Update, I have fixed this myself by using an app to turn all pictures black and white. I think the issue might have been with the binarisation of the images that tesseract was doing. I'm getting much better results now!
Il giorno sabato 10 settembre 2022 alle 08:09:53 UTC+2 Daniele Consoli ha scritto: > Greetings, > I'm new to Tesseract, but it seems like I'm having some fundemental issues > and couldn't find any solutions by looking at guides online, so I figured > I'd ask here. > > I am trying to scan a few pages of a pdf, but the results are typically > very inaccurate (see pictures below). > [image: 5.png] > [image: unknown.png] > I installed this version of Tesseract ( > https://github.com/UB-Mannheim/tesseract/wiki) for Windows. > > The command I used to get those results is "tesseract --oem 3 5.png 5" > > Any help would be greatly 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/7d87a070-015e-49fc-9961-de3b0fa3b0f3n%40googlegroups.com.
