You are here

Feature Extraction for Hyperspectral Imagery via Ensemble Localized Manifold Learning

TitleFeature Extraction for Hyperspectral Imagery via Ensemble Localized Manifold Learning
Publication TypeJournal Article
Year of Publication2015
AuthorsLi, F., L. Xu, A. Wong, and D. A. Clausi
JournalIEEE Geoscience and Remote Sensing Letters
Volume12
Issue12
Start Page2486 - 2490
Abstract

A feature extraction approach for hyperspectral image classification has been developed. Multiple linear manifolds are learned to characterize the original data based on their locations in the feature space, and an ensemble of classifier is then trained using all these manifolds. Such manifolds are localized in the feature space (which we will refer to as “localized manifolds”) and can overcome the difficulty of learning a single global manifold due to the complexity and nonlinearity of hyperspectral data. Two state-of-the-art feature extraction methods are used to implementlocalized manifolds. Experimental results show that classification accuracy is improved using both localized manifold learning methods on standard hyperspectral data sets.

Related files: