When you train tesseract you provide it with loads and loads of text in the font/language of your choice. It then turns this into outlines effectively that it can match to incoming images with text.
Now I am not 100% sure but I am quite certain that if you attempted to train Tesseract with a bunch of emoticons in TIF files (needed for training) it would not be able to break them down into shapes that give you the matching you're looking for. Best case it would see every emoticon as a circle shape and they'd all look the same to Tesseract. This is just my guess from what I know. Cheers On 23 May 2015 at 17:21, SRguy <sanderatla...@gmail.com> wrote: > That is FASCINATING, but since the emoticons to which I'm referring are > already represented in Unicode wouldn't I just train T. in the conventional > manner (for which I was hoping there were already files available )? > > -- > 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/9e1de0ef-edc1-410b-ab19-490536b23d39%40googlegroups.com > . > For more options, visit https://groups.google.com/d/optout. > -- 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/CAORW5vhCPMMGyDpqa%2BZET-znC1pz%2BKUqoVjWSGvQ_bK4L-qVNA%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
