Antonius Hermanus Maria Akkermans

Face recognition with renewable and privacy preserving binary templates

This paper considers generating binary feature vectors from biometric face data such that their privacy can be protected using recently introduced helper data systems. We explain how the binary feature vectors can be derived and investigate their statistical properties. Experimental results for a subset of the FERET and Caltech databases show that there is only a slight degradation in classification results when using the binary rather than the real-valued feature vectors. Finally, the scheme to extract the binary vectors is combined with a helper data scheme leading to renewable and privacy preserving facial templates with acceptable classification results provided that the within-class variation is not too large.

3D Face: biometric template protection for 3d face recognition

In this paper we apply template protection to an authentication system based on 3D face data in order to protect the privacy of its users. We use the template protection system based on the helper data system (HDS). The experimental results performed on the FRGC v2.0 database demonstrate that the performance of the protected system is of the same order as the performance of the unprotected system. The protected system has a performance of a FAR ≈ 0.19% and a FRR ≈ 16% with a security level of 35 bits.

Scanning optical microscope

In a scanning optical microscope a beam splitter (120) is arranged in the radiation path of the scanning beam with which splitter a reference beam synchronously moving with the scanning spot (21) is split off to a reference plane (140). The movement of the scanning spot (21) can be checked by measuring, with the aid of a radiation detector (160), the movement of a reference spot (121) formed by the reference beam in the reference plane. In this way an accurate determination of the position of the scanning spot (21) is possible while using simple beam-deflecting elements (40,42) having a relatively low accuracy. A cylindrical lens (131) gives the scanning spot the shape of a line, so that sensitivity to dust and other contaminations on the reference plane is reduced considerably.

Robust and Secure Biometrics: Some Application Examples

In the past years there has been much theoretical interest in secure extraction of robust strings from noisy measurements. In particular this technique allows extracting robust cryptographic keys from noisy biometric data. This paper starts with an overview of the ideas behind robust and secure string extraction in terms of information reconciliation, privacy amplification and helper data. The main part of the paper gives three application examples explaining how these techniques are used to enhance the convenience and security of devices (e.g. tokens) while preserving also the privacy of the user because neither biometric information nor secret cryptographic keys need to be stored on applications. We discuss a server access token, a 3-way check for a biometric ePassport and a password vault.