OrthoMAD: Morphing Attack Detection Through Orthogonal Identity Disentanglement
| dc.contributor.author | Pedro C Neto, Tiago Gonçalves | |
| dc.contributor.editor | Brömme, Arslan | |
| dc.contributor.editor | Damer, Naser | |
| dc.contributor.editor | Gomez-Barrero, Marta | |
| dc.contributor.editor | Raja, Kiran | |
| dc.contributor.editor | Rathgeb, Christian | |
| dc.contributor.editor | Sequeira Ana F. | |
| dc.contributor.editor | Todisco, Massimiliano | |
| dc.contributor.editor | Uhl, Andreas | |
| dc.date.accessioned | 2022-10-27T10:19:27Z | |
| dc.date.available | 2022-10-27T10:19:27Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | Morphing attacks are one of the many threats that are constantly affecting deep face recognition systems. It consists of selecting two faces from different individuals and fusing them into a final image that contains the identity information of both. In this work, we propose a novel regularisation term that takes into account the existent identity information in both and promotes the creation of two orthogonal latent vectors.We evaluate our proposed method (OrthoMAD) in five different types of morphing in the FRLL dataset and evaluate the performance of our model when trained on five distinct datasets. With a small ResNet-18 as the backbone, we achieve state-of-the-art results in the majority of the experiments, and competitive results in the others. | en |
| dc.identifier.doi | 10.1109/BIOSIG55365.2022.9897057 | |
| dc.identifier.isbn | 978-3-88579-723-4 | |
| dc.identifier.pissn | 1617-5484 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/39693 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | BIOSIG 2022 | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-329 | |
| dc.subject | Face | |
| dc.subject | Presentation Attack Detection | |
| dc.subject | Morphing | |
| dc.subject | Identity Disentanglement | |
| dc.subject | ResNet-18 | |
| dc.title | OrthoMAD: Morphing Attack Detection Through Orthogonal Identity Disentanglement | en |
| dc.type | Text/Conference Paper | |
| gi.citation.endPage | 181 | |
| gi.citation.publisherPlace | Bonn | |
| gi.citation.startPage | 173 | |
| gi.conference.date | 14.-16. September 2022 | |
| gi.conference.location | Darmstadt | |
| gi.conference.sessiontitle | Regular Research Papers |
Dateien
Originalbündel
1 - 1 von 1
Lade...
- Name:
- 17-BIOSIG_2022_paper_62-2.pdf
- Größe:
- 167.51 KB
- Format:
- Adobe Portable Document Format