MATLAB: K-Means: Indices of C in idx

centroidsclusterkmeans

Hello, I'm using the built-in kmeans function but I don't understand a thing. After I've applied the function, I have two output parameters: idx and C. The first one is a matrix containing, for each observation, the cluster's index where it has been classified. The second one is the matrix containing all the centroids location. Well, is there a way to know which are the indices of the centroids C inside the matrix idx? For example, I would like to know the index inside idx of C(:,1), etc.

Thank you very much.

Best Answer

I'm not certain I fully understand your question, but I'll make a guess.

The centroid is not (necessarily) one of the points of the original dataset, so none of the rows of idx correspond to the centroid itself.

The centroid locations are given by the rows of C (not the columns). The row C(1,:) is the centroid for the cluster of points with idx=1. The row C(2,:) is the centroid for the cluster of points with idx=2. And so on.

If that doesn't answer your question, maybe you could comment with some clarification.

Related Solutions

MATLAB: K-means: see the initial centroids

Yes it is possible.

kmeans allows you to set option parameters via the statset function. In the help page kmeans there some examples on how using stateset.

Set the parameter 'OutputFcn' as shown in this tutorial, for displaying iteration results in iterative solvers: https://it.mathworks.com/help/matlab/math/output-functions.html

MATLAB: How can I access to pixels of objects produced by connected componenets function

bwconncomp only returns the indices of the non-zero pixels.

bwconncomp returns a structure. The PixelIdxList field of the structure is a cell array. Each element of the cell array is a vector of linear indices. You can use ind2sub() if you want to turn those linear indices into row and column subscripts.

Example:

bw = rand(20,30) > 0.3;      %sample data
CC = bwconncomp(bw);
idxlists = CC.PixelIDxList;
first_component_idx = idxlists{1};
%now some manipulation
%notice we did not use bw(R(1:2), C(1:2)) as that would usually access 2 x 2 pixels
[R, C] = ind2sub(size(bw), first_components_idx);
bw(R(1), C(1)) = 0;
bw(R(2), C(2)) = 0;
%alternate manipulation equivalent to the above
bw(first_components_idx(1:2)) = 0;

Best Answer

Related Solutions

MATLAB: K-means: see the initial centroids

MATLAB: How can I access to pixels of objects produced by connected componenets function

Related Question