[Insight-users] Regisration: ImageMaskSpatialObject & CenteredTransformInitializer
Luis Ibanez
luis.ibanez at kitware.com
Mon Aug 17 10:24:28 EDT 2009
Hi Felix,
1) No, the moments calculators, and therefore the
CenteredTransformInitializers does
not take the masks into account when computing the initialization of the
Transform.
2) This could be done by modifying the code of both classes... The changes
will
include to add methods SetFixedSpatialObjectMask()
SetMovingSpatialObjectMask(),
and inserting if() statements in the main loop that computes the
moments.
When drinking the proper blend of coffee, this could be done in an
afternoon,
and the changes could be submitted to the Insight Journal the following day
:-)
Would you like to attempt these modifications ?
If so, we will be happy to guide you through the process.
Please let us know,
Thanks
Luis
---------------------------------------
On Mon, Aug 17, 2009 at 4:17 AM, Felix Bollenbeck <
Felix.Bollenbeck at iff.fraunhofer.de> wrote:
> Dear ITK users,
>
> I am using spatial masks to exclude points (I want to use only certain
> ROIs) from metric/optimization.
>
> (Can) is the CenteredTransformInitializer in MomentsOn() mode using the
> mask passed to the metric?
>
> What would be the best way to calculate Moments using only the masked
> regions (in the full images coordinates though)?
> - at the moment I use the masks themselves for calculating the centers,
> which is not quite the same.
>
> Thanks for your help,
>
> Felix.
>
>
>
>
>
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://www.itk.org/mailman/listinfo/insight-users
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20090817/c97bedf3/attachment-0001.htm>
More information about the Insight-users
mailing list