Please try again after inverting the images, i.e. black text on white background.
See also: - https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html - https://github.com/tesseract-ocr/tessdoc/blob/main/tess3/FAQ-Old.md#is-there-a-minimum--maximum-text-size-it-wont-read-screen-text - https://groups.google.com/g/tesseract-ocr/c/Wdh_JJwnw94/m/24JHDYQbBQAJ?pli=1 - https://groups.google.com/g/tesseract-ocr/c/B2-EVXPLovQ/m/lP0zQVApAAAJ Met vriendelijke groeten / Best regards, Ger Hobbelt -------------------------------------------------- web: http://www.hobbelt.com/ http://www.hebbut.net/ mail: [email protected] mobile: +31-6-11 120 978 -------------------------------------------------- On Mon, Dec 2, 2024 at 4:32 PM samuele tonon <[email protected]> wrote: > Hello, > i am trying to detect digits from some images that are made out from > screenshot of a web application. Since numbers are clear i was expecting > to see a correct reading but that is not the case. > > Images are taken from 2048 the game, i take the grid, convert to dark > background and white text. > > $ tesseract pil_check_1733137499.png stdout -c > preserve_interword_spaces=1 -l snum --psm 6 digits > > gives no output. > > $ tesseract pil_check_1733137501.png stdout -c preserve_interword_spaces=1 > -l snum --psm 6 digits > > gives no output. > > $ tesseract pil_check_1733137511.png stdout -c > preserve_interword_spaces=1 -l snum --psm 6 digits > > gives: > > 8 2 > > 2 2 2 16 > > 32 4 2 > > in this case output is good, I am missing the first line but that is > something i can live with. however I don't know how to further improve and > any help would be appreciated. > > > -- > 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 visit > https://groups.google.com/d/msgid/tesseract-ocr/126d22e2-7ed9-4ab8-8ce3-11af03933a47n%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/126d22e2-7ed9-4ab8-8ce3-11af03933a47n%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 visit https://groups.google.com/d/msgid/tesseract-ocr/CAFP60foJDaR2J%3DJJgvBKGPq87Fg5vVcQREOYhAeJfy2VpfewMw%40mail.gmail.com.
