[Insight-users] Segmentation based on discrete points

Kishore Mosaliganti kishoreraom at gmail.com
Sun Nov 15 11:21:33 EST 2009


Hi Xuan,

You can also compute the distance field of those set of point using
fast marching in ITK. Each point is an input seed and the speed map is
unity on the image grid.

Then, in the resulting distance map output, do region growing or watershed.

If there are small features, then you will lose them or will have to
manually include them by specifying seeds in those regions
iteratively.

Kishore



On Sun, Nov 15, 2009 at 10:38 AM, Luis Ibanez <luis.ibanez at kitware.com> wrote:
> Hi Xuan,
>
> Do you have only the dense cloud or points ?
>
> or
> do you have also a topological surface that connects these points ?
> (e.g. polygonal faces defining the surface)
>
> ---
>
> If you only have the cloud of points, then, this is
> an incompletely defined problem, and the best
> you can hope to get is a "reasonable" partition
> of space, but it will be impossible to guarantee
> that a correct segmentation can be constructed.
>
> ---
>
> Along the lines of "imperfect" but plausible methods:
>
> One option that you may want to explore is to use
> to dense set of points to turn on pixels in an underlying
> image. If the cloud is dense enough, you may get lucky
> and be able to create a closed surface of pixels.
>
> If you get there, then partitioning the space will be
> as simple as using the connected components filter
> in ITK, or if you don't mind providing a seed point,
> you could use the region growing filters.
>
>
>      Regards,
>
>
>           Luis
>
>
> -------------------------------------------------------------------------
> On Fri, Nov 13, 2009 at 12:27 PM, Xuan Zhao <xuanaux at gmail.com> wrote:
>>
>> Dear all,
>>
>> Is there a filter in ITK to do segmentation based on discrete points that
>> specify the surface of a volume of interest(VOI)? Or in other word, is there
>> a function in ITK that can discriminate whether a point is inside or outside
>> the surface determined by densely distributed discrete points?
>>
>> Thank you in advance,
>>
>> Xuan
>> --
>> View this message in context: http://old.nabble.com/Segmentation-based-on-discrete-points-tp26331613p26331613.html
>> Sent from the ITK - Users mailing list archive at Nabble.com.
>>
>> _____________________________________
>> Powered by www.kitware.com
>>
>> Visit other Kitware open-source projects at
>> http://www.kitware.com/opensource/opensource.html
>>
>> Kitware offers ITK Training Courses, for more information visit:
>> http://www.kitware.com/products/protraining.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
>>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.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
>


More information about the Insight-users mailing list