Share Email Print
cover

Proceedings Paper

Active one-class classification of remote sensing image
Author(s): Zhigang Liu; Zhichao Sun
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In many remote sensing image classification applications, interest focuses on a specific land-cover class. In these cases, one-class classification (OCC) approach is appropriate, because one classifier can be trained with samples of target class and just few or no samples of classes that are not of interest are required. However, it is always hard to build a training sample set effectively to represent the target class completely. In this paper, an active learning is introduced for OCC based on support vector data description (SVDD). In active SVDD learning, a SVDD classifier is started with a small size of training samples and an expert is asked to label supplementary training data by asking only for the labels of the most informative, unlabeled examples. Thus, it is possible to build a training sample set effectively to represent the target class completely. The effectiveness of active SVDD is proved by preliminary experiments.

Paper Details

Date Published: 29 December 2008
PDF: 9 pages
Proc. SPIE 7285, International Conference on Earth Observation Data Processing and Analysis (ICEODPA), 72850L (29 December 2008); doi: 10.1117/12.816115
Show Author Affiliations
Zhigang Liu, Beijing Normal Univ. (China)
Zhichao Sun, Beijing Normal Univ. (China)


Published in SPIE Proceedings Vol. 7285:
International Conference on Earth Observation Data Processing and Analysis (ICEODPA)
Deren Li; Jianya Gong; Huayi Wu, Editor(s)

© SPIE. Terms of Use
Back to Top