2013-07-31 05:03:20 -0600 | commented answer | hierarchical Clustering VS Kmeans Clustering If you mean flann::hierarchicalClustering in OpenCV it is a hierarchical k-means tree. You need to create a matrix for centers. The centers.rows will be the upper limit of clusters which you need. This matrix will contain the obtained centers of clusters. |
2013-07-31 02:41:41 -0600 | answered a question | hierarchical Clustering VS Kmeans Clustering That is not bad the explanation of the differences between hierarchical and k-means clustering(page 46): http://www.lcb.uu.se/KBIB/materials/L1.pdf. And there is an rational thought about the using of hierarchical k-means (top-down hierarchical clustering using k-means iteratively) there. The advantage of one or the other method depends of the task's conditions. |