A Band-Weighted Support Vector Machine Method for Hyperspectral Imagery Classification

A band-weighted support vector machine (BWSVM) method is proposed to classify hyperspectral imagery (HSI). The BWSVM presents an L 1 penalty term of band weight vector to regularize the regular SVM model. The L 1 norm regularization term guarantees the sparsity of band weights and describes potentia...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2017-10, Vol.14 (10), p.1710-1714
Main Authors: Sun, Weiwei, Liu, Chun, Xu, Yan, Tian, Long, Li, Weiyue
Format: Article
Language:English
Subjects:
Band-weighted support vector machine (BWSVM)
Classification
Coefficients
Data models
Feature extraction
hyperspectral imagery (HSI)
Hyperspectral imaging
Image classification
Imagery
Iterative methods
Kernel
Kernels
linearization
Mathematical models
Modelling
Regularization
Sun
Support vector machines
SVM
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:A band-weighted support vector machine (BWSVM) method is proposed to classify hyperspectral imagery (HSI). The BWSVM presents an L 1 penalty term of band weight vector to regularize the regular SVM model. The L 1 norm regularization term guarantees the sparsity of band weights and describes potentially divergent contributions from different bands in modeling the binary SVM model. The BWSVM adopts the KerNel iterative feature extraction algorithm to minimize the nonconvex program. It linearizes nonlinear kernels and iteratively optimizes two convex subproblems with respect to both sample coefficients and band weights. The class label is determined by picking the largest sample coefficients from all its binary models of BWSVM. Two popular HSI data sets are utilized to testify the classification performance of BWSVM. Experimental results show that the BWSVM outperforms three state-of-the-art classifiers including SVM, random forest, and k-nearest neighbor.
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2017.2729940