<table cellspacing="0" cellpadding="0" border="0" ><tr><td valign="top" style="font: inherit;">Dear Jack,<div><br></div><div>In addition to what karthik said, there is an open source software based on the ITK</div><div><br></div><div>developed by the Image Sciences Institute in Netherlands (elastix) which already </div><div><br></div><div>supports multiple metrics for image registration. You can download the elastix from </div><div><br></div><div>the following link,</div><div><br></div><div>http://elastix.isi.uu.nl/index.php</div><div><br></div><div>Hope this
helps,</div><div><br></div><div>Dawood</div><div><br></div><div><br></div><div>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<</div><div><br></div><div>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<</div><div><br></div><div><br></div><div><span class="Apple-style-span" style="font-family: 'Times New Roman'; font-size: medium; "><pre>Create a metric that contains these two metrics and delegates the GetValue
and GetValueAndDerivative to the two internal metrics. You could return a
lagrangian sum of both metrics if using a single valued optimizer / cost
function, or return both measures as a vector, if using a multi-valued
optimizer / cost function
On Wed, Feb 9, 2011 at 9:03 PM, Jack C. H. Hu <<a href="http://www.itk.org/mailman/listinfo/insight-users">m0985501 at mail.nuk.edu.tw</a>>wrote:
><i> hello all
</i>><i>
</i>><i> i'm wondering to know how to minimize more than one metric while
</i>><i> registering. for example, minimizing both mean square error and point set
</i>><i> distance.
</i>><i> thank you.
</i>><i>
</i>><i> regards,
</i>><i> Chia-Hsiang Hu</i></pre></span></div></td></tr></table><br>