Biometric Template Protection in the Image Domain Using Non-invertible Grey-scale Transforms

Various template protection schemes are providing solutions to fulfil privacy preservation in biometric recognition systems, among them Cancellable Biometrics (CB). In this paper we propose two CB schemes, so called non-invertible many-to-one transforms, that alter the image's grey values in key-dependent manner. The obtained recognition performance and unlinkability results are compared to other signal domain cancellable transformation schemes proposed earlier in literature (block re-mapping and warping). Experiments are conducted on a multi-biometrics dataset including finger-vein, hand-vein and thermal face images. In particular, for thermal face biometrics this represents the first study concerning uni-modal template protection techniques and their respective evaluation.