Evolution Strategies for Matching Active Appearance Models to Human Faces

Face registration is a challenging problem due in part to the non-rigid nature of human faces. Active Appearance Models (AAMs) have been proposed as a useful technique for face registration in part because they can account for changes in shape. Fitting of AAMs to imagery is typically done using the Gauss-Newton method; however this approach is known to fail when either the initial shape estimate is to far off and/or the appearance model fails to direct search toward a good match. In this paper, the authors employ Evolution Strategies (ES) to search for a near optimal fit, i.e. set of model parameters that relate an AAM to a novel face image. In addition, they dramatically reduce the dimensionality of the search problem by analytically determining the optimal texture parameters associated with any given shape.