Face Recognition in the presence of variance in Pose, Expression, and Occlusions

Simple item page
dc.contributor.advisorKakadiaris, Ioannis A.
dc.contributor.committeeMemberLaszka, Aron
dc.contributor.committeeMemberGnawali, Omprakash
dc.contributor.committeeMemberCoskun, Baris
dc.creatorXu, Xiang 1991-
dc.creator.orcid0000-0003-3814-7203
dc.date.accessioned2019-09-15T00:03:25Z
dc.date.available2019-09-15T00:03:25Z
dc.date.createdMay 2019
dc.date.issued2019-05
dc.date.submittedMay 2019
dc.date.updated2019-09-15T00:03:25Z
dc.description.abstractFace recognition is a technology in which a computing device either classifies a human identity based on a facial image or verifies whether two images belong to the same subject. The recent advances have achieved remarkable performance when comparing images that are both frontal and non-occluded. However, significant challenges remain in the presence of variations in pose, expression, and occlusions. The goal of this dissertation is to achieve statistically significant improvement in the performance of face recognition systems using 2D images that depict individuals with facial expressions and accessories. Four contributions made in this dissertation can be summarized as follows: (i) a 3D-aided 2D face recognition system with additional evaluation package that is modular, easy to use, and easy to install was designed, implemented, and evaluated. This proposed system can work with the facial images that have variations in head pose as large as 90 degree and improved the face recognition performance by 9\% on average when compared with FaceNet on UHDB31 dataset. (ii) two landmark detectors were developed and evaluated on 2D images that are fast and accurate; (iii) feature aggregation learning was proposed for face reconstruction from a single image, which achieved 16% and 10% improvement when compared with the current state-of-the-art on the BU-3DFE and JNU-3D datasets, respectively, and (iv) an occlusion-aware face recognition approach was proposed that improved the generalizability of the facial embedding generator and a graph neural network was designed in an unsupervised manner to adapt the knowledge learned in the image-based scenario to mixed-media set scenario.
dc.description.departmentComputer Science, Department of
dc.format.digitalOriginborn digital
dc.format.mimetypeapplication/pdf
dc.identifier.citationPortions of this document appear in: Xu, Xiang, and Ioannis A. Kakadiaris. "Open Source Face Recognition Performance Evaluation Package." arXiv preprint arXiv:1901.09447 (2019). And in: Xu, Xiang, Shishir K. Shah, and Ioannis A. Kakadiaris. "Face alignment via an ensemble of random ferns." In 2016 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA), pp. 1-8. IEEE, 2016. And in: Xu, Xiang, and Ioannis A. Kakadiaris. "Joint head pose estimation and face alignment framework using global and local CNN features." In 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), pp. 642-649. IEEE, 2017. And in: Xu, Xiang, Ha Le, and Ioannis Kakadiaris. "On the importance of feature aggregation for face reconstruction." In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 922-931. IEEE, 2019.
dc.identifier.urihttps://hdl.handle.net/10657/4660
dc.language.isoeng
dc.rightsThe author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. UH Libraries has secured permission to reproduce any and all previously published materials contained in the work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s).
dc.subjectFace recognition
dc.subject3D-aided Face Recognition
dc.subjectFace alignment
dc.subjectFace Reconstruction
dc.titleFace Recognition in the presence of variance in Pose, Expression, and Occlusions
dc.type.dcmiText
dc.type.genreThesis
thesis.degree.collegeCollege of Natural Sciences and Mathematics
thesis.degree.departmentComputer Science, Department of
thesis.degree.disciplineComputer Science
thesis.degree.grantorUniversity of Houston
thesis.degree.levelDoctoral
thesis.degree.nameDoctor of Philosophy

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
XU-DISSERTATION-2019.pdf
Size:
15.09 MB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.42 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.81 KB
Format:
Plain Text
Description:
Download

Collections

Published ETD Collection