Tried to run tesseract with your image seite1_1.PNG and got same results as shown by you. But it seems it will resolve the issue if you use proper PSM mode. for example:
tesseract -psm 6 /home/adarsh/Downloads/seite1_1.PNG out This will give you this output: AAAAAAEAAAAAAAAAYj EFAAkAAAAAIAAAAAkAAAAAAAAIAAAAAAAAAAAAAAAAAAAAIAAAAAQUAAAA AJQAquGJgAMAAAMMAAAMAIAAAAAAAAAIAAAAAEAAAAMAAAMAMMMAMAAANMAAAMA AAAMAAAAAAAAAAANMAAAAMMNMMMAAAAAAMMAAMMAAAAAAAAAAAAAANMAAAAAAMA This is correct to single words as i checked. Happy Coding. On Tuesday, November 28, 2017 at 12:15:49 PM UTC+5:30, 1609Tommi wrote: > > > Hello, > > so I am a total newbie with tesseract and coding in general, have fooled > around with tesseract for a couple of hours now, and just can`t get > acceptable outputs. > The context is that i have several pages of random characters printed on > paper, or now as .pngs, and want to get them back in a txt. file. How did > this happen? Well, 3 years ago i invested a (very) > small amount in bitcoins, but as the price was rather stable and it wasn`t > much money it all, i never sold them, and after a while forgot about them. > And stupid me also reseted my pc :(. But, i printed my wallet.dat, so here > I am. > Maybe you can help me. > The attached png is the picture with which i tried it, and the txt is my > result. > > So is there a way to improve the character recognition? > Or do i have to type it :D > > Thank you, > > Thomas > > -- 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 post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/599cd5a1-9584-4a8b-8793-acc972960109%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.