Template protection on multiple facial biometrics in the signal domain under visible and near-infrared lightKirchgasser, S., Debiasi, L., Schraml, R., Hofbauer, H., Uhl, A., Boyle, J. ORCID: https://orcid.org/0000-0002-5785-8046 and Ferryman, J. (2020) Template protection on multiple facial biometrics in the signal domain under visible and near-infrared light. In: 8th International Workshop on Biometrics and Forensics (IWBF), 29-30 April 2020, Porto, Portugal, https://doi.org/10.1109/IWBF49977.2020.9107964. Full text not archived in this repository. It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing. To link to this item DOI: 10.1109/IWBF49977.2020.9107964 Abstract/SummaryTemplate 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.
Altmetric Deposit Details University Staff: Request a correction | Centaur Editors: Update this record |