KINSHIPGAN: SYNTHESIZING OF KINSHIP FACES FROM FAMILY PHOTOS BY REGULARIZING A DEEP FACE NETWORK

dc.authorwosid ÖZKAN, Akın/AAA-9046-2022
dc.contributor.author Ozkan, Savas
dc.contributor.author Ozkan, Akin
dc.contributor.other Department of Electrical & Electronics Engineering
dc.date.accessioned 2024-10-06T10:58:31Z
dc.date.available 2024-10-06T10:58:31Z
dc.date.issued 2018
dc.department Atılım University en_US
dc.department-temp [Ozkan, Savas] Middle East Tech Univ, Dept Elect Elect Engn, Ankara, Turkey; [Ozkan, Akin] Atilim Univ, Dept Elect Elect Engn, Ankara, Turkey en_US
dc.description.abstract In this paper, we propose a kinship generator network that can synthesize a possible child face by analyzing his/her parent's photo. For this purpose, we focus on to handle the scarcity of kinship datasets throughout the paper by proposing novel solutions in particular. To extract robust features, we integrate a pre-trained face model to the kinship face generator. Moreover, the generator network is regularized with an additional face dataset and adversarial loss to decrease the overfitting of the limited samples. Lastly, we adapt cycle-domain transformation to attain a more stable results. Experiments are conducted on Families in the Wild (FIW) dataset. The experimental results show that the contributions presented in the paper provide important performance improvements compared to the baseline architecture and our proposed method yields promising perceptual results. en_US
dc.description.woscitationindex Conference Proceedings Citation Index - Science
dc.identifier.citationcount 14
dc.identifier.endpage 2146 en_US
dc.identifier.isbn 9781479970612
dc.identifier.issn 1522-4880
dc.identifier.startpage 2142 en_US
dc.identifier.uri https://hdl.handle.net/20.500.14411/8914
dc.identifier.wos WOS:000455181502053
dc.institutionauthor Özkan, Akın
dc.language.iso en en_US
dc.publisher Ieee en_US
dc.relation.ispartof 25th IEEE International Conference on Image Processing (ICIP) -- OCT 07-10, 2018 -- Athens, GREECE en_US
dc.relation.ispartofseries IEEE International Conference on Image Processing ICIP
dc.relation.publicationcategory Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.subject Kinship Synthesis en_US
dc.subject Fully Convolutional Networks en_US
dc.subject Generative Adversarial Network en_US
dc.title KINSHIPGAN: SYNTHESIZING OF KINSHIP FACES FROM FAMILY PHOTOS BY REGULARIZING A DEEP FACE NETWORK en_US
dc.type Conference Object en_US
dc.wos.citedbyCount 14
dspace.entity.type Publication
relation.isAuthorOfPublication f399fa5d-a26e-401f-84b2-4e77e16bc0a7
relation.isAuthorOfPublication.latestForDiscovery f399fa5d-a26e-401f-84b2-4e77e16bc0a7
relation.isOrgUnitOfPublication c3c9b34a-b165-4cd6-8959-dc25e91e206b
relation.isOrgUnitOfPublication.latestForDiscovery c3c9b34a-b165-4cd6-8959-dc25e91e206b

Files

Collections