<pre>I just want to comment that the morphological reconstruction filters are now available in ITK, as discussed in this ITK paper:<br><br><a href="http://insight-journal.org/dspace/handle/1926/169">http://insight-journal.org/dspace/handle/1926/169
</a><br><br>Improving performance of morphological reconstruction<br>Beare, Richard<br>15-Feb-2006<br><br>itkReconstructionImageFilter<br><br>Josiah Yoder<br><br>----- Original Message ---<br><b>Miller, James V (Research)
</b> <a href="mailto:insight-users%40itk.org?Subject=%5BInsight-users%5D%20Re%3A%20Marker%20controlled%20watershed%2C%20how%20to%20reali%0A%09ze%20in%20ITK&In-Reply-To=" title="[Insight-users] Re: Marker controlled watershed, how to reali
ze in ITK">millerjv at crd.ge.com<br></a><i>Wed Nov 24 10:48:15 EST 2004</i><br><br><br>I believe the morphological reconstructions are related to the <br>geodesic morphology algorithms. There are a number of geodesic<br>
morphology algorithms in ITK<br><br>itkGrayscaleConnectedClosingImageFilter.h<br>itkGrayscaleConnectedOpeningImageFilter.h<br>itkGrayscaleFillholeImageFilter.h<br>itkGrayscaleGeodesicDilateImageFilter.h<br>itkGrayscaleGeodesicErodeImageFilter.h
<br>itkGrayscaleGrindPeakImageFilter.h<br>itkHConcaveImageFilter.h<br>itkHConvexImageFilter.h<br>itkHMaximaImageFilter.h<br>itkHMinimaImageFilter.h<br><br>Jim<br><br><br><br>-----Original Message-----<br>From: Quan Chen [mailto:
<a href="http://www.itk.org/mailman/listinfo/insight-users">quanchen at gmail.com</a>]<br>Sent: Tuesday, November 23, 2004 6:02 PM<br>To: <a href="http://www.itk.org/mailman/listinfo/insight-users">insight-users at itk.org
</a><br>Cc: Luis Ibanez<br>Subject: [Insight-users] Re: Marker controlled watershed, how to realize<br>in ITK<br><br><br>Also, I am wondering if itk implemented the "morphological<br>reconstruction" algorithm. The following example mention about it.
<br><a href="http://www.mathworks.com/products/demos/image/watershed/ipexwatershed.html">http://www.mathworks.com/products/demos/image/watershed/ipexwatershed.html</a><br><br>There is also some papers like:<br><br>Luc Vincent, "Morphological Grayscale Reconstruction in Image
<br>Analysis: Applications and Efficient Algorithms," IEEE transactions on<br>Image Processing, vol 2 no. 2 1993.<br><br><br><br>On Tue, 23 Nov 2004 16:26:02 -0600, Quan Chen <<a href="http://www.itk.org/mailman/listinfo/insight-users">
quanchen at gmail.com</a>> wrote:<br>><i> I just realized someone has already asked this question this month.<br></i>><i> Luis, I don't know whether you proposed would work very well. As<br></i>><i> that coffee bean example shows. The objective is to seperate each
<br></i>><i> coffee beans from each other.<br></i>><i> <a href="http://cmm.ensmp.fr/%7Ebeucher/wtshed.html#examples">http://cmm.ensmp.fr/~beucher/wtshed.html#examples</a><br></i>><i> <br></i>><i> I belive it is an important feature for the watershed filter. Since
<br></i>><i> it offers more user intenvention so that it can do segmentation<br></i>><i> better. If we only rely on the image itself, even with Hierarchical<br></i>><i> segmentation, we would still only got crappy result with watershed
<br></i>><i> filter.<br></i>></pre>