: 2D Face images are traditionally used in civil governmental applications. An extension from 2D to 3D images will lead to several advantages when setting up automated authentication systems. However, privacy concerns of storing face images on smart cards or in databases will inhibit the acceptance of such systems. In this paper we concentrate on privacy enhancing technologies for biometric information where we focus on 3D face images. The feature vectors are obtained using a histogram-based approach and the privacy protected templates are generated based on fuzzy extractors. It is shown that the private face recognition system has an acceptable verification performance. Finally, it is described how the proposed system can be used in the setting of an ePassport.
Xuebing Zhou, Tom A. M. Kevenaar, Emile Kelkboom,