Support:Documents:Examples:K-Means and Fuzzy C-Means analysis

From COMKAT wiki
Jump to navigation Jump to search

K-Means and Fuzzy C-Means

In COMKAT R4.0a, you can analyze images by K-Means or Fuzzy C-Means clustering.


1.Select Image > Clustering

K Fuzzy Means 1.png


2.You can select K-Means or Fuzzy C-Means here:

K Fuzzy Means 2.png


3.If you select Fuzzy C-means, you can output Labels or Probability Maps /membership functions :

K Fuzzy Means 3.png


4.Assign number of clusters

K Fuzzy Means 4.png


5.If your images are several MR contrast (muti-bands), you can also analyze band-2 and band-3 by unchecking the checkbox as follows:

K Fuzzy Means 12.png


Examples

Here we use Fuzzy C-means for an example.


1.Load phantom imge:

a= phantom(256);
b= phantom(256);
c= cat(3,a,b);           % COMKAT do not read 2-D image
comkatimagetool(c)

2.Select Colormap > GreenFire

K Fuzzy Means 6.png


3.Select Image > Clustering

K Fuzzy Means 7.png


4.Set as follows:

K Fuzzy Means 8.png

5.Results

K Fuzzy Means 13.png