I got a lot of false positives, and most rotated characters aren't being
recognized at all, or aren't recognized properly.
--
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
sure. let it rotate itself
On Saturday, February 11, 2017 at 11:35:18 PM UTC+5:30, Bagi Alexandru
wrote:
>
> Anyone any ideas? :D
>
--
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
I noticed that tesseract4 reads الأ as األ which is pretty close, because
we need to switch the position of the last 2 letters to have ا ل أ, this
happens with similar word forms too like لا reads as ال and should be ل ا,
and i wish to correct it.
can someone show me how to fix this, or maybe
Okay, thank you very much!
On Thursday, March 9, 2017 at 8:13:59 AM UTC+1, shree wrote:
>
> The only public information regarding LSTM that has been shared by
> Google/Ray is linked from the following pages:
>
> https://github.com/tesseract-ocr/tesseract/wiki/4.0-with-LSTM
>
>
And i am interset how to have this result for each core.
--
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
Hi all!
It is very interesting for me if someone had any tests with different CPU,
memorry e.t.c
Is it real to make tesseract recognize a difficult image(small font,
tables, dirty image) less then 1 second.
If real then what I need to use for the best result?
Thank you.
--
You received this
6 matches
Mail list logo