Auflistung nach Autor:in "Haasnoot, Erwin"
1 - 3 von 3
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragFEERCI: A Package for Fast Non-Parametric Confidence Intervals for Equal Error Rates in Amortized O(m log n)(BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group, 2018) Haasnoot, Erwin; Khodabakhsh, Ali; Zeinstra, Chris; Spreeuwers, Luuk; Veldhuis, RaymondEqual Error Rates (EERs), or other weighted relations between False Match and Non- Match Rates (FMR/FNMR), are often used as a performance metric for biometric systems. Confidence Intervals (CIs) are used to denote the uncertainty underlying these EERs, with many methods existing to estimate said CIs in both parametric and non-parametric ways. These confidence intervals provide, foremost, a method of comparing scoring/ranking functions. Non-parametric methods often suffer from high computational costs, but do not make assumptions as to the shape of the EERand score distributions. For both EERs and CIs, contemporary open-source toolkits leave room for improvement in terms of computational efficiency. In this paper, we introduce the Fast EER (FEER) algorithm that calculates an EER in O(logn) on a sorted score list, we show how to adapt the FEER algorithm to calculate non-parametric, bootstrapped EER CIs (FEERCI) in O(mlogn) given m resamplings, and we introduce an opinionated open-source package named feerci that provides implementations of the FEER and FEERCI algorithm.We provide speed and accuracy benchmarks for the feerci package, comparing it against the most-used methods of calculating EERs in Python and show how it is able to calculate EERs and CIs on very large score lists faster than contemporary toolkits can calculate a single EER.
- KonferenzbeitragPredicted Templates: Learning-curve Based Template Projection for Keystroke Dynamics(BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group, 2018) Khodabakhsh, Ali; Haasnoot, Erwin; Bours, PatrickKeystroke Dynamics (KD) as a biometric modality can provide authentication tools in many real-life applications, virtually at zero-cost on the client side, due to the reliance of these techniques on existing hardware, and their low computational expense. One promising application is the use of KD as a second factor in password-based authentication. A downside of the existing modeling methods is the assumption of stationary behavior from the clients. However, it is expected that humans show improvements in performing a specific task following practice. In this study, we propose methods for utilization of learning models in predicting the future behavior of the clients, even with little enrollment data, and generate predicted behavioral models that can be used in different classifiers. In our experiments, the predicted templates show a reduction in the average equal-error-rate (EER) consistently across different classifiers a benchmark dataset. A reduction of 20% is achieved on the best classifier. Given fewer enrollment data, the performance gain was shown to reach above 30%. Furthermore, we show that blind detection of attacks is possible, solely relying on the global learning curve, with an EER of 16%.
- KonferenzbeitragShallow CNNs for the Reliable Detection of Facial Marks(BIOSIG 2018 - Proceedings of the 17th International Conference of the Biometrics Special Interest Group, 2018) Zeinstra, Chris; Haasnoot, ErwinFacial marks are local irregularities of skin texture. Their type and/or spatial pattern can be used as a (soft) biometric modality in several applications. A key requirement for a biometric system that utilises facial marks is their reliable detection. Detection methods typically use a blob detector followed by heuristic post processing steps to reduce the number of false positives. In this paper, we consider shallow Convolutional Neural Networks (CNNs) for facial mark detection. The choice of this network type seems natural as it learns multiple (non) blob detectors; shallow refers to the fact that we only consider CNNs up to three layers.We show that (a) these CNNs successfully address the false positive problem, (b) remove the need for post processing steps, and (c) outperform a classic blob detector, approaches taken in previous studies and some other non CNN type classifiers in terms of EER and FMR at TMR=0.95.