Three dimensional (3D) face recognition is a frequently used biometric and its performance is dependent on registration. Registration aligns two faces and makes a comparison possible between the two surfaces. In the literature, best results have been achieved by a one-to-all approach, where a test face is aligned to each gallery face separately. To overcome the computational bottleneck of this approach, we examine registration based on an Average Face Model (AFM). To improve the registration, we propose to group faces and register with category-specific AFMs. We see that gender and morphology...