Description
TitleA face tracking system for dynamic event recognition
Date Created2012
Other Date2012-01 (degree)
Extentxvii, 124 p. : ill.
DescriptionFace tracking has numerous applications in the field of Human Computer Interaction and behavior understanding in general. Yet, face tracking is a difficult problem because the tracker must generalize to new faces, adapt to changing illumination, keep up with fast motions and pose changes, and tolerate target occlusion. We first present our efforts to develop a system for probabilistic face tracking, using anthropometric and appearance constraints. We then move onto the focus of our work, which is the application of the face tracker to two interesting recognition problems. Firstly, given that sign language is used as a primary means of communication by deaf individuals and as augmentative communication by hearing individuals with a variety of disabilities, the development of robust, real-time sign language recognition technologies would be a major step forward in making computers equally accessible to everyone. However, most research in the field of sign language recognition has focused on the manual component of signs, despite the fact that there is critical grammatical information expressed through facial expressions and head gestures. Therefore, we present our novel framework for robust tracking and analysis of facial expressions and head gestures, by means of a dynamic feature descriptor, a 3D face model and temporal models, with an application to sign language recognition. We apply it to successful continuous recognition of six different classes of non-manual grammatical expressions. Secondly, deception is present in our everyday social and professional lives and its detection can be beneficial, not only to us individually but to our society as a whole. For example, accurate deception detection can aid law enforcement officers in solving a crime. It can also help border control agents to detect potentially dangerous individuals during routine screening interviews. Therefore, we also present two novel methods for deception detection, using only visual cues extracted from our face tracker and a skin blob tracker, both with promising results. One is based on a novel kernel density descriptor of human behavior, which can differentiate normal behavior profiles from over-controlled and agitated ones, using nearest neighbor search. The other is based on the notion of subject-interviewer synchrony.
NotePh.D.
NoteIncludes bibliographical references
NoteIncludes vita
Noteby Nicholas Michael
Genretheses, ETD doctoral
Languageeng
CollectionGraduate School - New Brunswick Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Statistical Profile