支持向量机是数据挖掘中的一项新技术,它能经过使用核映射插入的形式,对“困难维数”与“学习经过”等出现的困难能够更好的克服并对非线性问题得到更好的解决。当支持向量机在机器学习等领域展现出良好的性能后,人们开始研究将支持向量机应用于图像检索领域,通过支持向量机分类方法提高图像分类的精确度,改善图像检索的“语义鸿沟”问题。所以基于支持向量机的PCA遥感图像分类为研究对象,对支持向量机在图像处理中的应用具有理论价值和实际应用价值。 Support vector machine (SVM) is a new technique in data mining. It can overcome the difficulties of “difficult dimension ” and “learning through ” through the use of kernel mapping insertion, Linear problems are better solved. After SVM has shown good performance in machine learning and other fields, people begin to study the application of SVM in image retrieval, improve the accuracy of image classification by SVM, and improve the semantic gap of image retrieval "problem. Therefore, the classification of PCA remote sensing images based on SVM has the theoretical value and practical value for the application of SVM in image processing.