A Novel Clustering-Based Feature Representation for the Classification of Hyperspectral Imagery

A Novel Clustering-Based Feature Representation for the Classification of Hyperspectral Imagery

In this study, a new clustering-based feature extraction algorithm is proposed for the spectral-spatial classification of hyperspectral imagery. The clustering approach is able to group the high-dimensional data into a subspace by mining the salient information and suppressing the redundant informat...

Full description

Bibliographic Details
Main Authors: Qikai Lu, Xin Huang, Liangpei Zhang
Format: Article
Language:English
Published: MDPI AG 2014-06-01
Series:Remote Sensing
Subjects:
classification
feature extraction
hyperspectral imagery
clustering-based feature
Online Access:http://www.mdpi.com/2072-4292/6/6/5732

Internet

http://www.mdpi.com/2072-4292/6/6/5732

Similar Items