A mixture of ellipsoidal densities for 3D data modelling

Abstract: In this paper, we propose a new ellipsoidal mixture model. This model is based a new probability density function belonging to the family of elliptical distributions and designed to model points spread around an ellipsoidal surface. Then, we consider a mixture model based on this density, whose parameters are estimated with the help of an EM algorithm. The properties of the estimates are studied theoretically and empirically. The algorithm is compared to a state of the art ellipse fitting method and experimented on 3D data.