How is this supposed to help me? I have a program using the Tesseract
library to do OCR and then process the resulting text; I don't need a GUI
front end.
On Thu, Sep 22, 2022 at 10:09 PM Quan Nguyen wrote:
> You may want to try VietOCR, a Java desktop app that uses Tess4J. It works
> with Java
Hello,
I'm working on historical newspaper from the interwar period written in 3
different languages : corsican, french and italian.
After many tries, Tesseract seems to be the best OCR for me but the layout
analysis of a newspaper is complex.
However, using the API of Gallica (French national li
Hello !
I need to OCR some poor quality documents which contain different alphabets
e.g. german/polish/english.
I got a hint to use script/Latin instead of single languages. (I mean -l
scrpit/Latin vs -l eng+pol+deu )
Why is it better? How scrpits works? Are those models for whole alphabets?
Tesseract support uzn file[1] with psm 4. Seach forum for more details
[1] https://github.com/OpenGreekAndLatin/greek-dev/wiki/uzn-format
Zdenko
pi 23. 9. 2022 o 17:20 Vincent Sarbach-Pulicani
napísal(a):
> Hello,
> I'm working on historical newspaper from the interwar period written in 3
>
Ok, I'll check that, thanks again.
Le ven. 23 sept. 2022 à 18:44, Zdenko Podobny a écrit :
> Tesseract support uzn file[1] with psm 4. Seach forum for more details
>
> [1] https://github.com/OpenGreekAndLatin/greek-dev/wiki/uzn-format
>
>
> Zdenko
>
>
> pi 23. 9. 2022 o 17:20 Vincent Sarbach-Pul
I said that the problem was in AdaptiveClassifierIsEmpty because Windows
dumped the state of the process when the read-access violation occurred,
and AdaptiveClassifierIsEmpty was the currently-executing function at the
top of the call stack. This was deep within a call to the public function
6 matches
Mail list logo
