[Insight-developers] VoronoiSegmentationImageFilter

Mon, 21 Oct 2002 12:58:20 -0400

This message is in MIME format. Since your mail reader does not understand
this format, some or all of this message may not be legible.

------_=_NextPart_001_01C27922.940AFFBA
Content-Type: text/plain;
	charset="iso-8859-1"

More on the VoronoiSegmentation...

This filter has an ivar m_Var that can be set by the user or via the TakeAPrior() method.  In the 
TakeAPrior version, it looks like the standard deviation is being stored in the ivar not the
variance.

What was the intention? To  use variances or standard deviations?

The method names, ivar names, and calculations should be consistent.

-----Original Message-----
From: Miller, James V (Research) 
Sent: Monday, October 21, 2002 12:26 PM
To: Insight-developers (E-mail)
Subject: [Insight-developers] VoronoiSegmentationImageFilter

I am having problems getting the VoronoiSegmentation filter to produce any output.  

  itk::VoronoiSegmentationImageFilter<FloatImage, FloatImage>::Pointer
    voronoi=itk::VoronoiSegmentationImageFilter<FloatImage, FloatImage>::New();
  voronoi->SetInput( original->GetOutput() );
  voronoi->SetNumberOfSeeds( 100 );
  voronoi->SetOutputBoundary( false );
  voronoi->SetSteps( 500 );
  voronoi->TakeAPrior( masker->GetOutput() );
  voronoi->SetMeanPercentError(0.1);
  voronoi->SetVarPercentError(1);
  voronoi->Update();

The filter churns for a while but the output image is blank.

(I have toggled the OutputBoundary flag but I get a  blank image).

In terms of architecture, the prior image (used in TakeAPrior) is not one of the filter inputs, so
the filter does operate properly in the pipeline.

Jim Miller 
_____________________________________
Visualization & Computer Vision
GE Research
Bldg. KW, Room C218B
P.O. Box 8, Schenectady NY 12301

millerjv@research.ge.com <mailto:millerjv@research.ge.com> 

james.miller@research.ge.com
(518) 387-4005, Dial Comm: 8*833-4005, 
Cell: (518) 505-7065, Fax: (518) 387-6981 

------_=_NextPart_001_01C27922.940AFFBA
Content-Type: text/html;
	charset="iso-8859-1"

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML xmlns:o = "urn:schemas-microsoft-com:office:office"><HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">

<META content="MSHTML 6.00.2715.400" name=GENERATOR></HEAD>
<BODY>
<DIV>More on the 
VoronoiSegmentation...</DIV>
<DIV>&nbsp;</DIV>
<DIV>This filter has 
an ivar m_Var that can be set by the user or via the TakeAPrior() method.&nbsp; 
In the </DIV>
<DIV>TakeAPrior 
version, it looks like the standard deviation is being stored in the ivar not 
the variance.</DIV>
<DIV>&nbsp;</DIV>
<DIV>What was the 
intention? To&nbsp; use variances or standard deviations?</DIV>
<DIV>&nbsp;</DIV>
<DIV>The method names, 
ivar names, and calculations should be consistent.</DIV>
<DIV>&nbsp;</DIV>
<DIV>&nbsp;</DIV>
<BLOCKQUOTE dir=ltr 
style="PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #0000ff 2px solid; MARGIN-RIGHT: 0px">
 <DIV class=OutlookMessageHeader dir=ltr align=left>-----Original Message----- From: Miller, James V (Research) 
 Sent: Monday, October 21, 2002 12:26 PM To: 
 Insight-developers (E-mail) Subject: [Insight-developers] 
 VoronoiSegmentationImageFilter </DIV>
 <DIV>I am having problems getting 
 the VoronoiSegmentation filter to produce any output.&nbsp; 
 </DIV>
 <DIV class=Section1>
 &nbsp; 
 itk::VoronoiSegmentationImageFilter&lt;FloatImage, 
 FloatImage&gt;::Pointer &nbsp;&nbsp;&nbsp; 
 voronoi=itk::VoronoiSegmentationImageFilter&lt;FloatImage, 
 FloatImage&gt;::New(); &nbsp; voronoi-&gt;SetInput( 
 original-&gt;GetOutput() ); &nbsp; voronoi-&gt;SetNumberOfSeeds( 100 
 ); &nbsp; voronoi-&gt;SetOutputBoundary( false ); &nbsp; 
 voronoi-&gt;SetSteps( 500 ); &nbsp; voronoi-&gt;TakeAPrior( 
 masker-&gt;GetOutput() ); &nbsp; 
 voronoi-&gt;SetMeanPercentError(0.1); &nbsp; 
 voronoi-&gt;SetVarPercentError(1); &nbsp; 
 voronoi-&gt;Update(); &nbsp;
 The filter 
 churns for a while but the output image is blank.
 (I have toggled 
 the OutputBoundary flag but I get a&nbsp; blank image).
 In terms of 
 architecture, the prior image (used in TakeAPrior) is not one of the filter 
 inputs, so the filter does operate properly in the pipeline.
 Jim Miller 
 _____________________________________ Visualization &amp; 
 Computer Vision GE 
 Research Bldg. KW, Room C218B P.O. Box 8, Schenectady 
 NY 12301 <A 
 href="mailto:millerjv@research.ge.com">millerjv@research.ge.com</A>
 james.miller@research.ge.com (518) 387-4005, 
 Dial Comm: 8*833-4005, Cell: (518) 
 505-7065, Fax: (518) 387-6981 
 &nbsp;<o:p></o:p></DIV>
 <DIV>&nbsp;</DIV></BLOCKQUOTE></BODY></HTML>

------_=_NextPart_001_01C27922.940AFFBA--