Path: news.mathworks.com!not-for-mail
From: "Sven " <sven.holcombe@gmail.deleteme.com>
Newsgroups: comp.soft-sys.matlab
Subject: Deformable model
Date: Tue, 17 Jun 2008 13:33:01 +0000 (UTC)
Organization: The MathWorks, Inc.
Lines: 26
Message-ID: <g38eed$inv$1@fred.mathworks.com>
Reply-To: "Sven " <sven.holcombe@gmail.deleteme.com>
NNTP-Posting-Host: webapp-03-blr.mathworks.com
Content-Type: text/plain; charset="ISO-8859-1"
Content-Transfer-Encoding: 8bit
X-Trace: fred.mathworks.com 1213709581 19199 172.30.248.38 (17 Jun 2008 13:33:01 GMT)
X-Complaints-To: news@mathworks.com
NNTP-Posting-Date: Tue, 17 Jun 2008 13:33:01 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 1326470
Xref: news.mathworks.com comp.soft-sys.matlab:474227



Hi there,

I am attempting to segment a series of images based on a
known approximate model.

I have:
a) Grayscale image (in this case, chest CT slice)
b) Template location (approximate center of vertebra)
c) Template (a circle)

I want to try and make my template deform to match the edges
of the actual vertebra (just the main, mostly circular, part).

My template would be a circle with, say, 10 atoms around the
perimeter, and I want to try to make them migrate to the
edges of the image (that I can try to find with some filtering).

Does anybody have some startup code of something similar
from which I can work from?
Has anybody made an implementation of "deformable m-reps" in
matlab?

Any help would be fantastic.

Cheers,
Sven.