Description

Current day biometric recognition and digitized forensics research struggles with a problem severely impeding progress in these security relevant fields: Large scale datasets of biometric data would be required to allow for flexible and timely assessments, but these are missing due to various reasons, amongst them privacy concerns. The latter have increased with the EU GDPR to an extend that even well established standardization bodies like NIST in the USA removed a large part of their publically available datasets before the GDPR became effective in May 2018. To solve this problem and address the attached data quality dimensions (quantitative as well as qualitative concerns), we will research methods allowing for the generation of large-scale sets of plausible and realistic synthetic 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).

The project is organized as an international project conducted by two groups at Magdeburg (Germany) and Salzburg (Austria) Universities, respectively, which are lead by Prof. Jana Dittmann (for the German side) and Prof. Andreas Uhl (for the Austrian side).

Project duration

01.01.2020 - 31.03.2023

Members

• Prof. Dr. Jana Dittmann (Homepage)
• Christian Kraetzer (Homepage)
• Stefan Seidlitz (Homepage)
• Andrey Makrushin (Homepage)

Project Partners

The Multimedia Signal Processing and Security Lab at University of Salzburg (Web site)

Source code

https://gitti.cs.uni-magdeburg.de/Andrey/gensynth

Datasets & generative models

• Datasets owncloud folder, in order get an access please sign the license agreement here
• Generative models owncloud folder, in order get an access please sign the license agreement here

Publications

Andrey Makrushin, Venkata Srinath Mannam, and Jana Dittmann: Privacy-Friendly Datasets of Synthetic Fingerprints for Evaluation of Biometric Algorithms, Applied Sciences, vol. 13, no. 18: 10000, 2023; doi: 10.3390/app131810000; pdf

Andrey Makrushin, Andreas Uhl, and Jana Dittmann: A Survey on Synthetic Biometrics: Fingerprint, Face, Iris and Vascular Patterns, IEEE Access, vol. 11, pp. 33887-33899, 2023; doi: 10.1109/ACCESS.2023.3250852

Andrey Makrushin, Venkata Srinath Mannam, and Jana Dittmann: Data-Driven Fingerprint Reconstruction from Minutiae Based on Real and Synthetic Training Data, Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, pp. 229-237, 2023. doi:10.5220/0011660800003417

Andrey Makrushin, Jana Dittmann: Synthetische Daten in der Biometrie, Datenschutz und Datensicherheit - DuD, Vol. 47, pp. 22–26, 2023; doi.org/10.1007/s11623-022-1710-8

Andrey Makrushin, Venkata Srinath Mannam, Meghana Rao B.N. and Jana Dittmann: Data-driven Reconstruction of Fingerprints from Minutiae Maps, Proceedings of the 24th IEEE International Workshop on Multimedia Signal Processing (MMSP'22), Online, September 26–28, 2022; doi: 10.1109/MMSP55362.2022.9949242

Andrey Makrushin, Mark Trebeljahr, Stefan Seidlitz, and Jana Dittmann: On feasibility of GAN-based fingerprint morphing, Proceedings of the 23th IEEE International Workshop on Multimedia Signal Processing (MMSP'21), Tampere, Finland, October 6–8, 2021; doi:10.1109/MMSP53017.2021.9733526

Andrey Makrushin, Christof Kauba, Simon Kirchgasser, Stefan Seidlitz, Christian Kraetzer, Andreas Uhl, and Jana Dittmann: General Requirements on Synthetic Fingerprint Images for Biometric Authentication and Forensic Investigations, Proceedings of the 9th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec'21), pp. 93–104, 2021; doi:10.1145/3437880.3460410

Stefan Seidlitz, Kris Jürgens, Andrey Makrushin, Christian Kraetzer, and Jana Dittmann: Generation of Privacy-friendly Datasets of Latent Fingerprint Images using Generative Adversarial Networks, Proceedings of the 16th Int. Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP, pp. 345-352, 2021; doi:10.5220/0010251603450352