IEEE - Institute of Electrical and Electronics Engineers, Inc. - Background Robust Object Labeling by Voting of Weight-Aggregated Local Features

2006 18th International Conference on Pattern Recognition

Author(s): Sungho Kim ; Kuk-Jin Yoon ; In So Kweon
Sponsor(s): IEEE CPS
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 January 2006
Conference Location: Hong Kong, China
Conference Date: 20 August 2006
Volume: 2
Page(s): 219 - 222
ISBN (Paper): 0-7695-2521-0
ISSN (Paper): 1051-4651
DOI: 10.1109/ICPR.2006.311
Regular:

In this paper, we present a new voting-based object labeling method that is robust to background clutter. The conventional simple voting method shows very poor performance under clutter. To reduce... View More

Advertisement