Visual image recognition system with object level image representation
Bạn đang xem bản rút gọn của tài liệu. Xem và tải ngay bản đầy đủ của tài liệu tại đây (5.69 MB, 170 trang )
Visual Image Recognition System with
Object-Level Image Representation
Song, Zheng (Ph.D.)
A Thesis Submitted for the degree of Doctor of
Philosophy
Department of Electrical and Computer
Engineering
National University of Singapore
2012
Declaration
I hereby declare that this thesis is my original work and it has been written by me
in its entirety. I have duly acknowledged all the sources of information which
have been used in the thesis.
This thesis has also not been submitted for any degree in any university
previously.
__________________________
Song, Zheng
05 Dec 2012
Acknowledgements
This thesis is finished with the support of my supervisor Dr. Shuicheng Yan
and many members of our Learning & Vision group. I wish to thank you
all for your gracious help during my four years Ph.D. study.
I was first guided to the research area of image recognition by my su-
pervisor, Dr. Shuicheng Yan, four years ago when I began my Ph.D. study
in National University of Singapore. I am truly thankful to him for lead-
ing me to become a researcher in this area. The research works done in
these years gave me inexhaustible joy due to variant novel findings. Prof.
Yan has devoted much to help me to learn useful techniques and share his
experience in academic research. I deeply appreciate his advice upon my
research during these years.
I also wish to thank the researchers who collaborate with the works
in my thesis. Dr. Bingbing Ni and Dr. Dong Guo provided generous help
for my work on facial appearance recognition. The human face photo and
video collection and the preliminary implementation of our system are ac-
complished with their efforts. Dr. Si Liu and Dr. Meng Wang gave me great
help in my development of the human body recognition system. Lots of
work have been done with them about the data collection, system design
and paper presentation. I also thank Dr. Qiang Chen and Mengyou Li who
contributed in the object recognition and retrieval system for the algorithm
design, system refinement and demonstration. Many other members of our
group have also generously shared lots of their knowledge which guided
me to more insightful understanding of this research area. I would like to
address my sincere gratefulness here for all their assistance.
I also appreciate the detailed comments from my thesis committee mem-
bers and examiners. They provided valuable advice on the thesis structures,
experiments and presentations.
Finally, I wish to thank my parents and my wife. They were always
giving me faith no matter when I chose to pursue this Ph.D. degree or I
was facing difficulties during my study. This thesis is also not possible to
complete without their support.
