基于图像欧氏距离的高光谱图像流形降维算法  

Image Euclidean distance-based manifold dimensionality reduction algorithm for hyperspectral imagery

作　　者：陈宏达[1] 普晗晔[1] 王斌[1,2] 张立明[1] 

机构地区：[1]复旦大学电子工程系,上海200433 [2]复旦大学波散射与遥感信息重点实验室,上海200433

出　　处：《红外与毫米波学报》2013年第5期450-455,共6页Journal of Infrared and Millimeter Waves

基　　金：国家自然科学基金(No.61071134);上海市教委科研创新项目(No.13ZZ005);高等学校博士学科点专项科研基金(20110071110018)~~

摘　　要：提出两种基于图像欧氏距离的非线性降维方法.该方法利用高光谱图像物理特性,将图像欧氏距离引入到传统的流形降维算法中.与其它应用于高光谱图像的降维算法相比,该算法具有诸多优点.图像欧氏距离的引入,在考虑高光谱图像本身的空间关系的同时,很好地保持了数据点之间的局部特性,可以实现有效地去除原始数据集光谱维和空间维的冗余信息.实际高光谱数据的实验结果表明,该算法应用于高光谱图像分类时,与其它常见的方法相比具有更高的分类精度.Two nonlinear dimensionality reduction methods were proposed based on image Euclidean distance. Consider- ing the physical characters of hyperspectral imagery, the methods introduced image Euclidean distance into traditional manifold dimensionality reduction. Compared with other methods, our methods have several advantages. The introduc- tion of image Euclidean distance not only considers hyperspectral image＇ s spatial relationship, but also preserves the lo- cal feature of datasets well. Thus the proposed methods can discard efficiently the redundant information from both the spectral and spatial dimensions. The experiment results demonstrated that the proposed methods have~ higher classification accuracy than other methods when applied to hyperspectral image classification.

关 键 词：高光谱遥感图像 非线性降维 图像欧氏距离 分类 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]