi Alex, If you're up for some programming, you could recognise the squares yourself, and pass each one separately to tesseract with the PSM_SINGLE_CHAR segmentation type. That should help if Tesseract is not segmenting each whole square separately.
If the board is always the same size, you could even do it by just creating a .uzn file like this: 0 0 60 60 squarea1 60 0 60 60 squarea2 120 0 60 60 squarea3 etc. That way you're completely controlling the section segmentation. I suspect you'd get better results by feeding each square separately, though, as you can then use PSM_SINGLE_CHAR, and Tesseract has a better chance of taking the number in the corner into account. As Paul suggested, though, binarisation may be an issue too. You can check how well it does by using the tessedit_write_images config setting; see https://code.google.com/p/tesseract-ocr/wiki/ImproveQuality#Image_processing Nick -- 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/20140708161932.GA10866%40manta.lan. For more options, visit https://groups.google.com/d/optout.
