Achieving Facial De-Identification by Taking Advantage of the Latent Space of Generative Adversarial Networks
| dc.contributor.author | Frick, Raphael Antonius | |
| dc.contributor.author | Steinebach, Martin | |
| dc.contributor.editor | Gesellschaft fĂŒr Informatik e.V. (GI) | |
| dc.date.accessioned | 2021-12-14T10:57:41Z | |
| dc.date.available | 2021-12-14T10:57:41Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | The General Data Protection Regulation (EU)2016/679 passed by the European Union prohibits any data collection and processing that was conducted without the consent of the individuals involved. Especially images showing faces are often subject to these regulations and therefore, either need to be removed or anonymized. Early approaches however were often troubled by strong visual artifacts. In this work, we propose a novel anonymization pipeline that generates a proxy face for a group of individuals by taking advantage of the semantics of the latent space of generative adversarial networks. Experiments have shown that by following a đ-same approach and utilizing different clustering techniques, privacy for the individuals involved can be greatly enhanced, while preserving important facial characteristics. | en |
| dc.identifier.doi | 10.18420/informatik2021-068 | |
| dc.identifier.isbn | 978-3-88579-708-1 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/37735 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft fĂŒr Informatik, Bonn | |
| dc.relation.ispartof | INFORMATIK 2021 | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-314 | |
| dc.subject | Facial De-Identification | |
| dc.subject | k-Anonymity | |
| dc.subject | Privacy | |
| dc.subject | Generative Adversarial Networks | |
| dc.subject | Facial Image Data | |
| dc.title | Achieving Facial De-Identification by Taking Advantage of the Latent Space of Generative Adversarial Networks | en |
| gi.citation.endPage | 806 | |
| gi.citation.startPage | 795 | |
| gi.conference.date | 27. September - 1. Oktober 2021 | |
| gi.conference.location | Berlin | |
| gi.conference.sessiontitle | Workshop: Security, Datenschutz und Anonymisierung |
Dateien
OriginalbĂŒndel
1 - 1 von 1
Vorschaubild nicht verfĂŒgbar
- Name:
- H1-5.pdf
- GröĂe:
- 15.56 MB
- Format:
- Adobe Portable Document Format