[Insight-users] RelabelComponentImageFilter and objects analysis

Miller, James V (Research) millerjv at crd.ge.com
Tue Mar 8 09:18:46 EST 2005


There is a LabelStatisticsImageFilter that will take two images:
one an intensity image and the other a label map like the output of 
RelabelComponentImageFilter.  The LabelStatisticsImageFilter currently
only calculates the:

minimum, maximum, mean, standard deviation, variance, sum, and count

for each labelled region in the image.  However, the intention is to
add other statistics as well as needed.  For instance, perimeter, long axis length, short axis length, centroid, etc.

You can start by modifying the LabelStatisticsImageFilter to suit your needs.
Then feed back to us what features you need and we can add them to the 
LabelStatisticsImageFilter (or perhaps to a similar filter that measures
more geometric properties).

Jim






-----Original Message-----
From: insight-users-bounces at itk.org
[mailto:insight-users-bounces at itk.org]On Behalf Of Jens Eickmeyer
Sent: Tuesday, March 08, 2005 7:15 AM
To: Yann Gavet
Cc: insight-users at itk.org
Subject: Re: [Insight-users] RelabelComponentImageFilter and objects
analysis


Hi!

I had to do a similar task. I use a map with the label as key and a
struct as the value. The struct holds all the information which are
interesting for a certain object. I iterate over the label image and
use the corresponding pixel values in the original image to compute
the characteristics of each objects. This is pretty fast.

Jens

On Tue, 08 Mar 2005 11:09:45 +0100, Yann Gavet <gavet at emse.fr> wrote:
> Hello all,
> 
> I am trying to figure out how to use  itk::RelabelComponentImageFilter.
> I want to have some informations on zones defined by a skeleton. I see a
> method:
> GetNumberOfObjects () that gives the number of objects labelled, but I
> want information such centroid of object, elongation, etc.
> What is the easiest way to do it? Is there a method that could do a
> GetObject( i ); to give me a blob or something else ?
> 
> Thank you for your comments.
> 
> Yann
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
>
_______________________________________________
Insight-users mailing list
Insight-users at itk.org
http://www.itk.org/mailman/listinfo/insight-users


More information about the Insight-users mailing list