A generic, transform invariant 3D facial feature detection method based on mean (H) and Gaussian (K) curvature analysis is proposed. A scale space of the HK values is constructed differently from the previous HK attempts. The 3D features are extracted from this scale space and used in a global topology, which is trained with a Gaussian model using only faces with neutral and frontal poses. The model is then tested against 1323 faces with various poses and expressions. The method is compared with four other representative algorithms from the previous literature for 3D facial feature localisation and face detection purposes.