结合经验模态分解和Gabor滤波的高光谱图像分类  

Hyperspectral image classification by combining empirical mode decomposition with Gabor filtering

作　　者：王立国[1] 宛宇美 路婷婷[1] 杨月霜[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《哈尔滨工程大学学报》2016年第2期284-290,共7页Journal of Harbin Engineering University

基　　金：国家自然科学基金资助项目(61275010);国家教育部博士点基金资助项目(20132304110007);黑龙江省自然科学基金资助项目(F201409);中央高校基本科研业务费资助项目(HEUCFD1410)

摘　　要：针对传统实施于原始数据空间的纹理提取方法的不足,采用经验模态分解理论提取高光谱图像中空间结构明显的固有模态分量,并在提取出的分量上进行Gabor滤波操作,将传统纹理提取方式转移到变换域上进行,提出了一种基于二维经验模态分解融合空间信息的高精度纹理提取算法。对两个数据集进行仿真实验,实验结果表明改进算法有效地提高了高光谱图像分类精度且抗噪性能良好,提出算法性能明显优于传统Gabor-PCA算法,能够更大程度挖掘高光谱图像空间信息。Considering the shortcomings of traditional texture extraction methods implemented in original data space,in this paper we use the empirical mode decomposition theory to extract the intrinsic mode components of a distinct spatial structure from a hyperspectral image,and perform Gabor filtering on these extracted components. We transferred the traditional texture extraction method to the transform domain. In this way,we propose using a high-precision texture extraction algorithm for decomposing and integrating spatial information based on two-dimensional empirical mode decomposition. We carried out simulation tests on two datasets,and the results show that the improved algorithm effectively improves the classification accuracy of hyperspectral images and has good noise suppression performance. The proposed algorithm is thus clearly superior to the traditional Gabor-PCA algorithm,and can mine hyperspectral image spatial information to a greater extent.

关 键 词：高光谱图像 图像分类 空间信息 经验模态分解 GABOR滤波 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]