利用小波核最小噪声分离进行高光谱影像SVM分类  

SVM Classification of Hyperspectral Image Based on Wavelet Kernel Minimum Noise Fraction

作　　者：白璘[1] 刘盼芝[1] 惠萌[1] 

机构地区：[1]长安大学电子与控制工程学院,陕西西安710064

出　　处：《武汉大学学报（信息科学版）》2016年第5期624-628,664,共6页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金(51407012);中央高校基本科研业务费专项资金(310832163402;310832161001)~~

摘　　要：针对高光谱遥感影像线性特征提取方法在一定程度上会降低地物类别的可分性问题，在最小噪声分离变换基础上引入核方法，以小波核函数代替传统核函数，并将新型核最小噪声分离方法与支持向量机方法相结合，对高光谱影像数据进行分类。实验结果表明，基于小波核最小噪声分离变换的方法适合于高光谱遥感影像的非线性特征，将其应用于HYDICE系统与AVIRIS系统所获得的实验数据集，与对照算法相比，总体分类精度可提高3％～9％。Linear features extraction methods for hyperspectral imaging reduce feature class separability. Aiming to solve these problems, this paper introduces a novel kernel method based on minimum noise fraction transformation. This method focuses on the kernel function in the minimum noise fraction transformation and replacing the traditional kernel function with a wavelet kernel function. This new method improves the nonlinear mapping capability of kernel minimum noise fraction transforma- tion by exploiting the features of multi-resolution analysis. Classification experiments on hyperspectral image data combined the novel kernel minimum noise fraction transformation and support vector machine; simulation results show that the wavelet kernel minimum noise fraction transformation method is suitable for the nonlinear characteristics of hyperspectral images. The proposed method was applied to HYDICE and AVIRIS data, and compared with other algorithms. Classification accuracy increased 3%-9%.

关 键 词：高光谱影像 图像分类 核函数 最小噪声分离变换 

分 类 号：P237.4[天文地球—摄影测量与遥感] TP753[天文地球—测绘科学与技术]