[Insight-users] GaussianMixtureModelComponent set parameters when the measurments vector has dimension>1

[Luis Ibanez]

Hi Baoyun,

It is great that you looked at the source code of the base class.

That's the way to go.


However the key code is in the GaussianMixtureModelCompoent
class itself. Please take a look at the email that we just sent
http://www.itk.org/pipermail/insight-users/2009-March/029442.html

in response to your previous question.
http://www.itk.org/pipermail/insight-users/2009-March/029434.html



     Thanks


         Luis


---------------
Baoyun Li wrote:
> Dear All:
>  
> I have check the base class
>  
>  
> 
> 
>       template<class TSample>
>       class itk::Statistics::MixtureModelComponentBase< TSample >
> 
> the type of parameter is Array double
>  
> typedef Array <http://www.itk.org/Doxygen/html/classitk_1_1Array.html>< 
> double >  	ParametersType 
> <http://www.itk.org/Doxygen/html/classitk_1_1Statistics_1_1MixtureModelComponentBase.html#510f71c9bd3c1b348549bf2db671b058>
> 
>  
> So I think I need to give the tweleve pararameters in the case dimenion 
> of measurmentvetor is 3.
>  
>  
> Am I correct?
>  
> Is is ok I give the mean followed by covariance as:
>  
> params[0] = 10;params[1] = 10;params[2]=10;
>  params[3]=1;params[4]=0;params[5]=0;
>   params[6]=0;params[7]=1;params[8]=0;
>   params[9]=0;params[10]=0;params[11]=1;
>  
> Thanks
>  
> Baoyun
> 
> ------------------------------------------------------------------------
> *From:* Baoyun Li <baoyun_li123 at yahoo.com>
> *To:* Luis Ibanez <luis.ibanez at kitware.com>; Insight Users 
> <insight-users at itk.org>
> *Sent:* Wednesday, March 11, 2009 11:16:08 AM
> *Subject:* GaussianMixtureModelComponent set parameters when the 
> measurments vector has dimension>1
> 
> Dear All:
>  
> Can somebody have experience to SetParameters for  
> GaussianMixtureModelComponent class?
>  
> ITK statistic example is for one dimension MesuremenVector, thus
>   typedef itk::Array< double > ParametersType;
>   ParametersType params( 2 );
>  
> params(2) containing mean and variation are enough.
>  
>  
> Now my measurement vection is 3x1.
>  
> so the mean is 3x1, and the covariance  matrix should be 3x3.
>  
> How should I give this intial parameters in this case? Only mean value 
> for each component ok? (I tried only give means, at least, the program 
> can be build).
>  
> Can somebody teach me?
>  
> Thanks
>  
> Baoyun
> 
>