Image to text of Strike-through characters

Hello everyone,

I can't find a way to convert images that contain strike-through characters. OCR doesn't recognize them. Is there any way to overcome this problem?

I attached a simple example jpeg file.

Thanks in advance.

Anybody???

Hi Boraster,

I've no experience with strike-through text. In our integration we use Tess4J, which is a java wrapper for Tesseract OCR and has plently of options for customization (see Tab in node). If Tesseract offers the option to detect strike-through text, you can add it to the node configuration.

Best,

Christian

 

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.