Hi
It's image processing problem
you can use OpenCV to find text , here there are some idea's
-Use SWT to find text
-Use color histogram, Quantize histogram, and the maximum color is the
background , convert all other colors to black , now all text will be black
and you can pass it to Tesseract
Tesseract is what identify Chinese slowly
Identify Chinese spent 3 minutes
--
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
2 matches
Mail list logo
