Logo des Repositoriums
 

Robust Sclera Segmentation for Skin-tone Agnostic Face Image Quality Assessment

Kurzanzeige
dc.contributor.authorWassim Kabbani, Christoph Busch
dc.contributor.editorDamer, Naser
dc.contributor.editorGomez-Barrero, Marta
dc.contributor.editorRaja, Kiran
dc.contributor.editorRathgeb, Christian
dc.contributor.editorSequeira, Ana F.
dc.contributor.editorTodisco, Massimiliano
dc.contributor.editorUhl, Andreas
dc.date.accessioned2023-12-12T10:46:46Z
dc.date.available2023-12-12T10:46:46Z
dc.date.issued2023
dc.description.abstractFace image quality assessment (FIQA) is crucial for obtaining good face recognition performance. FIQA algorithms should be robust and insensitive to demographic factors. The eye sclera has a consistent whitish color in all humans regardless of their age, ethnicity and skin-tone. This work proposes a robust sclera segmentation method that is suitable for face images in the enrolment and the border control face recognition scenarios. It shows how the statistical analysis of the sclera pixels produces features that are invariant to skin-tone, age and ethnicity and thus can be incorporated into FIQA algorithms to make them agnostic to demographic factors.en
dc.identifier.isbn978-3-88579-733-3
dc.identifier.issn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/43260
dc.language.isoen
dc.pubPlaceBonn
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofBIOSIG 2023
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-339
dc.subjectFace and gesture recognition
dc.subjectBiometric sample quality; Ethical
dc.subjectlegal and socio-technological aspects; Soft biometric privacy
dc.subjectDemographic bias
dc.subjectFairness
dc.titleRobust Sclera Segmentation for Skin-tone Agnostic Face Image Quality Assessmenten
dc.typeText/Conference Paper
mci.conference.date20.-22. September 2023
mci.conference.locationDarmstadt
mci.conference.sessiontitleRegular Research Papers
mci.reference.pages123-131

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
LNI_037.pdf
Größe:
1.94 MB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P339 - BIOSIG 2023 - Proceedings of the 22nd International Conference of the Biometrics Special Interest Group