基于小波核MSVR的IKONOS影像多分类  

Multi-Classification of IKONOS Images Based on Wavelet Kernel MSVR

作　　者：尹凡[1] 胡根生[1] 王珏[1] 

机构地区：[1]安徽大学电子信息工程学院,安徽合肥230039

出　　处：《淮北师范大学学报（自然科学版）》2014年第2期66-70,共5页Journal of Huaibei Normal University：Natural Sciences

基　　金：国家自然科学基金(61172127);安徽省自然科学基金(1408085MF121);安徽大学学生科研训练计划资助

摘　　要：针对IKONOS影像波段和光谱特点,结合小波函数对非线性信号的良好描述能力和多输出支持向量回归(MSVR)在多维机器学习领域的优势,提出一种基于小波核MSVR的IKONOS影像多分类方法,并以安徽大学新校区的IKONOS影像进行仿真实验.结果表明,提出的多分类算法优于传统的有监督二分类方法和无监督K-Means分类方法,获得较好的分类效果.According to spectral and band characteristics of IKONOS images,combined with the good description ability of wavelet function for nonlinear signal and the advantages of multi-output support vector regression（MSVR）in the field of multi-dimensional machine learning,a multi-classification method is proposed for IKONOS images based on wavelet kernel MSVR. IKONOS images of the new campus of Anhui university are used for experimentation. The experimental results show that the proposed multi-classification algorithm is superior to the traditional supervised two-category method and unsupervised K-means classification method,and obtains better classification results.

关 键 词：IKONOS影像 分类 支持向量机 小波核 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]