Show simple item record

dc.contributor.authorYang, Heng
dc.date.accessioned2016-06-20T11:02:26Z
dc.date.available2016-06-20T11:02:26Z
dc.date.issued2015-10-21
dc.date.submitted2016-06-17T15:17:49.020Z
dc.identifier.citationYang, H. 2015. Face Alignment in the Wild. Queen Mary University of Londonen_US
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/12954
dc.descriptionPhDen_US
dc.description.abstractFace alignment on a face image is a crucial step in many computer vision applications such as face recognition, verification and facial expression recognition. In this thesis we present a collection of methods for face alignment in real-world scenarios where the acquisition of the face images cannot be controlled. We first investigate local based random regression forest methods that work in a voting fashion. We focus on building better quality random trees, first, by using privileged information and second, in contrast to using explicit shape models, by incorporating spatial shape constraints within the forests. We also propose a fine-tuning scheme that sieves and/or aggregates regression forest votes before accumulating them into the Hough space. We then investigate holistic methods and propose two schemes, namely the cascaded regression forests and the random subspace supervised descent method (RSSDM). The former uses a regression forest as the primitive regressor instead of random ferns and an intelligent initialization scheme. The RSSDM improves the accuracy and generalization capacity of the popular SDM by using several linear regressions in random subspaces. We also propose a Cascaded Pose Regression framework for face alignment in different modalities, that is RGB and sketch images, based on a sketch synthesis scheme. Finally, we introduce the concept of mirrorability which describes how an object alignment method behaves on mirror images in comparison to how it behaves on the original ones. We define a measure called mirror error to quantitatively analyse the mirrorability and show two applications, namely difficult samples selection and cascaded face alignment feedback that aids a re-initialisation scheme. The methods proposed in this thesis perform better or comparable to state of the art methods. We also demonstrate the generality by applying them on similar problems such as car alignment.
dc.description.sponsorshipChina Scholarship Councilen_US
dc.language.isoenen_US
dc.publisherQueen Mary University of Londonen_US
dc.subjectElectronic Engineering and Computer Scienceen_US
dc.titleFace Alignment in the Wild.en_US
dc.typeThesisen_US
dc.rights.holderThe copyright of this thesis rests with the author and no quotation from it or information derived from it may be published without the prior written consent of the author


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • Theses [2761]
    Theses Awarded by Queen Mary University of London

Show simple item record