Environment
Tesseract Version:
Commit Number: None
Platform: X64 Windows 10
Current Behavior:
I want to recognition below picture.
But it got 2 error words in chinese, so I use jTessBoxEditorFX to fix it as below.
And generate a new mylang.traineddata file to my tessdata.
If I only use the mylang as language, it works fine, two wrong words has been fixed.
but if I use below mutil-language, chi_sim+mylang, it got error again.
or use below mutil-language, mylang+chi_sim, it even got all wrong.
Expected Behavior:
So as you can see the two words be fixed only when I use single mylang as language, If I use mutil-language, it got error again.
Is there a way that set myself training traineddata file as a supplement dataset to the original chi_sim.traineddata?
So I can fix all wrong words which can not be recognitioned with chi_sim.traineddata file, thanks a lot! :)
Environment Tesseract Version:
Commit Number: None
Platform: X64 Windows 10
Current Behavior: I want to recognition below picture.![image](https://user-images.githubusercontent.com/4754497/90732450-b2a54400-e2fd-11ea-9333-98603aec2940.png)
But it got 2 error words in chinese, so I use jTessBoxEditorFX to fix it as below.![image](https://user-images.githubusercontent.com/4754497/90732643-fa2bd000-e2fd-11ea-9115-b0b70af3d004.png)
And generate a new mylang.traineddata file to my tessdata.![image](https://user-images.githubusercontent.com/4754497/90732693-0ca60980-e2fe-11ea-93db-96c792ca34d0.png)
If I only use the mylang as language, it works fine, two wrong words has been fixed.
![image](https://user-images.githubusercontent.com/4754497/90732993-7cb48f80-e2fe-11ea-8afd-675efdeb086e.png)
but if I use below mutil-language, chi_sim+mylang, it got error again.
![image](https://user-images.githubusercontent.com/4754497/90733075-9ce44e80-e2fe-11ea-88a0-981f5559bdb1.png)
or use below mutil-language, mylang+chi_sim, it even got all wrong.
![image](https://user-images.githubusercontent.com/4754497/90733345-fea4b880-e2fe-11ea-940e-a7b91df0c85d.png)
Expected Behavior: So as you can see the two words be fixed only when I use single mylang as language, If I use mutil-language, it got error again.
Is there a way that set myself training traineddata file as a supplement dataset to the original chi_sim.traineddata? So I can fix all wrong words which can not be recognitioned with chi_sim.traineddata file, thanks a lot! :)