Hi. 1. I've an image that's written in a "Science Fiction" style font, where 'E' is written similarly to '='. Therefore, the attached image is recognized as "AR= YOU SURE YOU WANT TO QuIT >"
However, since Tesseract is using an English dictionary, I'd expect it to understand that "ARE" is much more likely than "AR=". I assume this can be controlled by some configuration? 2. I tried using https://www.newocr.com/ , which is based on Tesseract, and it correctly recognized it: "ARE YOU SURE YOU WANT TO QUIT ?" (I've erased the new line) So, I assume it should be feasible. 3. Note that https://www.newocr.com/ also correctly recognized the 'U' of "QUIT"' as uppercase, and also the ending question mark - I assume that's also can be achieved by vanilla Tesseract, the question is how? Thanks, Zvika -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/6ca9ab15-56cc-4ead-8708-caac097fc03bn%40googlegroups.com.
