Thanks, I will try it. Evgeny
вторник, 4 августа 2020 г. в 20:18:54 UTC+3, zdenop: > First you need to remove the background. > Then > https://github.com/tesseract-ocr/tessdoc/blob/master/ImproveQuality.md > > Zdenko > > > ut 4. 8. 2020 o 13:07 Евгений Захаров <evgzak...@gmail.com> napísal(a): > >> Hi. It wold be great if somebody could help with parsing these bold white >> fonts. >> >> I try to parse this images with some preprocessing. For example after >> "erode", "GaussianBlur" and "Canny" some part of text start to recognise, >> but not all. And with different settings of preprocessing start to >> recognise different part of images. >> Does it exist any image preprocessing algorithm to detect such text? Or >> it possible only to retrain model to detect this bold font? >> >> [image: Untitled.png] >> >> [image: Untitled2.png] >> >> [image: Untitled3.png] >> >> >> -- >> 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-oc...@googlegroups.com. >> To view this discussion on the web visit >> https://groups.google.com/d/msgid/tesseract-ocr/51c6f97a-d541-4f06-bf4f-ad225723f761o%40googlegroups.com >> >> <https://groups.google.com/d/msgid/tesseract-ocr/51c6f97a-d541-4f06-bf4f-ad225723f761o%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/56854562-3961-4676-b71a-e4156f614987n%40googlegroups.com.
