Vis enkel innførsel

dc.contributor.authorHukkelås, Håkon
dc.contributor.authorLindseth, Frank
dc.contributor.authorMester, Rudolf
dc.date.accessioned2019-12-11T08:07:36Z
dc.date.available2019-12-11T08:07:36Z
dc.date.created2019-11-01T11:48:19Z
dc.date.issued2019
dc.identifier.isbn978-3-030-33720-9
dc.identifier.urihttp://hdl.handle.net/11250/2632578
dc.description.abstractWe propose a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. We ensure total anonymization of all faces in an image by generating images exclusively on privacy-safe information. Our model is based on a conditional generative adversarial network, generating images considering the original pose and image background. The conditional information enables us to generate highly realistic faces with a seamless transition between the generated face and the existing background. Furthermore, we introduce a diverse dataset of human faces, including unconventional poses, occluded faces, and a vast variability in backgrounds. Finally, we present experimental results reflecting the capability of our model to anonymize images while preserving the data distribution, making the data suitable for further training of deep learning models. As far as we know, no other solution has been proposed that guarantees the anonymization of faces while generating realistic images.nb_NO
dc.language.isoengnb_NO
dc.publisherSpringer Verlagnb_NO
dc.relation.ispartofAdvances in Visual Computing
dc.titleDeepPrivacy: A Generative Adversarial Network for Face Anonymizationnb_NO
dc.typeChapternb_NO
dc.description.versionacceptedVersionnb_NO
dc.source.pagenumber565-578nb_NO
dc.identifier.cristin1743210
dc.description.localcodeThis is a post-peer-review, pre-copyedit version of an article. Locked until 21.10.2020 due to copyright restrictions.nb_NO
cristin.unitcode194,63,10,0
cristin.unitnameInstitutt for datateknologi og informatikk
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel