摘要
支持向量机(SupportVector Machine,SVM)是一种基于统计学习理论的新型机器学习算法。通过解算最优化问题,在高维特征空间中寻找最优分类超平面,从而解决复杂数据的分类及回归问题。将支持向量机理论应用到遥感图像分类的研究还处在初级阶段,传统分类算法应用于遥感图像分类存在运算速度慢、精度比较低和难以收敛等问题。从支持向量机基本理论出发,建立了一个基于支持向量机的遥感图像分类器。用遥感图像数据进行实验,并将结果与其它方法的结果进行了比较分析。实验结果表明,利用SVM进行遥感图像分类的精度明显优于神经网络算法和最大似然算法分类精度。
Support Vector Machine（SVM） is a state-of-the-art machine learning algorithm based on statistical learning theory.It tries to find the optimal classification hyperplane in high dimensional feature space to handle complicated classification and regression problems by solving optimization problems.The SVM theory applied to remote sensing image classification is still in the initial stage.Traditional algorithms used in remote sensing image classification have some problems such as low computing rate,low accuracy and much difficulty for convergence.According to SVM theory,the classification model based on SVM was constructed.By experimenting with remote sensing data and comparing the resules with others,the results indicate that the radial basis kernel function of SVM has the highest accuracy.SVM classifier has more advantages in the classification in contrast with radial basis function neural network classifier and maximum likelihood classifier.As the in-depth research on SVM continues,it will be more widely used in remote sensing image classification.
出处
《科学技术与工程》
2010年第15期3659-3663,共5页
Science Technology and Engineering
关键词
支持向量机
遥感图像分类
神经网络
最大似然法
Support Vector Machine（SVM） machine learning statistical learning theory remote sensing image classification maximum likelihood classifier
