Hello everyone! I'm just getting started with Tesseract and am wowed at how well it does on tasks like scanned black and white text! I'm... less than thrilled at how it does at my current endeavor, which is to extract the text from animated GIFs, such as from reaction GIFs and memes and so on.
After reading the FAQ and the ImproveQuality articles as well as some further prodding around, it seems the DPI of the images isn't too small, but rather that most of the issue comes from the variety of background colors around the text and/or the font(s) commonly used for memes. Does anyone have any experience with this, or have any helpful advice for this specific task? Attached is a sample of the kind of thing I want to process. Thank you for your time. (Incidentally, even though the new version of leptonica and tesseract both say they support gifs, I get the following error when I send a gif in: Tesseract Open Source OCR Engine v3.04.00 with Leptonica Error in pixReadMemGif: function not present Error in pixReadMem: gif: no pix returned Error during processing. ) -- 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/c7872f44-b5b9-4479-8136-8b434044cda5%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
