[Insight-developers] VoronoiSegmentationImageFilter

Yinpeng Jin yj76@columbia.edu
Mon, 21 Oct 2002 13:28:30 -0400


This is a multi-part message in MIME format.

------=_NextPart_000_0029_01C27905.BEF99420
Content-Type: text/plain;
	charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

Yes, I should change the ivar name, they all should be standard =
deviations.
I think previously, we use variance, but later on, figure that std be =
more intuitive and easier to figure.

  ----- Original Message -----=20
  From: Miller, James V (Research)=20
  To: Insight-developers (E-mail)=20
  Sent: Monday, October 21, 2002 12:58 PM
  Subject: RE: [Insight-developers] VoronoiSegmentationImageFilter


  More on the VoronoiSegmentation...
  =20
  This filter has an ivar m_Var that can be set by the user or via the =
TakeAPrior() method.  In the=20
  TakeAPrior version, it looks like the standard deviation is being =
stored in the ivar not the variance.
  =20
  What was the intention? To  use variances or standard deviations?
  =20
  The method names, ivar names, and calculations should be consistent.
  =20
  =20
    -----Original Message-----
    From: Miller, James V (Research)=20
    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. =20
      itk::VoronoiSegmentationImageFilter<FloatImage, =
FloatImage>::Pointer
        voronoi=3Ditk::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();
    =20

    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=20
    _____________________________________
    Visualization & Computer Vision
    GE Research
    Bldg. KW, Room C218B
    P.O. Box 8, Schenectady NY 12301

    millerjv@research.ge.com

    james.miller@research.ge.com
    (518) 387-4005, Dial Comm: 8*833-4005,=20
    Cell: (518) 505-7065, Fax: (518) 387-6981=20

    =20



------=_NextPart_000_0029_01C27905.BEF99420
Content-Type: text/html;
	charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML xmlns:o =3D "urn:schemas-microsoft-com:office:office"><HEAD>
<META content=3D"text/html; charset=3Diso-8859-1" =
http-equiv=3DContent-Type>
<META content=3D"MSHTML 5.00.3504.2500" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT face=3DArial size=3D2>Yes, I should change the ivar name, =
they all should=20
be standard deviations.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>I think previously, we use variance, =
but later on,=20
figure that std be more intuitive and easier to figure.</FONT></DIV>
<DIV>&nbsp;</DIV>
<BLOCKQUOTE dir=3Dltr=20
style=3D"BORDER-LEFT: #000000 2px solid; MARGIN-LEFT: 5px; MARGIN-RIGHT: =
0px; PADDING-LEFT: 5px; PADDING-RIGHT: 0px">
  <DIV style=3D"FONT: 10pt arial">----- Original Message ----- </DIV>
  <DIV=20
  style=3D"BACKGROUND: #e4e4e4; FONT: 10pt arial; font-color: =
black"><B>From:</B>=20
  <A href=3D"mailto:millerjv@crd.ge.com" =
title=3Dmillerjv@crd.ge.com>Miller, James V=20
  (Research)</A> </DIV>
  <DIV style=3D"FONT: 10pt arial"><B>To:</B> <A=20
  href=3D"mailto:Insight-developers@public.kitware.com"=20
  title=3DInsight-developers@public.kitware.com>Insight-developers =
(E-mail)</A>=20
  </DIV>
  <DIV style=3D"FONT: 10pt arial"><B>Sent:</B> Monday, October 21, 2002 =
12:58=20
  PM</DIV>
  <DIV style=3D"FONT: 10pt arial"><B>Subject:</B> RE: =
[Insight-developers]=20
  VoronoiSegmentationImageFilter</DIV>
  <DIV><BR></DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff =
size=3D2>More on the=20
  VoronoiSegmentation...</FONT></SPAN></DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff=20
  size=3D2></FONT></SPAN>&nbsp;</DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff =
size=3D2>This filter has=20
  an ivar m_Var that can be set by the user or via the TakeAPrior()=20
  method.&nbsp; In the </FONT></SPAN></DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff =
size=3D2>TakeAPrior=20
  version, it looks like the standard deviation is being stored in the =
ivar not=20
  the variance.</FONT></SPAN></DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff=20
  size=3D2></FONT></SPAN>&nbsp;</DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff =
size=3D2>What was the=20
  intention? To&nbsp; use variances or standard =
deviations?</FONT></SPAN></DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff=20
  size=3D2></FONT></SPAN>&nbsp;</DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff =
size=3D2>The method=20
  names, ivar names, and calculations should be =
consistent.</FONT></SPAN></DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff=20
  size=3D2></FONT></SPAN>&nbsp;</DIV>
  <DIV><SPAN class=3D532455416-21102002><FONT color=3D#0000ff=20
  size=3D2></FONT></SPAN>&nbsp;</DIV>
  <BLOCKQUOTE dir=3Dltr=20
  style=3D"BORDER-LEFT: #0000ff 2px solid; MARGIN-LEFT: 5px; =
MARGIN-RIGHT: 0px; PADDING-LEFT: 5px">
    <DIV align=3Dleft class=3DOutlookMessageHeader dir=3Dltr><FONT =
face=3DTahoma=20
    size=3D2>-----Original Message-----<BR><B>From:</B> Miller, James V =
(Research)=20
    <BR><B>Sent:</B> Monday, October 21, 2002 12:26 PM<BR><B>To:</B>=20
    Insight-developers (E-mail)<BR><B>Subject:</B> [Insight-developers]=20
    VoronoiSegmentationImageFilter<BR><BR></FONT></DIV>
    <DIV><SPAN class=3D794501816-21102002><FONT size=3D2>I am having =
problems=20
    getting the VoronoiSegmentation filter to produce any output.&nbsp;=20
    </FONT></SPAN></DIV>
    <DIV class=3DSection1>
    <P class=3DMsoNormal><FONT size=3D2>&nbsp;=20
    itk::VoronoiSegmentationImageFilter&lt;FloatImage,=20
    FloatImage&gt;::Pointer<BR>&nbsp;&nbsp;&nbsp;=20
    voronoi=3Ditk::VoronoiSegmentationImageFilter&lt;FloatImage,=20
    FloatImage&gt;::New();<BR>&nbsp; voronoi-&gt;SetInput(=20
    original-&gt;GetOutput() );<BR>&nbsp; voronoi-&gt;SetNumberOfSeeds( =
100=20
    );<BR>&nbsp; voronoi-&gt;SetOutputBoundary( false );<BR>&nbsp;=20
    voronoi-&gt;SetSteps( 500 );<BR>&nbsp; voronoi-&gt;TakeAPrior(=20
    masker-&gt;GetOutput() );<BR>&nbsp;=20
    voronoi-&gt;SetMeanPercentError(0.1);<BR>&nbsp;=20
    voronoi-&gt;SetVarPercentError(1);<BR>&nbsp;=20
    voronoi-&gt;Update();<BR></FONT>&nbsp;</P>
    <P class=3DMsoNormal><SPAN class=3D794501816-21102002><FONT =
size=3D2>The filter=20
    churns for a while but the output image is blank.</FONT></SPAN></P>
    <P class=3DMsoNormal><SPAN class=3D794501816-21102002><FONT =
size=3D2>(I have=20
    toggled the OutputBoundary flag but I get a&nbsp; blank=20
    image).</FONT></SPAN></P>
    <P class=3DMsoNormal><SPAN class=3D794501816-21102002><FONT =
size=3D2>In terms of=20
    architecture, the prior image (used in TakeAPrior) is not one of the =
filter=20
    inputs, so the filter does operate properly in the=20
    pipeline.</FONT></SPAN></P>
    <P style=3D"MARGIN: 0in 0in 0pt"><B><SPAN=20
    style=3D"COLOR: navy; FONT-FAMILY: 'Comic Sans MS'">Jim =
Miller</SPAN></B>=20
    <BR><B><I><SPAN=20
    style=3D"COLOR: red; FONT-FAMILY: Arial; FONT-SIZE: =
10pt">_____________________________________</SPAN></I></B><BR><EM><SPAN=20
    style=3D"COLOR: black; FONT-FAMILY: Arial; FONT-SIZE: =
7.5pt">Visualization=20
    &amp; Computer Vision</SPAN></EM><I><SPAN=20
    style=3D"COLOR: black; FONT-FAMILY: Arial; FONT-SIZE: =
7.5pt"><BR><EM>GE=20
    Research</EM><BR><EM>Bldg. KW, Room C218B</EM><BR><EM>P.O. Box 8,=20
    Schenectady NY 12301</EM><BR><BR></SPAN></I><EM><U><SPAN=20
    style=3D"COLOR: blue; FONT-SIZE: 7.5pt"><A=20
    =
href=3D"mailto:millerjv@research.ge.com">millerjv@research.ge.com</A></SP=
AN></U></EM></P>
    <P style=3D"MARGIN: 0in 0in 0pt"><EM><U><SPAN=20
    style=3D"COLOR: blue; FONT-SIZE: =
7.5pt">james.miller@research.ge.com</SPAN></U></EM><BR><I><SPAN=20
    style=3D"COLOR: black; FONT-FAMILY: Arial; FONT-SIZE: 7.5pt">(518) =
387-4005,=20
    Dial Comm: 8*833-4005, </SPAN></I><BR><I><SPAN=20
    style=3D"COLOR: black; FONT-FAMILY: Arial; FONT-SIZE: 7.5pt">Cell: =
(518)=20
    505-7065, Fax: (518) 387-6981</SPAN></I> </P>
    <P class=3DMsoNormal>&nbsp;<o:p></o:p></P></DIV>
    <DIV>&nbsp;</DIV></BLOCKQUOTE></BLOCKQUOTE></BODY></HTML>

------=_NextPart_000_0029_01C27905.BEF99420--