Problems with OCR Recognition

Discussions about Tesseract OCR integration in GdPicture.
Post Reply
win568
Posts: 44
Joined: Tue Mar 24, 2015 1:00 pm

Problems with OCR Recognition

Post by win568 » Tue Sep 15, 2015 10:56 am

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
Attachments
HN.tif
HN.tif (790 KiB) Viewed 2065 times

Cedric
Posts: 263
Joined: Sun Sep 02, 2012 7:30 pm

Re: Problems with OCR Recognition

Post by Cedric » Mon Feb 15, 2016 3:27 pm

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,

win568
Posts: 44
Joined: Tue Mar 24, 2015 1:00 pm

Re: Problems with OCR Recognition

Post by win568 » Tue Apr 26, 2016 9:00 am

Hi Cedric

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

Cedric
Posts: 263
Joined: Sun Sep 02, 2012 7:30 pm

Re: Problems with OCR Recognition

Post by Cedric » Tue Apr 26, 2016 9:42 am

That would logically be the Scale method described here: http://guides.gdpicture.com/content/web ... Scale.html

Post Reply

Who is online

Users browsing this forum: No registered users and 1 guest