[ITK-users] Computational time of fast marching

[Lin M]

I'm using a i7-4650U 8G machine.

On Mon, Mar 23, 2015 at 12:10 PM, Lin M <majcjc at gmail.com> wrote:

> Hi guys.
>
> I'm using fast marching to compute the distance map, but the time of
> computation is much slower than I expected. Is it normal to cost about
> 250secs for a 512*512*365 image? I'm using the released mode.
>
> My process is like this:
> 1. initialize a binary image (alive image) where segmented target is set
> to 1, the rest is set to 0
> 2. initialize the trial image where the neighbourhood of alive image is
> set to 1, the rest is set to 0
> 3. give the two images to the adaptor and set the alive value and the
> trial value both to 1
> 4. run fast marching
>
> Do you have any ideas about that or some suggestions to improve the
> performance. Thank you very much!
>
> Best,
> Lin
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20150323/585c63ed/attachment.html>