A HYPERGRAPH BASED SEMI-SUPERVISED BAND SELECTION METHOD FOR HYPERSPECTRAL IMAGE CLASSIFICATION

被引:0
作者
Guo, Zhouxiao [1 ]
Bai, Xiao [1 ]
Zhang, Zhihong [2 ]
Zhou, Jun [3 ]
机构
[1] Beihang Univ, Sch Sci & Engn, Beijing 100191, Peoples R China
[2] Xiamen Univ, Xiamen, Peoples R China
[3] Griffith Univ, Sch Informat & Commun Technol, Nathan, Qld 4111, Australia
来源
2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013) | 2013年
关键词
Hyperspectral imaging; Band selection; Hypergraph; Image region classification; DIMENSIONALITY REDUCTION;
D O I
暂无
中图分类号
TB8 [摄影技术];
学科分类号
0804 ;
摘要
Band selection is a fundamental problem in hyperspectral data processing. In this paper, we present a semi-supervised learning approach and a hypergraph model to select useful bands based on few labeled object information. The contributions of this paper are two-fold. Firstly, the hypergraph model captures multiple relationships between hyperspectral image samples. Secondly, the semi-supervised learning method not only utilizes unlabeled samples in the learning process to improve model performance, but also requires little labeled samples which can significantly reduce large amount of human labor and costs. The proposed approach is evaluated on AVIRIS and APHI datasets, which demonstrate its advantages over several other band selection methods.
引用
收藏
页码:3137 / 3141
页数:5
相关论文
共 19 条
[1]  
Agarwal Abhishek, 2007, 2007 IEEE International Symposium on Signal Processing and Information Technology, P353, DOI 10.1109/ISSPIT.2007.4458191
[2]   Feature selection and classification of hyperspectral images, with support vector machines [J].
Archibald, Rick ;
Fann, George .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2007, 4 (04) :674-677
[3]   Methodology for hyperspectral band selection [J].
Bajcsy, P ;
Groves, P .
PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2004, 70 (07) :793-802
[4]   Constrained band selection for hyperspectral imagery [J].
Chang, Chein-I ;
Wang, Su .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2006, 44 (06) :1575-1585
[5]   A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification [J].
Chang, CI ;
Du, Q ;
Sun, TL ;
Althouse, MLG .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (06) :2631-2641
[6]   Dimensionality reduction of unsupervised data [J].
Dash, M ;
Liu, H ;
Yao, L .
NINTH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 1997, :532-539
[7]   Least angle regression - Rejoinder [J].
Efron, B ;
Hastie, T ;
Johnstone, I ;
Tibshirani, R .
ANNALS OF STATISTICS, 2004, 32 (02) :494-499
[8]   Band, selection for hyperspectral image classification using mutual information [J].
Guo, Baofeng ;
Gunn, Steve R. ;
Damper, R. I. ;
Nelson, J. D. B. .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (04) :522-526
[9]  
HAN TS, 1980, INFORM CONTROL, V46, P26, DOI 10.1016/S0019-9958(80)90478-7
[10]  
Kobayashi K., 2002, MATH INFORM CODING, V203