QuickShift: Hierarchical clustering based on the estimated density...

In benja0x40/QuickShift: QuickShift

Description

Hierarchical clustering based on the estimated density gradient

Usage

QuickShift(x, n, d = NULL, k = NULL, ...)

Arguments

x	numeric matrix representing multivariate data where rows = observations and columns = measurement conditions.
n	desired number of clusters.
d	numeric vector representing a density estimation at each observation.
k	number of nearest neighbors for density estimation (used only when argument d is not provided).
...	optional arguments passed to the QuickShiftAlgorithm or QuickShiftClusters functions.

Value

This function returns a list with the following elements:

membership	vector of integers in [1, nclust] indicating to which cluster each observation belongs.
csizes	number of observations in each cluster.
nclust	number of clusters.

And optionally:

graph

the QuickShift graph (see QuickShiftAlgorithm).

References

Vedaldi A., Soatto S. (2008) Quick Shift and Kernel Methods for Mode Seeking. In: Forsyth D., Torr P., Zisserman A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5305. Springer, Berlin, Heidelberg http://dx.doi.org/10.1007/978-3-540-88693-8_52

See Also

QuickShiftAlgorithm, QuickShiftClusters, knn_density

benja0x40/QuickShift documentation built on Jan. 22, 2021, 7:43 p.m.