Recovering facial pose with the EM algorithm

Abstract

This paper describes how 3D facial pose may be estimated by fitting a template to 2D feature locations. The fitting process is realised as projecting the control points of a 3D template onto the 2D feature locations under orthographic projection. The parameters of the orthographic projection are iteratively estimated using the EM algorithm. The method is evaluated on both contrived data with known ground-truth together with some more naturalistic imagery. These experiments reveal that under favourable conditions the algorithm can estimate facial pitch to within 3°.