Segmental discriminative analysis for American Sign Language recognition and verification

who made all of this possible, for their endless encouragement and patience. iii ACKNOWLEDGEMENTS I owe special thanks to many people, whose support and help were indispensable in completing this thesis. First, I would like to thank my advisors, Dr. and Dr. Jim Rehg, for their thorough guidance of my research and many aspects of my life as a foreign student in this country. The thoughtful discussion about attitudes toward life, a career path, and so forth, always reminded me that you were not only my mentors but also my friends. I would like to thank Dr. Harley Hamilton and Dr. Stan Sclaroff for their participation on my dissertation committee and their valuable feedback to this dissertation. I thank Dr. Aaron Bobick and Dr. Charles Isbell for their insightful critiques while they served as members of my Ph.D. qualifying exam committee. Their challenging questions contributed to the success of my research projects. I also thank other faculty members of the College of Computing, especially those in the School of Interactive Computing, for their knowledgeable input and support in my pursuit of a doctorate degree. The discussion with Vladimir Koltchinskii from the School of Mathematics have also been very productive. unhappy, anxious, or frustrated, you are always there for me. I am lucky to have so many friends at Georgia Tech.