Given a set of images or videos having common content, the objective of co-segmentation is to simultaneously segment the set of images or videos to extract this common content. The term “common content” here refers to the image or video regions that depict the same thing, which, in most of the cases, is the theme of the input images or videos acknowledged by the user. Most previous approaches focus on image co-segmentation, while recently, more and more attempts have been made on the problem of video co-segmentation, which presents much more complexity and difficulty than image segmentation. In this thesis, we address the challenge of video co-segmentation and develop techniques for common content extraction. (Abstract shortened by UMI.)
|School:||National University of Singapore (Singapore)|
|Department:||Electrical & Computer Engineering|
|School Location:||Republic of Singapore|
|Source:||DAI-B 77/06(E), Dissertation Abstracts International|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be