引入负相似的高光谱图像半监督分类  

Dissimilarity in Semisupervised Classification of Hyperspectral Image

作　　者：王立国[1] 王雪君[1] 郝思媛[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,哈尔滨150001

出　　处：《信号处理》2015年第4期414-422,共9页Journal of Signal Processing

基　　金：国家自然科学基金项目(61275010);教育部博士点基金(20132304110007);黑龙江省自然科学基金(F201409)

摘　　要：高光谱图像数据体现为波段多、地物标签获取困难大、谱信息抗干扰能力弱等特征,容易引起维数灾难、光谱空间变异性等问题,从而影响分类器的分类精度。针对这些问题,本文将负相似信息引入到拉普拉斯支持向量机(Laplacian Support Vector Machine,Lap SVM)的流形正则化项中,提出了一种引入负相似的拉普拉斯支持向量机(Dissimilarity in Laplacian Support Vector Machine,Diss-Lap SVM)分类算法,抑制光谱空间变异对分类结果的影响。同时,本文提出利用线性近邻传播(Linear Neighborhood Propagation,LNP)算法构造图的拉普拉斯矩阵,更有效地引入无标签样本的信息。实验结果表明,本文算法的分类精度得到了提高,特别是对光谱特征相似的地物。Hyperspectral image has some typical characteristics such as too many of bands,hard to obtaln labeling sam-ples,easy of being interfered of spectral information.These characteristics lead to the dimensionality disaster and the spa-tial variability of spectral information.To solve these problems,it is proposed to introduce dissimilarity in Laplacian support vector machine （Diss-LapSVM）by the adding dissimilarity information to machine’manifold regularization term,which re-stralns the influence of the spatial variability effectively.Meanwhile,in order to introduce appropriately distribution of unla-beled samples,This paper provides linear neighborhood propagation （LNP）to construct graph Laplacian matrix.The re-sults illustrated that the proposed method can improve the classification accuracy,especially for samples which have similar spectral features.

关 键 词：高光谱图像 负相似 LapSVM算法 LNP算法 半监督分类 

分 类 号：TN911.73[电子电信—通信与信息系统]