Mahalanobis distance in Kmeans Clustering using OpenCV

Question

I made a Kmeans cluster and discovered cluster centers using the OpenCV C ++ API.

kmeans(data_points, clusterCount, labels, TermCriteria( CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 10, 1.0), 3, KMEANS_PP_CENTERS, cluster_centers); 

Then I use the Euclidean distance to find the closest cluster for a new data point for all cluster centers .

 int distance = find_EucledianDist(new_datapoint, cluster_centers); 

How to use Mahalanobis Distance instead of Euclidean Distance ? I know that I need to calculate the covariance matrix and invert it and find the Mahalanobis distance.

However, I don’t know how I do it and in which ORDER (find the Kova matrix, the inverted matrix from which the data / matrix is)?

Answer 1

Could this link help you? :)

http://books.google.fr/books?id=seAgiOfu2EIC&pg=PA475&lpg=PA475&dq=mahalanobis+opencv&source=bl&ots=hSG09ijHLe&sig=H359_fRI53Pg12dYLOVUJpopb0g&hl=fr&sa=X&ei=O-JMT9-oAYem0AXIpL2eBQ&ved=0CEkQ6AEwBA#v=onepage&q=mahalanobis%20opencv&f= false

It will be: CalcCovarMatrix , then cvInvert and finally cvMahalanobis .