Gaussian curvature-based geometric invariance for ear recognition

Ear recognition is one of the new patterns of biometrics. In this paper we derive a novel geometric invariance on ear surfaces that it is preserved under affine and weak perspective transformations. Our 3D shape features are based on the Gaussian curvature and Mean curvature. When a surface undergoes an affine transformation, the shape features are the affine transformed shape features of the original surface; they are preserved and hence can be for shape matching. We have tested robustness of the shape feature on the 3D ear data for various linear geometric transformations. The experiment results show that our purposed shape feature is suitable for further application to 3D ear identification because its robustness to geometric transformation.