Skip to Main Content
Mixture models are frequently used to fit skin color distributions in various color spaces. However, the high computational cost of the conventional EM algorithm makes it intractable for large data sets. We propose a novel algorithm for estimating the parameters of mixture models. Multidimensional histograms are incorporated into the EM framework to group neighboring datapoints and reduce the size of the data set. We adopt this method to build Gaussian mixture models of skin color and compare the performance of models with different number of components. Further experiments on synthetic data show the efficiency of our method as a general approach to data clustering.