Hyperspectral Image Classification Through Bilayer Graph-Based Learning

Hyperspectral image classification with limited number of labeled pixels is a challenging task. In this paper, we propose a bilayer graph-based learning framework to address this problem. For graph-based classification, how to establish the neighboring relationship among the pixels from the high dim...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2014-07, Vol.23 (7), p.2769-2778
Main Authors: Gao, Yue, Ji, Rongrong, Cui, Peng, Dai, Qionghai, Hua, Gang
Format: Article
Language:English
Subjects:
Applied sciences
Classification
Educational institutions
Exact sciences and technology
Hyperspectral imaging
Image processing
Information, signal and communications theory
Linear programming
Random variables
Semisupervised learning
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
Telecommunications and information theory
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hyperspectral image classification with limited number of labeled pixels is a challenging task. In this paper, we propose a bilayer graph-based learning framework to address this problem. For graph-based classification, how to establish the neighboring relationship among the pixels from the high dimensional features is the key toward a successful classification. Our graph learning algorithm contains two layers. The first-layer constructs a simple graph, where each vertex denotes one pixel and the edge weight encodes the similarity between two pixels. Unsupervised learning is then conducted to estimate the grouping relations among different pixels. These relations are subsequently fed into the second layer to form a hypergraph structure, on top of which, semisupervised transductive learning is conducted to obtain the final classification results. Our experiments on three data sets demonstrate the merits of our proposed approach, which compares favorably with state of the art.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2014.2319735