How to make face images clustering using kmeans clustering?

I detected face using Viola-jones algorithm from video.I cropped faces from each frame.I recognized faces using eigen faces.In eigenface algorithm I calculated euclidian distance for input image.I even calculated threshold to recognize faces.Recognizing is over I guess.But now i have to do clustering.I dont know how to start.Can you suggest me to how to start?

Answer 1

[Shashank Prasanna]

You can start with the examples on the documentation page for KMEANS:

http://www.mathworks.com/help/stats/kmeans.html

You'll need 2 pieces of information. (1) X: your input matrix of features (2) k: number of clusters. Number of clusters is something you may have to start by guessing if you don't already know.

All that is left is to invoke KMEANS:

[IDX,C,sumd] = kmeans(X,k)

If you don't know how many clusters are there in the data, you can make use of cluster evaluation techniques as follows:

http://www.mathworks.com/machine-learning/examples.html?file=/products/demos/machine-learning/clusters_evaluation/cluster_evaluation.html

[prashanth]

I know number of clusters k.Please can you explain me little bit about X:input matrix of features?How to get this input matrix.Actually I used Eigenfaces to recognize faces.I calculated euclidian distance and threshold for input image.Is this anything helpful for X:input matrix of features?Iam new to this image processing.

[Shashank Prasanna]

Its a matrix of features, could be a vector form of the image. Maybe this example is useful:

http://www.mathworks.com/machine-learning/examples.html?file=/products/demos/machine-learning/color-based-segmentation-using-k-means-clustering/color-based-segmentation-using-k-means-clustering.html