|Table of Contents|

TM Image Classification Based on Support Vector Machine (PDF)

《地球科学与环境学报》[ISSN:1672-6561/CN:61-1423/P]

Issue:
2006年第02期
Page:
93-95
Research Field:
Publishing date:

Info

Title:
TM Image Classification Based on Support Vector Machine
Author(s):
HU I Wen-hua
School of Geological Engineering and Surveying Engineering, Chang' an University, Xi' an 710054, Shaanxi, China
Keywords:
support vector machine;  spectrum feature;  texture feature;  maximum likelihood classifier;  classifica- tion confusion matrix
PACS:
P23;TP79
DOI:
-
Abstract:
In order to improve the accuracy of remote sensing image classification and compensate the weakness of maximum likelihood classifier, this paper puts forward a new classification method, which is based on Support Vector Machine(SVM). This method combines the spectrum features with texture ones. According to the meth- od classification test is done with ETM data, and the accuracy is compared with the one of maximum likelihood classifier. The results indicate that the accuracy obtained from the new method is better than the other' s, and combining spectrum feature and texture one is better than the one of only using one kind of feature.

References:

[1] 祁亨年，杨建刚，方陆明 .基于多类 支持向量机的 遥感图像分 类及其半监督式改进策略[J] .复旦学报 :自然科学版，2004， 43(10):781 784 .
[2] Li Jiang，Narayan an Ram M .A Shape-based App roach to Change Det ecti on of Lakes Using Time Series Remot e Sensing Image[J] .IEEE Transact ions on Geoscience and Remot e Sensing，2003，41(11):2466 2477 .
[3] 关 勇 .基于支持向量机的图像特征选择研究[J] .现代计算 机，2004 (4):14 16 .
[4] 张学工 .关于统计学习理 论与支持向 量机[J] .自动 化学报， 2001，26 (1):32 42 .
[5] 张 翔，田金文，肖晓 玲, 等 .支持 向量机 及其在 医学图 像分 类中的应用[J] .信号处理，2004，20 (4):208 212 .
[6] 边肇 祺，张 学 工 .模 式 识别[M] .北 京 :清华 大 学 出版 社， 2000 .
[7] 韩 玲 .空 间逐 步寻优 数据 挖掘 在遥 感影像 分类 中的 应用 [J] .长安大学学报 :地球科学版，2003，25 (2):70 72 .

Memo

Memo:
-
Last Update: 2006-06-20