[Insight-users] Sobel edge detection in higher dimension than 2D (fwd)

Xinwei Xue xwxue@cs.utah.edu
Tue, 19 Nov 2002 18:07:41 -0700 (MST)


Hi,

Thanks for reporting bugs. I do find a bug in the itkSobelOperator.txx and
fixed it. After the change, the result looks a bit better, but for 3D it
does not seem to be very well in 3D comparing with other edge
detectors. Basicly, it is similar to the method of gradient magnigitude
filter, but it uses a more complex kernels to calculate it. The output
is the "gradient magnitude" calculated with sobel operator. 

Thanks,

Xinwei

On Tue, 19 Nov 2002, Joshua Cates wrote:

> Hi Xinwei,
> 
> Any thoughts on this?
> 
> Josh.
> 
> ______________________________
>  Josh Cates			
>  School of Computer Science	
>  University of Utah
>  Email: cates@sci.utah.edu
>  Phone: (801) 587-7697
>  URL:   www.cs.utk.edu/~cates
> 
> 
> ---------- Forwarded message ----------
> Date: Mon, 18 Nov 2002 09:23:06 +0100
> From: Martin Styner <martin_styner@ieee.org>
> To: insight-users <insight-users@public.kitware.com>
> Subject: [Insight-users] Sobel edge detection in higher dimension than 2D
> 
> Hi
> 
> I was experimenting with the different edge detector routines in itk on 
> 3D images. It seems that the Sobel edge detector filter 
> http://www.itk.org/Doxygen/html/classitk_1_1SobelEdgeDetectionImageFilter.html
> does not work with 3D images. Is that correct ? (in the manual pages it 
> says that it would deal with ND images...) Also the 
> EdgeDetection-Application does not seem uptodate.
> 
> best wishes
> Martin
> 
> -- 
> Martin Styner, PhD. Ing. ETH
> Group Head Medical Image Analysis for Orthopaedics
> M.E. Mueller Institute for Biomechanics
> Center for Computed Assisted Surgery
> University of Bern
> Murtenstrasse 35
> P.O.Box 30
> CH - 3010 Bern
> Switzerland
> Tel office: ++41-31-632-0940 , FAX: ++41-31-632-4951
> email: Martin.Styner@memot.unibe.ch, martin_styner@ieee.org
> WWW: http://cranium.unibe.ch/~mstyner
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users@public.kitware.com
> http://public.kitware.com/mailman/listinfo/insight-users
>