Fiducial facial point extraction with cross ratio
Hao Wang, Xin Fan, Yuntao Li · 2014
Automatic extraction of fiducial facial points is one of the key steps to face tracking, recognition and animation as well as video communication. In this paper, we present a method to localize 8 fiducial points in a face image with cross ratio (CR), a fundamental projective invariant. We derive strong shape priors, which characterize the intrinsic geometries shared by human faces, from CR statistics on a moderate size (515) of frontal upright faces. We combine these shape priors with Gabor textural features and edge/corner into a convex optimization. The Gabor features of local patches and geometric constraints from CR are insensitive to global perspective transformations. Thereafter, the proposed approach renders the robustness to great pose or viewpoint changes. Extensive experiments on facial images from several data sets with great variations on expressions, illuminations and poses demonstrate the effectiveness of the proposed approach.