Skip to main content
SpringerLink
Log in

Andrey Makrushin, Jana Dittmann

Synthetische Daten in der Biometrie

Sind echte biometrische Datensätze ersetzbar durch synthetische?

  • Schwerpunkt
  • Published:
Datenschutz und Datensicherheit - DuD Aims and scope Submit manuscript

Zusammenfassung

Die Generierung synthetischer biometrische Datensätze erfolgt vor dem ultimativen Ziel die möglichen Konflikte mit diversen Datenschutzverordnungen zu adressieren und Verzerrungseffekte (Biases) in biometrischen Datenbanken auszugleichen. Der aktuelle Durchbruch in der Entwicklung von neuronalen generativen Modellen hat der Fokus von mathematischer Modellierung zur Synthese von biometrischen Bildern zu datengetriebener Bildgeneration verschoben. Dieser Paradigmenwechsel hat einerseits den massiven positiven Einfluss auf realistisches Aussehen von synthetischen biometrischen Bildern und ermöglicht somit neue Nutzungsfälle, anderseits bringt er neue Herausforderungen und Anforderungen hervor. Obwohl synthetische Bilder realistisch aussehen, müssen diese auf ihre Tauglichkeit für die Aufgaben, für welche sie prädestiniert sind, geprüft werden. Das erfordert neue Qualitätsmetriken. Dieser Beitrag nennt die Vorteile der Nutzung von synthetischen Datensätzen und verschafft den Überblick über die Nutzungsfälle sowie zeigt den aktuellen Fortschritt und die Richtungen der zukünftigen Forschung auf. Es werden exemplarisch Bilddaten diskutiert.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Literatur

  1. N. Orlans, D. Buettner, and J. Marques. A survey of synthetic biometrics: Capabilities and benefits. In Proc. Int. Conf. on Artificial Intelligence (IC-AI’04), vol. 1, pp. 499–505, 2004.

  2. S. Yanushkevich. Synthetic biometrics: A survey. In Proc. IEEE Int. Joint Conference on Neural Networks (IJCNN’06), pp. 676–683, 2006.

  3. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Proc. 27th Int. Conf. on Neural Information Processing Systems – Vol. 2 (NIPS’14), pp. 2672–2680, 2014.

  4. Regulation (EU) 2016/679 of the European Parliament and of the Council of 27 April 2016 (General Data Protection Regulation).

  5. D. S. Quintana. A synthetic dataset primer for the biobehavioural sciences to promote reproducibility and hypothesis generation. eLife, 9:e53275, March 2020.

  6. Y. Ma, M. Schuckers, and B. Cukic. Guidelines for appropriate use of simulated data for bio-authentication research. In 4th IEEE Workshop on Automatic Identification Advanced Technologies (AutoID’05), pp. 251–256, 2005.

  7. D. J. Buettner. Biometric sample synthesis. In S. Z. Li and A. K. Jain, editors, Encyclopedia of Biometrics, Second Edition, pp. 211–217, Springer US, 2015.

  8. M. Gomez-Barrero and J. Galbally. Reversing the irreversible: A survey on inverse biometrics. Computer Security, 90(C), March 2020.

  9. P. Grother and E. Tabassi. Face image data interchange formats, standardization. In S. Z. Li and A. Jain, editors, Encyclopedia of Biometrics, pp. 314–321. Springer US, Boston, MA, 2009.

  10. J. Daugman. Information theory and the IrisCode. IEEE Trans. on Information Forensics and Security, 11(2):400–409, 2016.

  11. J. Galbally, M. Savvides, S. Venugopalan, and A. A. Ross. Iris image reconstruction from binary templates. In K. W. Bowyer and M. J. Burge, editors, Handbook of Iris Recognition, pp. 469–496. Springer London, 2016

  12. ISO/IEC. 19794-2:2011 Information technology — Biometric data interchange formats — Part 2: Finger minutiae data.

  13. K. P. Wijewardena, S. A. Grosz, K. Cao, and A. K. Jain. Fingerprint template invertibility: Minutiae vs. deep templates. CoRR, abs/2205.03809, 2022.

  14. A. Makrushin, C. Kauba, S. Kirchgasser, S. Seidlitz, C. Kraetzer, A. Uhl, and J. Dittmann. General requirements on synthetic fingerprint images for biometric authentication and forensic investigations. In Proc. ACM Workshop on Information Hiding and Multimedia Security, pp. 93–104, 2021.

  15. S. Kirchgasser, C. Kauba, and A. Uhl. Assessment of synthetically generated mated samples from single fingerprint samples instances. In Proc. IEEE Workshop on Information Forensics and Security (WIFS’21), pp. 1–6, 2021.

  16. C. Kang, Is Synthetic Dataset Reliable for Benchmarking Generalizable Person Re-Identification? In Proc. IEEE Int. Joint Conference on Biometrics (IJCB’22), 2022.

  17. R. Cappelli. SFinGe. In S. Z. Li and A. Jain, editors, Encyclopedia of Biometrics, pp. 1169–1176. Springer US, Boston, MA, 2009.

  18. M. Mirza and S. Osindero. Conditional generative adversarial nets. CoRR, abs/1411.1784, 2014.

  19. T. Karras, S. Laine and T. Aila. A Style-Based Generator Architecture for Generative Adversarial Networks. IEEE Trans. on Pattern Analysis and Machine Intelligence, 43(12):4217-4228, 2021.

  20. J. Mathai, I. Masi, and W. Abd-Almageed. Does Generative Face Completion Help Face Recognition? In Proc. IAPR Int. Conference on Biometrics (ICB’19), 2019.

  21. A. S. Joshi, A. Dabouei, J. Dawson, and N. M. Nasrabadi. FDeblur-GAN: Fingerprint deblurring using generative adversarial network. In Proc. IEEE Int. Joint Conference on Biometrics (IJCB’21), pp. 1–8, 2021.

  22. R. Durall, J. Jam, D. Strassel, M. H. Yap, and J. Keuper. FacialGAN: FacialGAN: Style Transfer and Attribute Manipulation on Synthetic Faces. In Proc. 32nd British Machine Vision Conference (BMVC’21), pp. 1–14, 2021.

  23. B. Gecer, S. Ploumpis, I. Kotsia, and S. Zafeiriou. Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction. IEEE Trans. on Pattern Analysis and Machine Intelligence, 44(9):4879–4893, 2022.

Download references

Author information

Authors and Affiliations

  1. Otto-von-Guericke-Universität Magdeburg, Magdeburg, Deutschland

    Andrey Makrushin &  Jana Dittmann

Authors
  1. Andrey Makrushin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jana Dittmann
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrey Makrushin.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Makrushin, A., Dittmann, J. Synthetische Daten in der Biometrie. Datenschutz Datensich 47, 22–26 (2023). https://doi.org/10.1007/s11623-022-1710-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11623-022-1710-8

Search

Navigation