摘要
高光谱遥感图像具有维数高的特点,当样本较少时,利用传统的统计识别方法分类,分类精度低。可支撑向量机(SVM)能解决小样本、高维、非线性分类问题。采用归一化法对原始图像做预处理,再分析不同的SVM核函数对分类精度的影响;并把SVM与最小距离法,马氏距离法等的分类结果进行比较。结果表明SVM的核函数类型对分类正确率影响不大,其分类精度高于传统的统计识别方法。
The characteristic of hyper- spectral remote sensing data is high dimensional. The accuracy of traditional classification methods is always unsatisfactory. Support vector machine （SVM） is a good method for solving limited sample, high dimensional, and nom -linear classification problem. The image data are preprocessed by Image normalization method, the influences of different kernel functions on classification accuracy are analyzed, and the classification results by SVM are compared with that of other methods （ such as Minimum Distance method, Mahalanobis Distance Method）. Experiment results show that the classification accuracy is almost identical for different kernel functions, and VM method has better classification and recognition accuracy than traditional algorithms.
出处
《计算机仿真》
CSCD
北大核心
2009年第12期164-167,共4页
Computer Simulation
关键词
高光谱遥感
图像预处理
支撑向量机
核函数
Hyper - spectral remote sensing
Image preprocessing
Support vector machines （SVM）
Kernel function
