Hi all, I'm trying to OCR deck lists from the game Hearthstone. One such deck list is below:
<https://lh3.googleusercontent.com/-B3nKqkhbUgE/V2lfBc0c2wI/AAAAAAAAAX8/EviVUop5zU0PiyoC_6C4XVKqHgs1LP_JwCLcB/s1600/decklist.tiff> I think this should be a good case for Tesseract because the set of possible lines of text is very restricted. That is, there are only 877 possible card names (e.g. "Blood to Ichor", "Slam") that can appear on a given line. However, before trying to figure out how to train Tesseract for these 877 cards and fairly unusual font, I wanted to ask: is this a good idea? Should Tesseract perform very accurately for such a task? Thanks! Matt -- 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/24279e6a-082f-45cc-9e2c-6be039280f43%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
