EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GANonymization: A GAN-Based Face Anonymization Framework for Preserving Emotional Expressions

Fabio Hellmann, Silvan Mertes, Mohamed Benouis, Alexander Hustinx, Tzung-Chien Hsieh, Cristina Conati, Peter Krawitz, Elisabeth André

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.01.2025 · 21 (1) · 1-27

DOI: 10.1145/3641107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 14.12.2024. Verfasst von Fabio Hellmann und 7 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DFG through the Leibniz Award of Elisabeth André.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, the increasing availability of personal data has raised concerns regarding privacy and security. One of the critical processes to address these concerns is data anonymization, which aims to protect individual privacy and prevent the release of sensitive information. This research focuses on the importance of face anonymization. Therefore, we introduce GANonymization, a novel face anonymization framework with facial expression-preserving abilities. Our approach is based on a high-level representation of a face, which is synthesized into an anonymized version based on a generative adversarial network (GAN). The effectiveness of the approach was assessed by evaluating its performance in removing identifiable facial attributes to increase the anonymity of the given individual face. Additionally, the performance of preserving facial expressions was evaluated on several affect recognition datasets and outperformed the state-of-the-art methods in most categories. Finally, our approach was analyzed for its ability to remove various facial traits, such as jewelry, hair color, and multiple others. Here, it demonstrated reliable performance in removing these attributes. Our results suggest that GANonymization is a promising approach for anonymizing faces while preserving facial expressions.

Förderung

  • DFG through the Leibniz Award of Elisabeth André

Zitieren

APA

Hellmann, F., Mertes, S., Benouis, M., Hustinx, A., Hsieh, T., Conati, C., Krawitz, P., & André, E. (2025). GANonymization: A GAN-Based Face Anonymization Framework for Preserving Emotional Expressions. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(1), 1-27. https://doi.org/10.1145/3641107

Vancouver

Hellmann F, Mertes S, Benouis M, Hustinx A, Hsieh T, Conati C, et al. GANonymization: A GAN-Based Face Anonymization Framework for Preserving Emotional Expressions. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(1):1-27. doi:10.1145/3641107

BibTeX
@article{Hellmann2025,
  author = {Hellmann, Fabio and Mertes, Silvan and Benouis, Mohamed and Hustinx, Alexander and Hsieh, Tzung-Chien and Conati, Cristina and Krawitz, Peter and André, Elisabeth},
  title = {GANonymization: A GAN-Based Face Anonymization Framework for Preserving Emotional Expressions},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2025},
  volume = {21},
  number = {1},
  pages = {1--27},
  doi = {10.1145/3641107}
}
Kostenlos starten →