Modeling and synthesis of kinship patterns of facial expressions

Simple item page
buir.contributor.authorDibeklioğlu, Hamdi
dc.citation.epage143en_US
dc.citation.spage133en_US
dc.citation.volumeNumber79en_US
dc.contributor.authorErtuğrul, I. Ö.en_US
dc.contributor.authorJeni, L. A.en_US
dc.contributor.authorDibeklioğlu, H.en_US
dc.date.accessioned2019-02-21T16:01:38Z
dc.date.available2019-02-21T16:01:38Z
dc.date.issued2018en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractAnalysis of kinship from facial images or videos is an important problem. Prior machine learning and computer vision studies approach kinship analysis as a verification or recognition task. In this paper, for the first time in the literature, we propose a kinship synthesis framework, which generates smile and disgust videos of (probable) children from the expression videos (smile and disgust) of parents. While the appearance of a child's expression is learned using a convolutional encoder-decoder network, another neural network models the dynamics of the corresponding expression. The expression video of the estimated child is synthesized by the combined use of appearance and dynamics models. In order to validate our results, we perform kinship verification experiments using videos of real parents and estimated children generated by our framework. The results show that generated videos of children achieve higher correct verification rates than those of real children. Our results also indicate that the use of generated videos together with the real ones in the training of kinship verification models, increases the accuracy, suggesting that such videos can be used as a synthetic dataset. Furthermore, we evaluate the expression similarity between input and output frames, and show that the proposed method can fairly retain the expression of input faces while transforming the facial identity.
dc.description.provenanceMade available in DSpace on 2019-02-21T16:01:38Z (GMT). No. of bitstreams: 1 Bilkent-research-paper.pdf: 222869 bytes, checksum: 842af2b9bd649e7f548593affdbafbb3 (MD5) Previous issue date: 2018en
dc.embargo.release2020-11-01en_US
dc.identifier.doi10.1016/j.imavis.2018.09.012
dc.identifier.issn0262-8856
dc.identifier.urihttp://hdl.handle.net/11693/49889
dc.language.isoEnglish
dc.publisherElsevier
dc.relation.isversionofhttps://doi.org/10.1016/j.imavis.2018.09.012
dc.source.titleImage and Vision Computingen_US
dc.subjectFacial action unitsen_US
dc.subjectFacial dynamicsen_US
dc.subjectKinship synthesisen_US
dc.subjectKinship verificationen_US
dc.subjectTemporal analysisen_US
dc.titleModeling and synthesis of kinship patterns of facial expressionsen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Modeling_and_synthesis_of_kinship_patterns_of_facial_expressions.pdf
Size:
2.07 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Scholarly Publications - Computer Engineering