Show simple item record

dc.contributor.advisorDibeklioğlu, Hamdi
dc.contributor.authorÇalıkkasap, Oğuzhan
dc.date.accessioned2021-09-23T08:52:14Z
dc.date.available2021-09-23T08:52:14Z
dc.date.copyright2021-09
dc.date.issued2021-09
dc.date.submitted2021-09-22
dc.identifier.urihttp://hdl.handle.net/11693/76543
dc.descriptionCataloged from PDF version of article.en_US
dc.descriptionThesis (Master's): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2021.en_US
dc.descriptionIncludes bibliographical references (leaves 74-82).en_US
dc.description.abstractKinship veri cation from facial images using deep learning is an interesting problem that is unsolved and gains growing attention of the research community. However, the most recent kinship veri cation systems su er from age- and genderrelated facial attributes that cause problems in kinship veri cation between subjects of di erent age and gender. In this study, we propose various methods to reduce the negative e ect of the age- and gender-related facial attributes in kinship veri cation to achieve a more robust veri cation model. The proposed approach utilizes the comprehensive modeling capabilities of the recent generative adversarial network architectures to model the age and gender of subjects and reduce their e ect in kinship veri cation, if not remove entirely. Furthermore, we conduct a thorough analysis over individual and combined e ects of age and gender normalization, performed in both image and latent space of the generative models. Lastly, we investigate the impact of additional emphasis on the facial identity information during the normalization process. Taking one of the most recent kinship veri cation models as our baseline, we show that gender normalization has reduced the veri cation performance gap between subject pairs with the same and di erent gender, up to 6%. Furthermore, joint normalization of age and gender improves the kinship veri cation accuracy up to 5% and 10% on two di erent in-the-wild kinship datasets. Therefore, this thesis proposes generic approaches to improve the reliability and robustness of kinship veri cation by normalizing the age and gender attributes without making changes in the core architecture of the employed kinship veri cation system.en_US
dc.description.statementofresponsibilityby Oğuzhan Çalıkkasapen_US
dc.format.extentxiii, 90 leaves : color illustrations, charts, graphics ; 30 cm.en_US
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectKinship veri cationen_US
dc.subjectGenerative modelingen_US
dc.subjectAge and gender normalizationen_US
dc.titleAge and gender normalization in kinship verificationen_US
dc.title.alternativeAkrabalık doğrulamasında yaş ve cinsiyet normalizasyonuen_US
dc.typeThesisen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.publisherBilkent Universityen_US
dc.description.degreeM.S.en_US
dc.identifier.itemidB133270
dc.embargo.release2022-03-22


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record