On 1/24/07, <b class="gmail_sendername">José Santamaría López</b> <<a href="mailto:jsantam@ugr.es">jsantam@ugr.es</a>> wrote:<br><br><div><span class="gmail_quote"></span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Could someone tell me how many metrics there exist<br>in ITK working with cloud of points images or these<br>ones with additional information such as normals or<br>curvature information ?</blockquote><div><br>"could of points image with normals / curvature information" is a bit vague.
<br>
<br>Please clarify if you have a <br> (1) point set or <br> (2) mesh (point set with connectivity info)<br> (3) a bunch of pixels in an image, that you're referring to as a point set.<br><br>----<br><br>If what you have is a point set (1), then ITK offers you the metrics :
<br> - ICP <br> - Hausdorff distance [The filter in ITK takes images as input, but if you have a point set, you should find it really simple to do that with a forloop ].<br><br>---<br><br>If you have a mesh (2), nothing that I know of that takes advantage of connectivity as well.
<br><br>---<br><br>If you have a bunch of pixels in an image (3) ..<br><br>Where did those pixels come from ? <br>(a) If they are the points that represent the contour of a segmented object, the hausdorff distance filter will work for you.
<br>(b) You can compute the signed distance image of one object from the other (the hausdorff distance is actually a max function of this distance) and compute the mean signed distance.<br>(c) Narrow band to narrow band registration - Please Read
<a href="http://www.itk.org/cgi-bin/viewcvs.cgi/*checkout*/Papers/MedIASpecialIssue/NarrowBandToImageRegistration/NarrowBandToImageRegistration.pdf?rev=1.1&root=InsightDocuments">http://www.itk.org/cgi-bin/viewcvs.cgi/*checkout*/Papers/MedIASpecialIssue/NarrowBandToImageRegistration/NarrowBandToImageRegistration.pdf?rev=1.1&root=InsightDocuments
</a><br><br>HTH<br>-karthik<br></div></div>