<div><div>Good morning Maria,<br><br>I have an ITK implementation of the Chan-Vese "Active Contours without Edges for Vector Valued Images" paper (<a href="http://www.math.ucla.edu/~lvese/PAPERS/JVCIR2000.pdf">http://www.math.ucla.edu/~lvese/PAPERS/JVCIR2000.pdf
</a>). This paper details a level set method to create a segmentation which can be based on spectral information (take a look at some of the examples in the paper). If this might be applicable to your problem, I would be interested in sharing the code and / or discussing further.
<br><br>Cheers,<br><br>Benjamin Smith<br> </div><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">------------------------------<br><br>Message: 3
<br>Date: Mon, 8 Jan 2007 00:31:04 +0100<br>From: "Maria Cira Avvinto" <<a href="mailto:millarkaa@gmail.com">millarkaa@gmail.com</a>><br>Subject: [Insight-users] Level Set Segmentation<br>To: <a href="mailto:insight-users@itk.org">
insight-users@itk.org</a><br>Message-ID:<br> <<a href="mailto:c26d75cf0701071531j6718c2bdk715c73dd87245c37@mail.gmail.com">c26d75cf0701071531j6718c2bdk715c73dd87245c37@mail.gmail.com</a>><br>Content-Type: text/plain; charset=ISO-8859-1; format=flowed
<br><br>Hi,<br>I have a two important question:<br>1)Can i use level set segmentation for multispectral image?<br><br>2)Where can i collocate level set method in this scheme?<br><br> Image Segmentation Method
<br> / \<br> Single Contrast Multispectral<br> |<br> |_______<br> Threshold /
<br> \<br> |<br>Supervised Unsupervised<br> Boundary Tracing |<br> | Pattern
<br> Edge Detector Recognition<br> | |<br> Seed Growing Artificial<br>
| Neural<br> Template Model Networks<br> |<br> Random Fields<br><br><br><br>
Please, help me.<br>Thanks a lot to everybody.<br><br>Mary<br><br><br>------------------------------<br></blockquote></div><br>