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.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.