|
|
| Tools for the Generation of Synthetic Biometric Sample Data (GENSYNTH) |
|
Project Description:
Tools for the Generation of Synthetic Biometric Sample Data (FWF project I4272) is a joint DFG/FWF bilateral project together with
Jana Dittmanns group at the University of Magdeburg
which researches methods allowing for the generation of large-scale sets of plausible and realistic synthetic biometric data to enable reproducible, flexible and timely biometric and forensic experimental assessments, not only compliant with the hunger for data we see with modern day techniques, but also with EU data protection legislation.
To achieve our goals, the work in this project follows two distinct solution approaches: The first (data adaptation) takes existing biometric / forensic samples, adapts them to reflect certain acquisition conditions (sensorial, physiological as well as environmental variability), and (if required by the application context) conducts context sensitive control of privacy attributes. The second approach (synthesizing) creates completely artificial samples from scratch according to specified sensorial, physiological as well as environmental variability.
The practical work in the project is focused on digitized forensic (latent) fingerprints as well as on the two biometric modalities fingerprint (FP) and vascular data of hand and fingers (i.e. hand- and finger-vein images) (HFV). The theoretical and methodological concepts and empirical findings will be generalized, to discuss the potential benefits of the research performed also for other modalities (esp. in face recognition).
|
|
|
Members:
|
|
|
Timeframe:
|
|
|
Publications:
- [Langer24a ] Difficulties in Using Synthetic Data for Presentation Attack Detection in Finger Vein Recognition: The Role of Model Fingerprints Moritz Langer, Michael Hafner, Stefan Findenig, Alexandar Radovic, Andreas Vorderleitner, Andreas Uhl In 2024 IEEE/IAPR International Joint Conference on Biometrics (IJCB), pp. 1-10, 2024
- [Kauba24a ] Extension and further Evaluation of the PLUS Multi-Sensor and Longitudinal Fingerprint Dataset Christof Kauba, Simon Kirchgasser, Andreas Uhl In Proceedings of the 12th International Workshop on Biometrics and Forensics (IWBF'24), pp. 1-6, Enschede, Netherlands, April 11 - April 12, 2024
- [Vorderleitner23a ] Hand Vein Spoof GANs: Pitfalls in the Assessment of Synthetic Presentation Attack Artefacts Andreas Vorderleitner, Jutta Hämmerle-Uhl, Andreas Uhl In Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security, pp. 133–138, New York, NY, USA, IH&MMSec '23, Association for Computing Machinery, 2023
- [Vorderleitner23b ] Finger Vein Spoof GANs: Can we Supersede the Production of Presentation Attack Artefacts? Andreas Vorderleitner, Jutta Hämmerle-Uhl, Andreas Uhl In 22th International Workshop on Digital Forensics and Watermarking (IWDW'23), pp. 109-124, Jinan, China, Springer LNCS, 14511, November 25 - November 26, 2023
- [Lamminger23a ] First Learning Steps to Recognize Faces in the Noise Lukas Lamminger, Heinz Hofbauer, Andreas Uhl In Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security, pp. 139–144, New York, NY, USA, IH&MMSec '23, Association for Computing Machinery, 2023
- [Mitterreiter23a ] Morphing-Attacks against Binary Fingervein Templates Tobias Mitterreiter, Jutta Hämmerle-Uhl, Andreas Uhl In Image Analysis and Processing. ICIAP 2023 Workshops (Recent Advances in Digital Security: Biometrics and Forensics (BioFor'23)), pp. 305-317, Cham, Lecture Notes in Computer Science, 14365, Springer International Publishing, September 11 - September 15, 2023
- [Soellinger23a ] Protocol Based Similarity Evaluation of Publicly Available Synthetic and Real Fingerprint Datasets Dominik Söllinger, Simon Kirchgasser, Andrey Makrushin, Jana Dittmann, Andreas Uhl In 2023 IEEE International Joint Conference on Biometrics (IJCB'23), pp. 1-8, Ljubljana (Slovenia), September 25 - September 28, 2023
- [Makrushin23a ] A Survey On Synthetic Biometrics: Fingerprint, Face, Iris and Vascular Patterns Andrey Makrushin, Andreas Uhl, Jana Dittmann IEEE ACCESS 11, pp. 33887-33899, 2023
- [Kirchgasser21a ] The PLUS Multi-Sensor and Longitudinal Fingerprint Dataset: An Initial Quality and Performance Evaluation Simon Kirchgasser, Christof Kauba, Andreas Uhl IEEE Transactions on Biometrics, Behavior, and Identity Science 4:1, pp. 43-56, 2022
- [Paulitsch21a ] Temporal Image Forensics: Using CNNs for a Chronological Ordering of Line-Scan Data Matthias Paulitsch, Andreas Vorderleitner, Andreas Uhl In Computational Science and Its Applications -- ICCSA 2021, pp. 147-162, Cham, LNCS, 12950, Springer International Publishing, 2021
- [Kauba21c ] Assessment of Sensor Ageing-Impact in Air Travelled Fingerprint Capturing Devices Christof Kauba, Simon Kirchgasser, Robert Jöchl, Andreas Uhl In Proceedings of the IEEE 20th International Conference of the Biometrics Special Interest Group (BIOSIG 2021), pp. 1-8, Darmstadt, Germany, September 15 - September 17, 2021
- [Kirchgasser21b ] Assessment of Synthetically Generated Mated Samples from Single Fingerprint Samples Instances Simon Kirchgasser, Christof Kauba, Andreas Uhl In Proceedings of the IEEE Workshop on Information Forensics and Security (WIFS2021), pp. 1-6, Montpellier, France, December 7 - December 10, 2021
- [Makrushin21a ] General requirements on synthetic fingerprint images for biometric authentication and forensic investigations Andrey Makrushin, Christof Kauba, Simon Kirchgasser, Stefan Seidlitz, Christian Kraetzer, Andreas Uhl, Jana Dittmann In Proceedings of the 9th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec'21), pp. 1-11, Brussels, Belgium (held Online due to Covid), June 22 - June 25, 2021
- [Iakovidis21a ] Roadmap on signal processing for next generation measurement systems (Section 4.6. Signal and image processing methods for biometrics: the impact of DL) Dimitris Iakovidis, ...., Andreas Uhl, .... Measurement Science and Technology 33:1, pp. 012002, 2021
- [Drozdowski20a ] Demographic Bias: A Challenge for Fingervein Recognition Systems? Pawel Drozdowski, Bernhard Prommegger, Georg Wimmer, Rudolf Schraml, Christian Rathgeb, Andreas Uhl, Christoph Busch In 2020 28th European Signal Processing Conference (EUSIPCO), pp. 825-829, Amsterdam, The Nederlands, 2021
- [Debiasi20a ] Presentation Attacks and Detection in Finger- and Hand-Vein Recognition Luca Debiasi, Christof Kauba, Heinz Hofbauer, Bernhard Prommegger, Andreas Uhl In Proceedings of the Joint Austrian Computer Vision and Robotics Workshop (ACVRW'20), pp. 65-70, Graz, Austria, September 17 - September 18, 2020
|
|