Logo des Repositoriums

P212 - BIOSIG 2013 - Proceedings of the 12th International Conference of the Biometrics Special Interest Group

https://dl.gi.de/handle/20.500.12116/20079
Auflistung nach:

Auflistung P212 - BIOSIG 2013 - Proceedings of the 12th International Conference of the Biometrics Special Interest Group nach Titel

1 - 10 von 36
  • Konferenzbeitrag
    Absolute fingerprint pre-alignment in minutiae-based cryptosystems
    (BIOSIG 2013, 2013) Tams, Benjamin
    Most biometric cryptosystems that have been proposed to protect fingerprint minutiae make use of public alignment helper data. This, however, has the inadvertent effect of information leakage about the protected templates. A countermeasure to avoid auxiliary alignment data is to protect absolutely pre-aligned fingerprints. As a proof of concept, we run performance evaluations of a minutiae fuzzy vault with an automatic method for absolute pre-alignment. Therefore, we propose a new method for estimating a fingerprint's directed reference point by modeling the local orientation around the core as a tented arch.1
  • Konferenzbeitrag
    Assignment of the evidential value of a fingermark general pattern using a Bayesian network
    (BIOSIG 2013, 2013) Haraksim, Rudolf; Meuwly, Didier; Doekhie, Gina; Vergeer, Peter; Sjerps, Marjan
    When visible on a fingermark, the general pattern maintains its importance in the fingerprint examination procedure, since the difference between the general pattern of a fingermark and a fingerprint is sufficient for exclusion. In the current work, the importance of the general pattern is extended by evaluating the strength of evidence of a match given corresponding general pattern. In current practice (due to the lack of statistical support for the general pattern evidence) the fingerprint examiners assign personal probabilities to the general pattern evidence based on their knowledge and experience, while in this work the probabilities are calculated using a Bayesian Network which is fed by empirical data.
  • Konferenzbeitrag
    Automatic landmark detection and face recognition for side-view face images
    (BIOSIG 2013, 2013) Santemiz, Pinar; Spreeuwers, Luuk J.; Veldhuis, Raymond N. J.
    In real-life scenarios where pose variation is up to side-view positions, face recognition becomes a challenging task. In this paper we propose an automatic sideview face recognition system designed for home-safety applications. Our goal is to recognize people as they pass through doors in order to determine their location in the house. Here, we introduce a recognition method, where we detect facial landmarks automatically for registration and identify faces. We test our system on side-view face images from CMU-Multi PIE database. We achieve 95 95% accuracy on detecting . landmarks, and 89 04% accuracy on identification. .
  • Konferenzbeitrag
    Behavioral biometrics for DARPA's active authentication program
    (BIOSIG 2013, 2013) Deutschmann, Ingo; Lindholm, Johan
    The aim of the US Defense Advance Research Project Agency`s (DARPA) Active Authentication program is the continuous authentication of users by using behavioral biometrics authentication systems, which does not depend on specific hardware or sensors. This paper presents how such a continuous authentication system would perform in an office like environment. The analysis is performed on a data set captured from 99 users over a 10 week period. Our continuous authentication system builds a behavior biometric profile of the user by observing mouse movement, keystrokes and application usage. The user is then actively matched against his profile. The goal was, as DARPA is mentioning in their Active Authentication program, ”This means the system would, potentially have to falsely reject the user more than five times in a row during continuous usage over a 40 hour period to fail to meet this target. The technologies developed under this solicitation should be able to work invisibly to the user unless five false positives are reached”. The results of our study indicate that the correct user can work through a regular workday without being falsely rejected, while the incorrect user would be detected within 18 seconds using keyboard or 2.4 minutes using mouse. Application process usage results show that the incorrect user would be detected in just over 1.5 minutes.
  • Konferenzbeitrag
    BioHashing with fingerprint spectral minutiae
    (BIOSIG 2013, 2013) Topcu, Berkay; Erdogan, Hakan; Karabat, Cagatay; Yanikoglu, Berrin
    In recent years, the interest in human authentication has been increasing. Biometrics are one of the easy authentication schemes, however, security and privacy problems limit their widespread usage. Following the interest in privacy protecting biometric authentication, template protection schemes for biometric modalities has increased significantly in order to cope with security and privacy issues. BioHashing, which is based on transforming the biometric template using pseudo-random projections that are generated using a user-specified key or token, has received much attention as it improves verification accuracies over using only the biometric data, allows template revocation and preserves privacy. In our work, we develop a new BioHashing scheme for fingerprints. A fixed-length feature vector is required in order to design a BioHashing scheme. In the literature, most of the studies on fingerprint BioHashing uses features extracted from fingerprint texture. On the other hand, our new BioHashing scheme is based on minutia based feature vectors. We use the spectral minutiae representation for obtaining a fixed-length feature vector for a fingerprint sample. Then, we use a random projection matrix, which is generated from user's key/token, in order to generate a BioHash vector. We propose to randomly project each column of the spectral minutiae feature matrix via a single matrix which allows fast bit string extraction and adaptive quantization. Experiments on FVC2002 databases show the promise of the proposed system for fast and secure verification.
  • Editiertes Buch
    BIOSIG 2013
    (2013)
  • Konferenzbeitrag
    Combination of facial landmarks for robust eye localization using the discriminative generalized Hough transform
    (BIOSIG 2013, 2013) Hahmann, Ferdinand; Böer, Gordon; Schramm, Hauke
    The Discriminative Generalized Hough Transform (DGHT) is a general and robust automated object localization method, which has been shown to achieve state-of-the-art success rates in different application areas like medical image analysis and person localization. In this contribution the framework is enhanced by a novel facial landmark combination technique which is theoretically introduced and evaluated for an eye localization task on a public database. The technique applies individually trained DGHT models for the localization of different facial landmarks, combines the obtained Hough spaces into a 3D feature matrix and applies a specifically trained higher-level DGHT model for the final localization based on the given features. In addition to that, the framework is further improved by a task-specific multi-level approach which adjusts the zooming-in strategy with respect to relevant structures and confusable objects. With the new system it was possible to increase the iris localization rate from 96.6% to 97.9% on 3830 evaluation images. This result is promising, since the variation of the head pose in the database is quite large and the applied error measure considers the worst of a left and right eye localization attempt.
  • Konferenzbeitrag
    Continuous authentication using mouse dynamics
    (BIOSIG 2013, 2013) Mondal, Soumik; Bours, Patrick
    In this paper, we demonstrate a new way to perform continuous authentication using Mouse Dynamics as the behavioural biometric modality. In the proposed scheme, the user will be authenticated per mouse event performed on his/her system. We have used a publicly available mouse dynamics dataset and extracted per event features suitable for the proposed scheme. In this research, we have used the mouse dynamics data of 49 users and evaluated the system performance with 6 machine learning algorithms. In this approach, the genuine user has never been classified as an impostor throughout a full session whereas the average number of mouse actions an impostor could perform before detection is 94 from the best classification algorithm with a person based threshold.
  • Konferenzbeitrag
    EEG based user recognition using BUMP modelling
    (BIOSIG 2013, 2013) Rocca, Daria La; Campisi, Patrizio; Solé-Casals, Jordi
    In this paper the use of electroencephalogram (EEG) as biometric identifier is investigated. The use of EEG within the biometric framework has already been introduced in the recent past although it has not been extensively analyzed. In this contribution we apply the “bump” modelling analysis for the feature extraction stage within an identification framework, in order to reduce the huge amount of data recorded through EEG. For the purpose of this study we rely on the “resting state with eyes closed” protocol. The employed database is composed of 36 healthy subjects whose EEG signals have been acquired in an ad hoc laboratory. Different electrodes configurations pertinent with the employed protocol have been considered. A classifier based on Mahalanobis distance have been tested for the enrollment of the subjects and their identification. An information fusion performed at the score level has shown to improve correct classification performance. The obtained results show that an identification accuracy of 99.69% can be achieved. It represents an high degree of accuracy, given the current state of research on EEG biometrics.
  • Konferenzbeitrag
    An efficient 3D facial landmark detection algorithm with Haar-like features and anthropometric constraints
    (BIOSIG 2013, 2013) Böckeler, Martin; Zhou, Xuebing
    In the last few years 3D face recognition has become more and more popular due to reducing cost of scanners and increasing computational power. The crucial and time-consuming step is landmark localization and normalization of facial surface. Due to acquisition, noise and other artifacts like spikes and holes occur. Most systems require computational intensive preprocessing steps to eliminate these artifacts. As a consequence, a trade-off between runtime or detection accuracy must be made. In contrast, we propose a landmark detection algorithm which uses the Viola & Jones classifier on gradient images. The algorithm is able to reliably detect landmarks in raw 3D data without complicated preprocessing. Additionally, selection of sub regions is exploited to limit search regions. It further reduces false detection rate and improves significantly detection accuracy.