[Insight-users] using itkVoronoiSegmentationImageFilter ?
Seungbum Koo
koosb2@hanmail.net
Tue, 22 Oct 2002 05:51:15 +0900 (KST)
Hi,
<br>Thanks for the help. It worked and segmented but not as I expected. I don't understand well about VoronoiSegmentationImageFilter but it seems to segment all similar color regions in whole image as the seed region. I just wanted to find more exact boundary of that found using FuzzyConnectednessScalarFilter.
<br>Anyway I think the VoronoiSegmentationImageFilter worked fine. What do you think about using DeformableMeshFilter instead of VoronoiSegmentationImageFilter?
<br>
<br>regards
<br>Seungbum Koo
<br>
<br>> Title : Re: [Insight-users] using itkVoronoiSegmentationImageFilter ?
<br>> Date : Sun, 20 Oct 2002 13:34:32 -0400
<br>> From : "Yinpeng Jin" <yj76@columbia.edu>
<br>> To : Seungbum Koo<koosb2@hanmail.net>,<insight-users@public.kitware.com>
<br>>
<br>> if you use takeaprior, then you don't want to setMean and setVar, those two parameters will be calculated from the binary mask.
<br>> and
<br>> try to use
<br>> m_voronoiFilter->SetMeanPercentError(PERCENT);
<br>> m_voronoiFilter->SetVarPercentError(VARPERCENT);
<br>> in stead of
<br>> m_voronoiFilter->SetMeanTolerance(10);
<br>> m_voronoiFilter->SetVarTolerance(20);
<br>>
<br>> they are trying to manipulate the same parameter, but usually are more intuitive to figure.
<br>> the MeanPercentError could usually be set between 0.1 to 0.3
<br>> and the VarPercentError could be between 1 to 3. they don't depends on your pixel intensity range, while the MeanTolerance and VarTolerance usually do.
<br>> Also, you can first output your m_binaryImage to see if it is something reasonable. the VoronoisegmentationImagefilter will need something at least represents
<br>> parts of your target object as the a prior.
<br>> Try the above, and let me know what happens.
<br>> Yinpeng.
<br>>
<br>>
<br>>
<br>> ----- Original Message -----
<br>> From: Seungbum Koo
<br>> To: insight-users@public.kitware.com
<br>> Sent: Sunday, October 20, 2002 12:45 AM
<br>> Subject: [Insight-users] using itkVoronoiSegmentationImageFilter ?
<br>>
<br>>
<br>> Hi,
<br>>
<br>> I'm trying to use itkVoronoiSegmentationImageFilter combined with itkSimpleFuzzyConnectednessScalarImageFilter.
<br>>
<br>> I made a binary image from itkSimpleFuzzyConnectednessScalarImageFilter but I couldn't figure out how to set itkVoronoiSegmentationImageFilter variables. Here is my source code.
<br>>
<br>> =============================================================
<br>> m_voronoiFilter->SetInput(m_rawImageSource->GetOutput());
<br>> m_voronoiFilter->TakeAPrior(m_binaryImage);
<br>> m_voronoiFilter->SetMean(520);
<br>> m_voronoiFilter->SetVar(20);
<br>> m_voronoiFilter->SetMeanTolerance(10);
<br>> m_voronoiFilter->SetVarTolerance(20);
<br>> // m_voronoiFilter->SetNumberOfSeeds(400); // ??
<br>> m_voronoiFilter->SetSteps(5);
<br>> m_voronoiFilter->Update();
<br>> =============================================================
<br>>
<br>> m_binaryImage is calculated from m_rawImageSource and as I expected.
<br>> But this code just makes a black image... all zeros.
<br>><table border=0 cellpadding=0 cellspacing=1 align=center>
<tr><td bgcolor="#ffffff" align="center" width=130>
<iframe src='http://avatarfile.hanmail.net/bin/getavatar?EUSERID=ERhXTWfI29g0&LOOK=1' width=130 height=150 border=0 frameborder=0 scrolling=no></iframe></td>
<td align="left" valign="middle">
<table border=0 cellpadding=0 cellspacing=0>
<tr><td><img src='http://image.hanmail.net/hm/av/box1_c1.gif'></td>
<td background='http://image.hanmail.net/hm/av/box1_upbg.gif'></td>
<td><img src='http://image.hanmail.net/hm/av/box1_c2.gif'></td>
</tr>
<tr><td background='http://image.hanmail.net/hm/av/box1_lbg.gif' valign=top><img src='http://image.hanmail.net/hm/av/box1_c11.gif'></td>
<td background='http://image.hanmail.net/hm/av/box1_bg.gif' style='line-height:120%; padding:10px'><font color=#775100>Seungbum Koo</font></td>
<td background='http://image.hanmail.net/hm/av/box1_rbg.gif'></td>
</tr>
<tr><td><img src='http://image.hanmail.net/hm/av/box1_c3.gif'></td>
<td background='http://image.hanmail.net/hm/av/box1_dwbg.gif'></td>
<td><img src='http://image.hanmail.net/hm/av/box1_c4.gif'></td>
</tr>
</table></td>
<td> </td>
</tr>
</table>
<br><br>
<table border=0 cellpadding=5 cellspacing=0 width=100%%><tr>
<td background='http://image.hanmail.net/hanmail/general/dotline_sim.gif' height=1></td></tr>
<tr><td><font color="#312400" style="font-size:9pt;">"¿ì¸® ÀÎÅͳÝ, Daum"
<a href='http://www.daum.net' target=_top><font color="#312400">http://www.daum.net</font></a>
¡º Æò»ý¾²´Â ¹«·á ÇѸÞÀÏ³Ý ¡»<br></font></td></tr></table>
<table bgcolor="#ECECEC" border=0 cellpadding=0 cellspacing=1 width=100%%><tr bgcolor=#F8F8F8>
<td>
<table border=0 cellpadding=3 cellspacing=0 width=100%%><tr>
<td width=50 align=right nowrap>
<a href='http://hmm.daum.net/footer_msg' target=_blank><img src='http://image.hanmail.net/hanmail/top/adver/messenger.gif' width=40 height=40 border=0></a></td>
<td width=50%% class=base style="line-height:140%%; font-size:9pt;">
<a href='http://hmm.daum.net/footer_msg' target=_blank><font color=#BD8000 style="font-size:9pt;">ºü¸£´Ù! ÆíÇÏ´Ù! Daum¸Þ½ÅÀú</font></a><br>¸ÅÀϸÅÀÏ ¾²°í °è½ÃÁÒ?</td>
<td width=3 nowrap><img src='http://image.hanmail.net/hm/line_h.gif' width=3 height=40></td>
<td width=40><a href='http://hmm.daum.net/card_0401' target=_blank><img src='http://image.hanmail.net/hanmail/top/adver/ecard.gif' width=40 height=40 border=0></a></td>
<td width=50%% class=base style="line-height:140%%; font-size:9pt;">
<a href='http://hmm.daum.net/card_0401' target=_blank><font color=#BD8000 style="font-size:9pt;">Daum¿£ÅÍÄ«µå</font></a><br>Daumȸ¿øÀÇ ÇʼöÇ°! ¿Â¿ÀÇÁ ÃÖ°íÀÇ ÇýÅÃ~</td></tr></table>
</td>
<td width="135" align="center"><a href='http://hmm.daum.net/footer_ad_1007' target='new'>
<img src='http://image.hanmail.net/hm/ad/lotte_1.gif' width=120 height40 border=0></a></td></tr></table>
<img src="http://www24.hanmail.net/Mail-bin/chkcmail?from=koosb2&rcpt=insight%2Dusers%40public%2Ekitware%2Ecom&msgid=%3C20021022055115%2EHM%2EN00000000052U3W%40www24%2Ehanmail%2Enet%3E">