I used jTessBoxEditor to create tessdata for a text and a font file. It works pretty well. But as I need to OCR photos of printed labels, the font is very similar to the one used in the labels, but I guess it would be better to directly train tesseract with the label letters themselves. It's actually only digits, so I only need 10 symbols, I can cut them and prepare a TIF training file by hand, but jTessBoxEditor doesn't seem to accept that, it only generates a TIFF from text and a font. Is this possible to do with tesseract?
or jTessBoxEditor? (I know this is not part of tesseract, but maybe some of you use it?) Thanks! -- 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/fa13ce71-b8a7-46cf-83c8-d0c8b9f091b1%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
