3

I was just playing around a little with Tesseract as I noticed some strange behavior of the program, which I can’t explain myself. Firstly I gave tesseract this preprocessed Picture1 but it didn’t understand any letter.

Picture1

Then I put this one in and guess what it gave me?

Picture2

Neuinitialisierung des automatischen
Karten-Updates erforderlich. Aktuellste

The exact letters and words, every single letter was correct!
So can anybody tell me why it didn't got the text in the first picture.
(btw. I preprocessed the two pictures in the absolut same way)

Thanks in advance!

alseether
  • 1,889
  • 2
  • 24
  • 39
Schnurrbart
  • 31
  • 3
  • It **might** have gotten confused by the `ß`. Have you tried putting a white rectangle over it, or replacing it with double "s" to see whether the programme does anything differently? – sjaustirni Mar 05 '18 at 13:44
  • good idea! I tried that out and it get's the word! Any Idea how I could overcome that problem? – Schnurrbart Mar 05 '18 at 13:58
  • 1
    Were you using deu.traineddata? – Dmitrii Z. Mar 05 '18 at 14:20
  • I just use -lang deu in my script but I was wondering why tesseract didn't stated the other letters "schlie" & "en" if ß is the only Problem. I already tried some other "schließen" pictures where tesseract just missspelled it as "schlief3en". – Schnurrbart Mar 05 '18 at 15:18

0 Answers0