<html>
<head>
<style><!--
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 12pt;
font-family:Calibri
}
--></style></head>
<body class='hmmessage'><div dir='ltr'><div><div>Hi,</div></div><div><br></div><div><p class="MsoNormal"><span lang="EN-US">The
implementation of Mattes Mutual Information is much faster in contrary to
Normalized MI. Like I understood, this is due to the fact how the histograms
respectively the probability distributions are calculated / estimated. Like
Louis suggested[1] Mattes MI could be modified to obtain NMI. I tried that by
changing itkMattesMutualInformationImageToImageMetric (ITK version 4.3.1) at lines
583-617 (and accordingly 862-944) to the code below.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Because I
don’t want to mess up the ITK library on my system, I’d like to ask if someone
could explain, how to test the code and integrate it into the library.<o:p></o:p></span></p><p class="MsoNormal"><span lang="EN-US"><br></span></p><p class="MsoNormal"><span lang="EN-US">Kid Regards,</span></p><p class="MsoNormal"><span lang="EN-US">Omar Hamo</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal">[1] <span lang="EN-US"><span lang="DE"><a href="http://public.kitware.com/pipermail/insight-users/2006-May/017911.html">http://public.kitware.com/pipermail/insight-users/2006-May/017911.html</a></span></span><o:p></o:p></p><p class="MsoNormal"><span lang="EN-US"><br></span></p><p class="MsoNormal"><span lang="EN-US"><br></span></p></div> </div></body>
</html>