Learning Skin Pixels in Color Images Using Gaussian Mixture

This paper is concerned with estimating a probability density function of human skin color using a finite Gaussian mixture model whose parameters are estimated through the EM algorithm. There are no limitations regarding if person is black or white. Two important sections of Gaussian mixture are parameter estimation and determining the number of mixture components. Experimental results show that the estimated Gaussian mixture model fits skin images from a large database. Using different color models most suitable was chosen and final outputs were showed in the experiments section.