This topic and its replies were posted before the current version of LEADTOOLS was released and may no longer be applicable.
#1
Posted
:
Tuesday, February 20, 2007 1:54:07 AM(UTC)
Groups: Registered
Posts: 7
In my application I am using the ICR, OCR and OMR dotnet APIs.
I created a template that I use for all the three recognition methods (ICR, OCR and OMR).
Then I set the engine with all the options for the three methods because when I recognize a page I use that template.
My question is: in case I create three different templates, one for each recognition method, could I obtain more accurate results?
could this approach decreases the application performance?
Thanks in advance.
--Andrea
#2
Posted
:
Wednesday, February 21, 2007 10:01:53 AM(UTC)
Groups: Guests
Posts: 3,022
Was thanked: 2 time(s) in 2 post(s)
For best performance, images should be at least 300 DPI and contain black text on a white background. To speed up performance, you can create zones so that the engine will only search the area you specify, not the entire image. This of coarse would require you know before hand where the text exist on the page.
You cannot post new topics in this forum.
You cannot reply to topics in this forum.
You cannot delete your posts in this forum.
You cannot edit your posts in this forum.
You cannot create polls in this forum.
You cannot vote in polls in this forum.