Show simple item record

2021-09-18Zeitschriftenartikel DOI: 10.3390/computers10090117
Feature Focus: Towards Explainable and Transparent Deep Face Morphing Attack Detectors †
dc.contributor.authorSeibold, Clemens
dc.contributor.authorHilsmann, Anna
dc.contributor.authorEisert, Peter
dc.date.accessioned2021-10-14T09:06:39Z
dc.date.available2021-10-14T09:06:39Z
dc.date.issued2021-09-18none
dc.date.updated2021-10-01T17:45:22Z
dc.identifier.urihttp://edoc.hu-berlin.de/18452/24197
dc.description.abstractDetecting morphed face images has become an important task to maintain the trust in automated verification systems based on facial images, e.g., at automated border control gates. Deep Neural Network (DNN)-based detectors have shown remarkable results, but without further investigations their decision-making process is not transparent. In contrast to approaches based on hand-crafted features, DNNs have to be analyzed in complex experiments to know which characteristics or structures are generally used to distinguish between morphed and genuine face images or considered for an individual morphed face image. In this paper, we present Feature Focus, a new transparent face morphing detector based on a modified VGG-A architecture and an additional feature shaping loss function, as well as Focused Layer-wise Relevance Propagation (FLRP), an extension of LRP. FLRP in combination with the Feature Focus detector forms a reliable and accurate explainability component. We study the advantages of the new detector compared to other DNN-based approaches and evaluate LRP and FLRP regarding their suitability for highlighting traces of image manipulation from face morphing. To this end, we use partial morphs which contain morphing artifacts in predefined areas only and analyze how much of the overall relevance each method assigns to these areas.eng
dc.language.isoengnone
dc.publisherHumboldt-Universität zu Berlin
dc.rights(CC BY 4.0) Attribution 4.0 Internationalger
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectface morphing attackseng
dc.subjectDNN explainabilityeng
dc.subjectface image forgery detectioneng
dc.subject.ddc004 Informatiknone
dc.titleFeature Focus: Towards Explainable and Transparent Deep Face Morphing Attack Detectors †none
dc.typearticle
dc.identifier.urnurn:nbn:de:kobv:11-110-18452/24197-4
dc.identifier.doi10.3390/computers10090117none
dc.identifier.doihttp://dx.doi.org/10.18452/23539
dc.type.versionpublishedVersionnone
local.edoc.container-titleComputersnone
local.edoc.pages18none
local.edoc.type-nameZeitschriftenartikel
local.edoc.institutionMathematisch-Naturwissenschaftliche Fakultätnone
local.edoc.container-typeperiodical
local.edoc.container-type-nameZeitschrift
local.edoc.container-publisher-nameMDPInone
local.edoc.container-publisher-placeBaselnone
local.edoc.container-volume10none
local.edoc.container-issue9none
dc.description.versionPeer Reviewednone
local.edoc.container-articlenumber117none
dc.identifier.eissn2073-431X
local.edoc.affiliationSeibold, Clemens; 1Department of Vision and Imaging Technologies, Fraunhofer Heinrich-Hertz-Institute, 10587 Berlin, Germany; anna.hilsmann@hhi.fraunhofer.de (A.H.); peter.eisert@hhi.fraunhofer.de (P.E.)none
local.edoc.affiliationHilsmann, Anna; 1Department of Vision and Imaging Technologies, Fraunhofer Heinrich-Hertz-Institute, 10587 Berlin, Germany; anna.hilsmann@hhi.fraunhofer.de (A.H.); peter.eisert@hhi.fraunhofer.de (P.E.)none
local.edoc.affiliationEisert, Peter; 1Department of Vision and Imaging Technologies, Fraunhofer Heinrich-Hertz-Institute, 10587 Berlin, Germany; anna.hilsmann@hhi.fraunhofer.de (A.H.); peter.eisert@hhi.fraunhofer.de (P.E.)none

Show simple item record