Date of Award
1-1-2015
Document Type
Dissertation
Degree Name
Ph.D.
Department
Computer Engineering
First Advisor
Mohammad H. Mahoor, Ph.D.
Keywords
Action unit detection, Facial expression recognition, Multiple kernel learning, Multi-task learning, Support vector machines, Transfer learning
Abstract
Automated analysis of facial expressions has remained an interesting and challenging research topic in the field of computer vision and pattern recognition due to vast applications such as human-machine interface design, social robotics, and developmental psychology. This dissertation focuses on developing and applying transfer learning algorithms - multiple kernel learning (MKL) and multi-task learning (MTL) - to resolve the problems of facial feature fusion and the exploitation of multiple facial action units (AUs) relations in designing robust facial expression recognition systems. MKL algorithms are employed to fuse multiple facial features with different kernel functions and tackle the domain adaption problem at the kernel level within support vector machines (SVM). lp-norm is adopted to enforce both sparse and nonsparse kernel combination in our methods. We further develop and apply MTL algorithms for simultaneous detection of multiple related AUs by exploiting their inter-relationships. Three variants of task structure models are designed and investigated to obtain fine depiction of AU relations. lp-norm MTMKL and TD-MTMKL (Task-Dependent MTMKL) are group-sensitive MTL methodsthat model the co-occurrence relations among AUs. On the other hand, our proposed hierarchical multi-task structural learning (HMTSL) includes a latent layer to learn a hierarchical structure to exploit all possible AU interrelations for AU detection. Extensive experiments on public face databases show that our proposed transfer learning methods have produced encouraging results compared to several state-of-the-art methods for facial expression recognition and AU detection.
Publication Statement
Copyright is held by the author. User is responsible for all copyright compliance.
Recommended Citation
Zhang, Xiao, "Facial Expression Analysis via Transfer Learning" (2015). Electronic Theses and Dissertations. 731.
https://digitalcommons.du.edu/etd/731
Provenance
Received from ProQuest
Rights holder
Xiao Zhang
File size
107 p.
Copyright date
2015
File format
application/pdf
Language
en
Discipline
Computer engineering
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons