The Community for Technology Leaders
RSS Icon
Subscribe
Orlando, FL
Oct. 19, 2009 to Oct. 22, 2009
ISBN: 978-1-4244-5390-0
pp: 95-98
Hideaki Uchiyama , Keio University, Japan
Hideo Saito , Keio University, Japan
ABSTRACT
We propose a technique for text document tracking over a large range of viewpoints. Since the popular SIFT or SURF descriptors typically fail on such documents, our method considers instead local arrangement of keypoints. We extends Locally Likely Arrangement Hashing (LLAH), which is limited to fronto-parallel images: We handle a large range of viewpoints by learning the behavior of keypoint patterns when the camera viewpoint changes. Our method starts tracking a document from a nearly frontal view. Then, it undergoes motion, and new configurations of keypoints appear. The database is incrementally updated to reflect these new observations, allowing the system to detect the document under the new viewpoint. We demonstrate the performance and robustness of our method by comparing it with the original LLAH.
CITATION
Hideaki Uchiyama, Hideo Saito, "Augmenting text document by on-line learning of local arrangement of keypoints", ISMAR, 2009, 2009 8th IEEE International Symposium on Mixed and Augmented Reality 2009. Science and Technology. ISMAR 2009, 2009 8th IEEE International Symposium on Mixed and Augmented Reality 2009. Science and Technology. ISMAR 2009 2009, pp. 95-98, doi:10.1109/ISMAR.2009.5336491
37 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool