Accession number:20080811105759
Title:SLEX-NWFE feature extraction method for hyperspectral image classification
Authors:Huang, Hsiao-Yun (1); Kuo, Bor-Chen (2); Liu, Hsiang-Chuan (3); Liu, Yu-Lung (4)
Author affiliation:(1) Department of Statistics and Information Science, Fu Jen Catholic University, Taipei, Taiwan; (2) Graduate School of Educational Measurement and Statistics, National Taichung University, Taichung, Taiwan; (3) Department of Bioinformatics, Asia University, Taiwan; (4) Department of Mathematics Education,
National Taichung University, Taichung, Taiwan Corresponding author:Huang, H.-Y.
(stat2021@mail.fju.edu.tw)
Source title:International Geoscience and Remote Sensing Symposium (IGARSS)
Abbreviated source title:Dig Int Geosci Remote Sens Symp (IGARSS) Monograph title:2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007
Issue date:2008
Publication year:2008 Pages:3210-3214
Article number:4423528 Language:English
CODEN:IGRSE3
ISBN-10:1424412129 ISBN-13:9781424412129
Document type:Conference article (CA)
Conference name:2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007
Conference date:June 23, 2007 - June 28, 2007 Conference location:Barcelona, Spain
Conference code:71398
Publisher:Institute of Electrical and Electronics Engineers Inc., 445 Hoes Lane / P.O. Box 1331, Piscataway, NJ 08855-1331, United States
Abstract:Each pixel of the hyperspectral image is composed of
hundreds of individual bands. Usually, these pixels are considered as
high dimensional vectors. NWFE is a very robust and superior feature extraction method in this aspect of view of image pixel. On the other hand, since adjacent bands in a pixel are usually highly correlated, each pixel can also be viewed as a time series or signal.
Therefore, the classification of hyperspectral data becomes the problem of distinguishing between different time series. As the consequence, time series discrimination methods, such as SLEX related time series methods, can then be applied in the
classification of hyperspectral image. In this paper, a selection ensemble of NWFE and SLEX is proposed for classifying multi-group hyperspectral image. The performance of the proposed scheme is compared to SLEX and NWFE both by simulation data set and real hyperspectral image dataset, Washington DC Mall. These results show that the proposed scheme has higher testing data
classification accuracy than others. © 2007 IEEE.
Number of references:12
Main heading:Image classification
Controlled terms:Computer simulation - Data acquisition - Feature extraction - Pixels - Remote sensing - Time series analysis
Uncontrolled terms:Hyperspectral image - Image pixel - Multi-group classification
Classification code:716 Telecommunication; Radar, Radio and Television - 722.2 Computer Peripheral Equipment - 723.2 Data Processing and Image Processing - 723.5 Computer Applications - 731.1 Control Systems - 922.2 Mathematical Statistics
DOI:10.1109/IGARSS.2007.4423528 Database:Compendex
Compilation and indexing terms, Copyright 2009 Elsevier Inc.