P270 - BIOSIG 2017 - Proceedings of the 16th International Conference of the Biometrics Special Interest Group
Auflistung P270 - BIOSIG 2017 - Proceedings of the 16th International Conference of the Biometrics Special Interest Group nach Erscheinungsdatum
1 - 10 von 29
Treffer pro Seite
Sortieroptionen
- TextdokumentOn the Generalization of Fused Systems in Voice Presentation Attack Detection(BIOSIG 2017, 2017) Gonçalves,André R.; Korshunov,Pavel; Violato,Ricardo P.V.; Simões,Flávio O.; Marcel,SébastienThis paper describes presentation attack detection systems developed for the Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2017). The submitted systems, using calibration and score fusion techniques, combine different sub-systems (up to 18), which are based on eight state of the art features and rely on Gaussian mixture models and feedforward neural network classifiers. The systems achieved the top five performances in the competition. We present the proposed systems and analyze the calibration and fusion strategies employed. To assess the systems’ generalization capacity, we evaluated it on an unrelated larger database recorded in Portuguese language, which is different from the English language used in the competition. These extended evaluation results show that the fusion-based system, although successful in the scope of the evaluation, lacks the ability to accurately discriminate genuine data from attacks in unknown conditions, which raises the question on how to assess the generalization ability of attack detection systems in practical application scenarios.
- TextdokumentDe-duplication using automated face recognition: a mathematical model and all babies are equally cute(BIOSIG 2017, 2017) Spreeuwers,LuukDe-duplication is defined as the technique to eliminate or link duplicate copies of repeating data. We consider a specific de-duplication application where a subject applies for a new passport and we want to check if he possesses a passport already under another name. To determine this, a facial photograph of the subject is compared to all photographs of the national database of passports.We investigate if state of the art facial recognition is up to this task and find that for a large database about 2 out of 3 duplicates can be found while few or no false duplicates are reported. This means that de-duplication using automated face recognition is feasible in practice.We also present a mathematical model to predict the performance of de-duplication and find that the probability that k false duplicates are returned can be described well by a Poisson distribution using a varying, subject specific false match rate. We present experimental results using a large database of actual passport photographs consisting of 224 000 images of about 100 000 subjects and find that the results are predicted well by our model.
- TextdokumentExploring Texture Transfer Learning via Convolutional Neural Networks for Iris Super Resolution(BIOSIG 2017, 2017) Ribeiro,Eduardo; Uhl,AndreasIncreasingly, iris recognition towards more relaxed conditions has issued a new superresolution field direction. In this work we evaluate the use of deep learning and transfer learning for single image super resolution applied to iris recognition. For this purpose, we explore if the nature of the images as well as if the pattern from the iris can influence the CNN transfer learning and, consequently, the results in the recognition process. The good results obtained by the texture transfer learning using a deep architecture suggest that features learned by Convolutional Neural Networks used for image super-resolution can be highly relevant to increase iris recognition rate.
- TextdokumentBenchmarking Fingerprint Minutiae Extractors(BIOSIG 2017, 2017) Chugh,Tarang; Arora,Sunpreet S.; Jain, Anil K.; Paulter Jr.,Nicholas G.The performance of a fingerprint recognition system hinges on the errors introduced in each of its modules: image acquisition, preprocessing, feature extraction, and matching. One of the most critical and fundamental steps in fingerprint recognition is robust and accurate minutiae extraction. Hence we conduct a repeatable and controlled evaluation of one open-source and three commercial-off-the-shelf (COTS) minutiae extractors in terms of their performance in minutiae detection and localization. We also evaluate their robustness against controlled levels of image degradations introduced in the fingerprint images. Experiments were conducted on (i) a total of 3;458 fingerprint images from five public-domain databases, and (ii) 40;000 synthetically generated fingerprint images. The contributions of this study include: (i) a benchmark for minutiae extractors and minutiae interoperability, and (ii) robustness of minutiae extractors against image degradations.
- TextdokumentxTARP: Improving the Tented Arch Reference Point Detection Algorithm(BIOSIG 2017, 2017) Merkle,Johannes; Tams,Benjamin; Dieckmann,Benjamin; Korte,UlrikeIn 2013, Tams et al. proposed a method to determine directed reference points in fingerprints based on a mathematical model of typical orientation fields of tented arch type fingerprints. Although this Tented Arch Reference Point (TARP) method has been used successfully for prealignment in biometric cryptosystems, its accuracy does not yet ensure satisfactory error rates for single finger systems. In this paper, we improve the TARP algorithm by deploying an improved orientation field computation and by integrating an additional mathematical model for arch type fingerprints. The resulting Extended Tented Arch Reference Point (xTARP) method combines the arch model with the tented arch model and achieves a significantly better accuracy than the original TARP algorithm. When deploying the xTARP method in the Fuzzy Vault construction of Butt et al., the false non-match rate (FNMR) at a security level of 20 bits is reduced from 7:4% to 1:7%.
- TextdokumentFingerprint Damage Localizer and Detector of Skin Diseases from Fingerprint Images(BIOSIG 2017, 2017) Barotova,Stepanka; Drahansky,MartinThis article describes a novel approach for detection and classification of skin diseases in fingerprints using three methods - Block Orientation Field, Histogram Analysis and Flood Fill. The combination of these methods brings a surprising results and using a rule descriptor for selected skin diseases, we are able to classify the disease into a group or concrete name.
- TextdokumentSteady-State Visual Evoked Potentials for EEG-Based Biometric Identification(BIOSIG 2017, 2017) Piciucco,Emanuela; Maiorana,Emanuele; Falzon,Owen; Camilleri,Kenneth P.; Campisi,PatrizioIn this paper we propose a biometric recognition system based on steady-state visual evoked potentials (SSVEPs), exploiting brain signals elicited by repetitive stimuli having a constant frequency as identifiers. EEG responses to SSVEP stimuli flickering at different frequencies are recorded, and both mel-frequency cepstral coefficients (MFCCs) and autoregressive (AR) reflection coefficients are used as discriminative features of the enrolled users. An analysis of the permanence across time of the brain response to SSVEP stimuli is also performed, by exploiting EEG data acquired in sessions disjoint in time. The employed database is composed by EEG recordings taken from 25 healthy subjects during two different sessions with 15 day average distance between them. The results show that good recognition performance and a high level of permanence can be reached exploiting the proposed method.
- TextdokumentPool Adjacent Violators Based Biometric Rank Level Fusion(BIOSIG 2017, 2017) Susyanto,NanangWe propose a new method in rank level fusion for biometric identification. Our method is based on the pool adjacent violators (PAV) algorithm after the ranks have been transformed to the approximated scores.We then show that our method outperforms various approaches that commonly used in biometric rank level fusion on NIST BSSR1 multimodal database.
- TextdokumentIntrinsic Limitations of Fingerprint Orientation Estimation(BIOSIG 2017, 2017) Schuch,Patrick; Schulz,Simon-Daniel; Busch,ChristophEstimation of orientation field is a crucial issue when processing fingerprint samples. Many subsequent fingerprint processing steps depend on reliable and accurate estimations. Algorithms for such estimations are usually evaluated against ground truth data. As true ground truth is usually not available, human experts need to mark-up ground truth manually. However, the accuracy and the reliability of such mark-ups for orientation fields have not been investigated yet. Mark-ups produced by six humans allowed insights into both aspects. A Root Mean Squared Error of about 7 against true ground truth can be achieved. Reproducibility between two mark-ups of a single dactyloscopic expert is at the same precision. We concluded that the accuracy of human experts is competitive to the best algorithms evaluated at FVC-ongoing.
- TextdokumentResting-state EEG: A Study on its non-Stationarity for Biometric Applicaions(BIOSIG 2017, 2017) Hine, Gabriel Emile; Maiorana, Emanuele; Campisi,PatrizioIn the last years, several papers on EEG-based biometric recognition systems have been published. Specifically, most of the proposed contributions focus on brain signals recorded in resting state conditions, with either closed or open eyes. A common assumption is that the acquired signals are quasi-stationarity. In this paper, we investigate such property in terms of discriminative capability, and we analyze whether or not it holds throughout the entire duration of data collected over long periods. An extensive set of experimental tests, conducted over a database comprising signals collected from 50 subjects in three distinct acquisition sessions, shows that the most distinctive information of the brain signals is temporally located at the beginning of each recording.
- «
- 1 (current)
- 2
- 3
- »