26 October 2013 Object recognition with incomplete features based on evidence accumulation
Author Affiliations +
Proceedings Volume 8918, MIPPR 2013: Automatic Target Recognition and Navigation; 89180Z (2013) https://doi.org/10.1117/12.2031497
Event: Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, 2013, Wuhan, China
Abstract
In this paper, we address the problem of object recognition in clutter with incomplete features, focusing on challenging small target. Since the discriminative illumination, occluded or imperfect of the feature extraction algorithm, multi-class features of the object are incomplete which increase the false alarm rate of object recognition. How to use the incomplete features such as region and edge for object recognition, the vote of each fragment region contributes to the recognition result according to its reliability. We cast it as a graph search problem and propose a novel evidence accumulation algorithm to efficiently solve it.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Li Zhang, Fan Peng, "Object recognition with incomplete features based on evidence accumulation", Proc. SPIE 8918, MIPPR 2013: Automatic Target Recognition and Navigation, 89180Z (26 October 2013); doi: 10.1117/12.2031497; https://doi.org/10.1117/12.2031497
PROCEEDINGS
6 PAGES


SHARE
Back to Top