KERNEL METHODS FOR STATISTICAL LEARNING IN COMPUTER VISION AND

The memory of my mother who died on August 29, 1985 My lovely wife Yosra iii ACKNOWLEDGMENTS All deepest and sincere thanks are due to Almighty ALLAH, the merciful, the com-passionate for the uncountable gifts given to me. I would like to extend my deepest appreciation to Dr. Aly A. Farag for giving me the opportunity to join the CVIP Lab and for his direction and assistance in developing this dissertation. I would also like to thank Dr. Moumen Ahmed for helping me in joining the Lab. Many thanks for Dr. Greg Rempala for his continuous discussion and support. I would also like to thank Dr. Jon Atli Benediktsson for joining my PhD committee. I would also like to thank Dr. Hichem Frigui, Dr. Xiangqian Liu, Dr. Tamer Inanc, and Dr. Ryan Gill for serving on my committee. I would also like to thank my colleagues in the CVIP Lab for their continuous support and friendship during the past years, with special thanks to Ayman El-Baz for his collaboration. I would like to thank all my friends in Louisville for turning my stay here into a pleasant life. Finally, I would like to thank my family for their unwaivering encouragement and support, without which this thesis and research would not have been possible. i