Show simple item record

dc.contributor.advisorGao, Yongsheng
dc.contributor.authorZhang, Xiaozheng
dc.date.accessioned2018-01-23T02:29:14Z
dc.date.available2018-01-23T02:29:14Z
dc.date.issued2008
dc.identifier.doi10.25904/1912/3670
dc.identifier.urihttp://hdl.handle.net/10072/366373
dc.description.abstractPose invariance is a key ability for face recognition to achieve its advantages of being non-intrusive over other biometric techniques requiring cooperative subjects such as fingerprint recognition and iris recognition. Due to the complex 3D structures and various surface reflectivities of human faces, however, pose variations bring serious challenges to current face recognition systems. The image variations of human faces under 3D transformations are larger than that existing face recognition can tolerate. This research attempts to achieve pose-invariant face recognition through 3D reconstructions, which inversely estimates 3D shape and texture information of human faces from 2D face images. This extracted information is intrinsic features useful for face recognition which is invariable to pose changes. The proposed framework reconstructs personalised 3D face models from images of known people in a database (or gallery views) and generates virtual views in possible poses for face recognition algorithms to match the captured image (or probe view). In particular, three different scenarios of gallery views have been scrutinised: 1) when multiple face images from a fixed viewpoint under different illumination conditions are used as gallery views; 2) when a police mug shot consisting of a frontal view and a side view per person is available as gallery views; and 3) when a single frontal face image per person is used as gallery view. These three scenarios provide the system different amount of information and cover a wide range of situations which a face recognition system will encounter. Three novel 3D reconstruction approaches have then been proposed according to these three scenarios, which are 1) Heterogeneous Specular and Diffuse (HSD) face modelling, 2) Multilevel Quadratic Variation Minimisation (MQVM), and 3) Automatic Facial Texture Synthesis (AFTS), respectively. Experimental results show that these three proposed approaches can effectively improve the performance of face recognition across pose...
dc.languageEnglish
dc.publisherGriffith University
dc.publisher.placeBrisbane
dc.rights.copyrightThe author owns the copyright in this thesis, unless stated otherwise.
dc.subject.keywordspose-invariant face recognition
dc.subject.keywordspose invariance
dc.subject.keywordsface recognition
dc.subject.keywordsface recognition systems
dc.subject.keywordsface recognition algorithms
dc.titlePose-invariant Face Recognition through 3D Reconstructions
dc.typeGriffith thesis
gro.facultyScience, Environment, Engineering and Technology
gro.rights.copyrightThe author owns the copyright in this thesis, unless stated otherwise.
gro.hasfulltextFull Text
dc.contributor.otheradvisorDimitrijev, Sima
dc.rights.accessRightsPublic
gro.identifier.gurtIDgu1316995907870
gro.identifier.ADTnumberadt-QGU20100730.111318
gro.source.ADTshelfnoADT0786
gro.thesis.degreelevelThesis (PhD Doctorate)
gro.thesis.degreeprogramDoctor of Philosophy (PhD)
gro.departmentSchool of Engineering
gro.griffith.authorZhang, Paul


Files in this item

This item appears in the following Collection(s)

Show simple item record