[1]ZHAO Chun-hui,CHEN Wan-hai,WAN jian.An improved hyperspectral image classification method for? a multiclass support vector machine[J].CAAI Transactions on Intelligent Systems,2008,3(1):77-82.
Copy

An improved hyperspectral image classification method for? a multiclass support vector machine

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 3 Number of periods: 2008 1 Page number: 77-82 Column: 学术论文—机器学习 Public date: 2008-02-25
Title:
An improved hyperspectral image classification method for? a multiclass support vector machine
Author(s):
ZHAO Chun-hui;  CHEN Wan-hai;  WAN jian
College of Information and Communication Engineering, Harbin Engineering Univer sity, Harbin 150001，China
Keywords:
support vector machine;  secondary classification;  multiclass SVM
CLC:
TN919.81
DOI:
-
Abstract:
SVM is a machine learning method developed on the basis of statistics theory and originally designed for binary classification problems. The most effe ctive way to extend it for multiclass classification is still an area of conside rable discussion. This paper presental a secondary classification method based o n 1a1 SVM classification algorithm after a general overview of typical method s for a multiclass SVM. Our method improves the penalty factors, so it enhances th e divisibility of classes that were difficult to classify. Experimental results o f hyperspectral image classification showed that the suggested multiclass SVM ha s higher classification precision.
References:
［1］任建峰,郭 雷.多类支持向量机的自然图像分类［J］. 西北工业大学学报, 2005, 23（3） : 295298.
?REN Jianfeng, GUO Lei. Improving scene image classification with multiclass SVMs［J］. Journal of Northwestern Polytechnical University, 2005, 23（3）: 29 5298.
［2］HSU C W, LIN C J. A comparison of methods for multiclass support ve ctor machines［J］.IEEE Transactions on Neural Networks, 2002, 13(2): 415425
. ［3］刘志刚,李德仁,秦前清,等.支持向量机在多类分类问题中的推广［J］. 计算机工程与应用, 2004(7): 1013.
LIU Zhigang, LI Deren, QIN Qianqing,et al. An analytical overvie w of methods for multicategory support vector machines［J］. Computer Enginee ring and Applications, 2004(7): 1013.
［4］LANDGREBE D. Multispectral data analysis: a signal theory perspectiv e［R］. West Lafayette,USA: University, 1998.
［5］刘春红,赵春晖,张凌雁.一种新的高光谱遥感图像降维方法［J］.中国图像图形学报, 2005, 10（3）: 218222.
LIU Chunhong, ZHAO Chunhui, ZHANG Lingyan. A new method of hyperspectral r emote sensing image dimensional reduction［J］. Journal of Image and Graphic, 2 005, 10(3): 218222.
［6］赵英时.遥感应用分析原理与方法［M］. 北京: 科学出版社, 2003.
Similar References:

Memo

-

Last Update: 2009-05-10

Copyright © CAAI Transactions on Intelligent Systems