Hello, this is about image preprocessing/thresholding rather than tesseract... Please post an example image so tesseract users can test it and suggest a possible solution.
Zdenko št 21. 9. 2023 o 13:04 Iago Giné <let7once10and17for3...@gmail.com> napísal(a): > Hi all, > > Is there some option to tell tesseract-ocr that there is text with > multiple colours, so it detect all the text? For example, in my case, I > have a pdf with the cover of a book, with yellow background and text both > in black and also in white. Depending on how I proceed, I get only the text > in black or the text in white, but not both. > > I have only found the next issue, but no answer or anything more : > https://github.com/tesseract-ocr/tesseract/issues/3078 > > Thank you for your time! > > Iago > > -- > 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/6610a558-975c-4ce4-8bba-c2b56fd9c50an%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/6610a558-975c-4ce4-8bba-c2b56fd9c50an%40googlegroups.com?utm_medium=email&utm_source=footer> > . > -- 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/CAJbzG8xxxAeyO3Q85hvkLz7Mu7QkaOqN3dUFSWkOfJOygMW0xw%40mail.gmail.com.
