Charles,<div><br></div><div>I believe that the way this works is that at every iteration every point in the current segmentation and neighborhood are evaluated against the current mean and standard deviation. Which means that as you progress a segmentation can shrink as well as grow. What you are seeing is exactly that. At first, when the variance is high, the segmentation brings in more voxels. Then as more voxels begin getting accumulated near the mean, the variance decreases and previously acceptable voxels are discarded. So, it is behaving as designed. WHether the design is correct is a different discussion. :-)</div>
<div><br></div><div>- Wes<br><br><div class="gmail_quote">On Fri, Apr 1, 2011 at 8:47 AM, charles mac duff <span dir="ltr"><<a href="mailto:charlesmcdff@gmail.com">charlesmcdff@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<p class="MsoNormal"><span lang="EN-US">Hi
everyone,</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal"><span lang="EN-US">I notice
that when I’m using the plug-in: Confidence connected of VolView 3.2, there’s
something strange happening for certain set of parameters.</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal"><span lang="EN-US">When I set
the number of iteration to 1 and the variance multiplier to 1 (other
parameters by default), the final segmented volume is bigger than when I put
the number of iteration to 20 (with the same variance multiplier).</span></p>
<p class="MsoNormal"><span lang="EN-US">Logically,
at 20 iterations, the final segmented volume should be bigger because de growth
has processed several times.</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal"><span lang="EN-US">Also, after
a variance multiplier of about 1.5, the algorithm begins to work normally (more
iterations we have, bigger the final segmented volume will be).</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal"><span lang="EN-US">So, I
wonder what’s happening.</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal"><span lang="EN-US">Thank you
very much in advance for your precious help, </span></p>
<br clear="all"><br>-- <br><font color="#888888"><font color="#3366ff" face="courier new,monospace">Charles Mac Duff<span></span><span></span></font><br>
</font><br>_____________________________________<br>
Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
<br>
Visit other Kitware open-source projects at<br>
<a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
<br>
Kitware offers ITK Training Courses, for more information visit:<br>
<a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
<br>
Please keep messages on-topic and check the ITK FAQ at:<br>
<a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
<br>
Follow this link to subscribe/unsubscribe:<br>
<a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
<br></blockquote></div><br><br clear="all"><br>-- <br>Wesley D. Turner, Ph.D.<br>Kitware, Inc.<br>Technical Leader<br>28 Corporate Drive<br>Clifton Park, NY 12065-8662<br>Phone: 518-881-4920<br>
</div>