【摘要】 研究遥感图像分类精度问题,遥感图像分类根据图像特征进行分类,然而其特征维数相当高且信息冗余严重,分类器不能降低特征维数,导致分类器计算量大,图像分类效率和正确率低。利用主成分分析(PCA)降维特征维数的优点,提出一种基于PCA-SVM的遥感图像分类方法。PCA-SVM算法首先采用LBP算子提取遥感图像特征,然后采用PCA对遥感图像特征进行降维处理,减少特征维数并消除特征冗余信息,获得对分类结果贡献大的特征,最后采用SVM进行遥感图像分类。仿真结果表明,PCA-SVM提高了遥感图像分类效率和正确率。更多还原

【Abstract】 Study remote sensing image classification.In order to improve the accuracy of remote sensing image classification,we proposed a remote sensing image classification method based on the PCA-SVM.Firstly,the improved LBP operator was used to extract the image characteristics,and then the PCA was used for remote sensing image feature dimension reduction and elimination of redundant information,to obtain the classification results of the important feature.Finally,the SVM was used for the classification of remote sensing images.The simulation experimental results show that PCA-SVM is a good solution to the current problems in the remote sensing image classification algorithm,which can reduce the computation greatly and improve the efficiency and accuracy of remote sensing image classification.更多还原