K-means++ clustering for classification

K-means clustering algorithm implementation with k-means++ augmentation.

K-means++ augmentation improves both the speed and the accuracy of the k-means clustering algorithm.

The Matlab code of the algorithm is provided together with a simple elbow searching function to get the minimum of the objective function when the slope of the curve becomes less than 2%.

As a stopping criterion for the clustering algorithm, a threshold on the relative difference of the values of the objective function compared to the best found has been considered.