<div>Hi Ella,</div>
<div> </div>
<div>You could look at creating a preliminary rough segmentation and putting a bounding box around it and then do an iterative refined segmentation within the bounding box around a label map. </div>
<div> </div>
<div>A bounding box can be created using the Label Geometry Filter: </div>
<div><a href="http://www.insight-journal.org/browse/publication/301">http://www.insight-journal.org/browse/publication/301</a><br></div>
<div>This is related to the Label Statistics Filter as well:</div>
<div>(you create a label map)</div>
<div><a href="http://www.insight-journal.org/browse/publication/176">http://www.insight-journal.org/browse/publication/176</a></div>
<div> </div>
<div>Take care,</div>
<div>John<br></div>
<div class="gmail_quote">On Tue, Mar 22, 2011 at 2:50 AM, Ella Maria Kadas <span dir="ltr"><<a href="mailto:ella_kadas@yahoo.com">ella_kadas@yahoo.com</a>></span> wrote:<br>
<blockquote style="BORDER-LEFT: #ccc 1px solid; MARGIN: 0px 0px 0px 0.8ex; PADDING-LEFT: 1ex" class="gmail_quote">
<table border="0" cellspacing="0" cellpadding="0">
<tbody>
<tr>
<td valign="top">Hi,<br><br> I am trying to use in a processing step the region growing filters in a 3D image. My problem is that no matter which filter i use from the ThresholdConnected, ConfidenceConected or even NeihborhoodConnected and no matter how i set the parameters i always get in some cases sometimes almost the hole image.<br>
Even if i doesn't seem that the points are related as neighbors and grey values. <br> So i was wondering if there is some way the define like a bounding cube, in order to do apply this filters only on a volume cut from the image.<br>
I suppose i could create a new image only containing this cut, i am just afraid that i will get in trouble then to go back with the segmented region in the right position on the original image.<br> Is there some other good way to do this?<br>
Thanks,<br>Ella<br></td></tr></tbody></table><br><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>
<div>John Drozd<br></div>
<div>Post-Doctoral Fellow, Robarts Research Institute</div>
<div>The University of Western Ontario</div>
<div>London, ON, Canada<br></div><br>