Faltaous, SarahLiebers, JonathanAbdelrahman, YomnaAlt, FlorianSchneegass, Stefan2020-01-152020-01-152019https://dl.gi.de/handle/20.500.12116/31047Biometric authentication received considerable attention lately. The vein pattern on the back of the hand is a unique biometric that can be measured through thermal imaging. Detecting this pattern provides an implicit approach that can authenticate users while interacting. In this paper, we present the Vein-Identification system, called VPID. It consists of a vein pattern recognition pipeline and an authentication part. We implemented six different vein-based authentication approaches by combining thermal imaging and computer vision algorithms. Through a study, we show that the approaches achieve a low false-acceptance rate (“FAR”) and a low false-rejection rate (“FRR”). Our findings show that the best approach is the Hausdorff distance-difference applied in combination with a Convolutional Neural Networks (CNN) classification of stacked images.enThermal imagingusable securitybiometricsText/Journal Article10.1515/icom-2019-00091618-162X