Page 1 of 1

Problems with OCR Recognition

Posted: Tue Sep 15, 2015 10:56 am
by win568
Hi Guys

We test your Tesseract OCR Engine to replace our old Product. As Attachment, I Send you as Attachment a Tif Document, where the OCR Engine cannot Extract the Total Amount Value. Can you check, why this happens ?? Out old Engine has the Same Problem. The Context of the OCR is OCRContext_OCRContextDocument

Re: Problems with OCR Recognition

Posted: Mon Feb 15, 2016 3:27 pm
by Cedric
Hello,

The issue here is that this document has a very low resolution (96 DPI) when the minimal value to get acceptable results with OCR should be around 200, sometimes even around 300 DPI depending on the document quality.
Here the document quality is good so by simply scaling up the document to get a proper OCR resolution (200% scale will give a 192 DPI resolution) the document is properly read including the Total Amount value.

Regards,

Re: Problems with OCR Recognition

Posted: Tue Apr 26, 2016 9:00 am
by win568
Hi Cedric

Which Method should i use to scale the Document for 200% ??

Re: Problems with OCR Recognition

Posted: Tue Apr 26, 2016 9:42 am
by Cedric
That would logically be the Scale method described here: https://www.gdpicture.com/guides/gdpicture/web ... Scale.html