I don't see anything in the ITK software guide about agglomerative (or divisive) clustering. I would like to take a set of N-d points, treat them each as their own cluster, and then merge clusters until some "continue merging?" tolerance is
met. I don't know the number of clusters so I can't use K-means clustering and this type of clustering has been my fall back - but the memory usage of my implementation grows quickly out of control. Does ITK have anything like this?<br>
<br clear="all">Thanks,<br><br>David<br>