Skin Colour Segmentation using Fintte Bivariate Pearsonian Type-IV a Mixture Model

Abstract

The human computer interaction with respect to skin colour is an important area of research due to its ready applications in several areas like face recognition, surveillance, image retrievals, identification, gesture analysis, human tracking etc.  For efficient skin colour segmentation statistical modeling is a prime desiderata.  In general skin colour segment is done based on Gaussian mixture model.  Due to the limitations on GMM like symmetric and mesokurtic nature the accuracy of the skin colour segmentation is affected.  To improve the accuracy of the skin colour segmentation system, In this paper the skin colour is modeled by a finite bivariate Pearsonian type-IVa mixture distribution under HSI colour space of the image.  The model parameters are estimated by EM algorithm.  Using the Bayesian frame the segmentation algorithm is proposed.  Through experimentation it is observed that the proposed skin colour segmentation algorithm perform better with respect to the segmentation quality metrics like PRI, GCE and VOI.  The ROC curves plotted for the system also revealed that the developed algorithm segment pixels in the image more efficiently.

Keywords: Skin colour segmentation, HSI colour space, Bivariate Pearson type IVa mixture model, Image segmentation metrics.