Abstract
Template protection techniques like cancellable biometrics have been introduced in order to overcome privacy issues in biometric applications. We conduct an ISO/IEC Standard 24745 compliant assessment of block re-mapping and warping focusing on recognition performance issues as well as security and unlinkability aspects. Both of these template protection schemes are applied on a multi-biometrics dataset in the signal (image) domain. The dataset includes 2D face, iris and periocular images which have been acquired not only using visual light (VIS) but also near-infrared light (NIR). With respect to the used data, this is the first study that applies and evaluates cancellable template protection methods in the signal domain on VIS/NIR 2D face, iris and periocular biometrics.
Author supplied keywords
Cite
CITATION STYLE
Kirchgasser, S., Debiasi, L., Schraml, R., Hofbauer, H., Uhl, A., Boyle, J., & Ferryman, J. (2020). Template Protection on Multiple Facial Biometrics in the Signal Domain under Visible and Near-Infrared Light. In 2020 8th International Workshop on Biometrics and Forensics, IWBF 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/IWBF49977.2020.9107964
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.