Date of Award
5-2012
Document type
dissertation
Access Type
Open Access Dissertation
Degree Name
Doctor of Philosophy (PhD)
Degree Program
Computer Science
First Advisor
Erik Learned-Miller
Second Advisor
Allen Hanson
Third Advisor
Andrew McCallum
Subject Categories
Computer Sciences
Abstract
Machine face recognition has traditionally been studied under the assumption of a carefully controlled image acquisition process. By controlling image acquisition, variation due to factors such as pose, lighting, and background can be either largely eliminated or specifically limited to a study over a discrete number of possibilities. Applications of face recognition have had mixed success when deployed in conditions where the assumption of controlled image acquisition no longer holds. This dissertation focuses on this unconstrained face recognition problem, where face images exhibit the same amount of variability that one would encounter in everyday life. We formalize unconstrained face recognition as a binary pair matching problem (verification), and present a data set for benchmarking performance on the unconstrained face verification task. We observe that it is comparatively much easier to obtain many examples of unlabeled face images than face images that have been labeled with identity or other higher level information, such as the position of the eyes and other facial features. We thus focus on improving unconstrained face verification by leveraging the information present in this source of weakly supervised data. We first show how unlabeled face images can be used to perform unsupervised face alignment, thereby reducing variability in pose and improving verification accuracy. Next, we demonstrate how deep learning can be used to perform unsupervised feature discovery, providing additional image representations that can be combined with representations from standard hand-crafted image descriptors, to further improve recognition performance. Finally, we combine unsupervised feature learning with joint face alignment, leading to an unsupervised alignment system that achieves gains in recognition performance matching that achieved by supervised alignment.
DOI
https://doi.org/10.7275/5g66-7363
Recommended Citation
Huang, Gary B., "Weakly Supervised Learning for Unconstrained Face Processing" (2012). Open Access Dissertations. 559.
https://doi.org/10.7275/5g66-7363
https://scholarworks.umass.edu/open_access_dissertations/559