Operation: fuzzy c means clustering

fuzzy c means clustering

Author:

The algorithm as described in the paper below has been implemented by Volker Baecker.
 
Professional Paper, Comparison of Fuzzy C-means Algorithm and New Fuzzy Clustering and Fuzzy Merging Algorithm,
Liyan Zhang, Computer Science Department University of Nevada, Reno Reno, NV 89557,

Example

input image    result image

Description

The operation segments an image into n classes using the fuzzy c means clustering algorithm. 

Options

options
number of clusters: The number of clusters is the number of different segments in the result image.
max. iterations.: The maximum number of iterations that the optimisation runs.
fuzziness: The higher this value, the faster the algorithm converges.
min quality: The minimal quality that must be  reached before the algorithm may be stopped because of the quality change threshold.
quality change threshold: The algorithm stops when the change of the quality is less then the threshold value and the min quality has already been reached.

Parameter

The only parameter is the input image.

Results

The only result is the result image. Each cluster is represented by a different number (0, 1, 2, ...) starting from 0.