Logo des Repositoriums

Auflistung nach Autor:in "Veldhuis, Raymond N. J."

1 - 5 von 5
  • 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
    Fixed FAR vote fusion of regional facial classifiers
    (BIOSIG 2014, 2014) Spreeuwers, Luuk J.; Veldhuis, Raymond N. J.; Sultanali, Siar; Diephuis, Jasper
    Holistic face recognition methods like PCA and LDA have the disadvantage that they are very sensitive to expression, hair and illumination variations. This is one of the main reasons they are no longer competitive in the major benchmarks like FRGC and FRVT. In this paper we present an LDA based approach that combines many overlapping regional classifiers (experts) using what we call a Fixed FAR Voting Fusion (FFVF) strategy. The combination by voting of regional classifiers means that if there are sufficient regional classifiers unaffected by the expression, illumination or hair variations, the fused classifier will still correctly recognise the face. The FFVF approach has two interesting properties: it allows robust fusion of dependent classifiers and it only requires a single parameter to be tuned to obtain weights for fusion of different classifiers. We show the potential of the FFVF of regional classifiers using the standard benchmarks experiments 1 and 4 on FRGCv2 data. The multi-region FFVF classifier has a FRR of 4\% at FAR=0.1\% for controlled and 38\% for uncontrolled data compared to 7\% and 56\% for the best single region classifier.
  • Konferenzbeitrag
    Generating and analyzing synthetic finger vein images
    (BIOSIG 2014, 2014) Hillerström, Fieke; Kumar, Ajay; Veldhuis, Raymond N. J.
    The finger-vein biometric offers a higher degree of security, personal privacy and strong anti-spoofing capabilities than most other biometric modalities employed today. Emerging privacy concerns with the database acquisition and lack of availability of large scale finger-vein databases have posed challenges in exploring this technology for large scale applications. This paper details the first attempt to synthesize finger-vein images and presents analysis of synthesized images for the biometrics authentication. We generate a database of 50,000 fingervein images, corresponding to 5000 different subjects, with 10 different synthesized finger-vein images from each of the subject. We use tractable probability models to compare synthesized finger-vein images with the real fingervein images for their image variability. This paper also presents matching accuracy using the synthesized finger-vein database from 5000 different subjects, using 225,000 genuine and 1249,750,000 impostor matching scores, which suggests significant promises from finger-vein biometric modality for the large scale biometrics applications.
  • Konferenzbeitrag
    Identification performance of evidential value estimation for fingermarks
    (BIOSIG 2015, 2015) Kotzerke, Johannes; Davis, Stephen A.; Hayes, Robert; Spreeuwers, Luuk J.; Veldhuis, Raymond N. J.; Horadam, Kathy J.
    Law enforcement agencies around the world use biometrics and fingerprints to solve and fight crime. Forensic experts are needed to record fingermarks at crime scenes and to ensure those captured are of evidential value. This process needs to be automated and streamlined as much as possible to improve efficiency and reduce workload. It has previously been demonstrated that is possible to estimate a fingermark's evidential value automatically for image captures taken with a mobile phone or other devices, such as a scanner or a high-quality camera. Here we study the relationship between a fingermark being of evidential value and its correct and certain identification and if it is possible to achieve identification despite the mark not having sufficient evidential value. Subsequently, we also investigate the influence the capture device used makes and if a mobile phone is an option worth considering. Our results show that automatic identification is possible for 126 of the 1 428 fin- , germarks captured by a mobile phone, of which 116 were marked as having evidential value by experts and 123 by an automated algorithm.
  • Konferenzbeitrag
    Multi-sample fusion with template protection
    (BIOSIG 2009: biometrics and electronic signatures, 2009) Kelkboom, Emile J. C.; Breebaart, Jeroen; Veldhuis, Raymond N. J.; Zhou, Xuebing; Busch, Christoph
    The widespread use of biometrics and its increased popularity introduces privacy risks. In order to mitigate these risks, solutions such as the helper-data system, fuzzy vault, fuzzy extractors, and cancelable biometrics were introduced, also known as the field of template protection. Besides these developments, fusion of multiple sources of biometric information have shown to improve the verification performance of the biometric system. Our work consists of analyzing feature-level fusion in the context of the template protection framework using the helper-data system. We verify the results using the FRGC v2 database and two feature extraction algorithms.