Can you share original pdf to investigate if the problem could not be solved on pdf level (e.g. extract image from pdf without watermark) ?
Your problem is not related to tesseract (or other way - tesseract is not tool that helps you remove watermark), so better option would be to post in on stackoverflow. I found several examples how remove watermark, but unfortunately non of them works with your image. Just for inspiration what is possible: https://stackoverflow.com/questions/50792812/how-to-remove-watermark-background-in-image-python http://davidsteccieblog.blogspot.com/2017/10/removing-watermarks.html https://stackoverflow.com/questions/32125281/removing-watermark-out-of-an-image-using-opencv?noredirect=1&lq=1 https://magda.space/removing-circles-lines-patterns-part-1/ https://magda.space/removing-circles-lines-patterns-part-1-5/ https://magda.space/removing-circles-lines-patterns-part-2/ Zdenko pi 7. 2. 2020 o 17:11 Mark Heere <[email protected]> napísal(a): > Is there a way to remove the diagonal letters from this page? I'm trying > to send it through tesseract but I'm getting a bunch of garbage where the > watermark is meeting the letters in the image. I used GhostScript to > convert the original PDF image into the PNG file. > > Thanks in advance for your help! > > > > -- > 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 view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/e275c83b-0d38-4d0a-9dc6-e514d46b1216%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/e275c83b-0d38-4d0a-9dc6-e514d46b1216%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 [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAJbzG8wT%3DVbxNqf96bRmBT529nHH6NpDkbZUbz75nxguAeN7jA%40mail.gmail.com.
