Hello everybody. I wonder if there is way to train tesseract to effective recogize only SEUENCE of dots in scanned document. For example is there way to recognize these two pictures characteres, which are filled only with dots:
<https://lh3.googleusercontent.com/-PlHu1RiA0ks/Vef66bxrblI/AAAAAAAAAQA/u_C3Qb08ifQ/s1600/dots-even.gif> <https://lh3.googleusercontent.com/-4oPXEib1nX0/Vef6tue7rTI/AAAAAAAAAP4/UQ_5JxNADQY/s1600/pimentel.bmp> I have tried also with text and a lot of dots, but I found out that the resolution must be super hight for the effective work of tesseract. I`ll be glad if someone can help. If someone think of another way - please to share his opinion, but in that case there is one more condition to observe - on the page there can be not only dots, but text and raster images, so the algorithm should make difference between these three objects, and get only the dots. <https://lh3.googleusercontent.com/-4oPXEib1nX0/Vef6tue7rTI/AAAAAAAAAP4/UQ_5JxNADQY/s1600/pimentel.bmp> -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. 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/d8709e39-3b55-4f4b-91d2-d42ff1d668b9%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.