Rvcg (version 0.24)

vcgKmeans: fast Kmean clustering for 1D, 2D and 3D data

Description

fast Kmean clustering for 1D, 2D and 3D data

Usage

vcgKmeans(x, k = 10, iter.max = 10, getClosest = FALSE, threads = 0)

Value

returns a list containing

centers

cluster center

class

vector with cluster association for each coordinate

If getClosest=TRUE

selected

vector with indices of points closest to the centers

Arguments

x

matrix containing coordinates or mesh3d

k

number of clusters

iter.max

maximum number of iterations

getClosest

logical: if TRUE the indices of the points closest to the k-centers are sought.

threads

integer: number of threads to use

See Also

vcgSample

Examples

require(Rvcg);require(rgl)
data(humface)
set.seed(42)
clust <- vcgKmeans(humface,k=1000,threads=1)