I just saw the second picture I attached should be the following. In that 
one you can see the .box file information.

[image: GoogleGroupsQuestion2.png]

Simon schrieb am Sonntag, 3. Dezember 2023 um 10:38:51 UTC+1:

> Hello everybody,
>
> is anyone familar with jTessBoxEditor. 
> I am currently generating synthetic training data. Within this 
> synthetically created tif files are numbers to be trained. Within this 
> program I also automatically create .box files. But somehow the box 
> coordinates jTessBoxEditor shows are different form the coordinates defined 
> in the .box file. Can someone explain where the difference comes from. If 
> theres a problem with jTessBoxEditor? Because it is absolutely not 
> traceable where the difference comes from. 
>
> Attached you will find the information from jTessBoxEditor. In blue shown 
> the box information from jTessBoxEditor and in green how the boxes should 
> look like. For the first sign there of course should also be a green box 
> but this one is the only sign with a good box around it in jTessBoxEditor. 
> [image: GoogleGroupsQuestion.png][image: GoogleGroupsQuestion.png]
> Also see that if I am modify the coordinates in jTessBoxEditor manually so 
> that thy align with the one given in the box file I have perfect box 
> information.[image: GoogleGroupsQuestion3.png]
>
> I am grateful for any help!
>

-- 
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/e8198129-a413-4ad6-b2a9-41f544859c78n%40googlegroups.com.

Reply via email to