[Insight-users] Applying labels from KmeansModelEstimator toinput image pixels

[Magnotta, Vincent A]

I would suggest that you look at itkScalarImageKmeansImageFilter.txx. This is essentially performing this classification using scalar images. A ListSampleAdaptor is used to classify the image. The algorithm then iterates over the Samples setting the image. Since this is a Adaptor class, it is assumed that the ordering of the samples is the same as the image. 

Vince


----------------------
Associate Professor 
Department of Radiology 
0453-D JCP 
200 Hawkins Drive 
Iowa City, IA 52242 
E-mail: vincent-magnotta at uiowa.edu 
Phone: 319-356-8255 Fax: 319-353-6275 
Website: http://www.radiology.uiowa.edu 



-----Original Message-----
From: insight-users-bounces at itk.org on behalf of Dawood Masslawi
Sent: Thu 11/11/2010 7:33 PM
To: insight-users at itk.org
Subject: Re: [Insight-users] Applying labels from KmeansModelEstimator toinput image pixels
 
Dear David,
I think using the ImageToListSampleAdaptor seems reasonable since you can easily 
access the coordination of the pixels using an IteratorWithIndex after the labeling process
is done, this way you can input the ListSampleAdaptor all at once instead of iterating over 
the image. 
Another approach could be using the itkScalarImageKmeansImageFilter and then 
using a IteratorWithIndex to access the coordination of the pixels but I'm not sure 
how would a decision rule fit in that scenario.
Regards,
Dawood Masslawi


      

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20101111/f0f7ae4b/attachment.htm>