Discriminative Multiple Kernel Learning for Hyperspectral Image Classification

Discriminative Multiple Kernel Learning for Hyperspectral Image Classification
复制标题

高光谱图像分类的判别性多核学习

DOI:
10.1109/tgrs.2016.2530807
复制
发表时间:
2016-03
影响因子:
8.2
通讯作者:
Tuia Devis
Tuia Devis
中科院分区:
工程技术1区
文献类型:
--
作者:
Wang Qingwang;Gu Yanfeng;Tuia Devis

文献摘要

参考文献

被引文献

相似文献

本文提出了一种判别多核学习(DMKL)的光谱图像分类方法。该方法的核心思想是通过最大化再现核希尔伯特空间中的可分性,从预定义的基本核中学习最优组合核。DMKL通过根据统计显著性找到最优投影方向来实现最大可分离性,从而使类内散点最小,类间散点最大,而不是耗时地寻找最优核组合。采用Fisher准则(FC)和最大余量准则(MMC)来寻找最优投影方向,从而得到DMKL-FC和DMKL-MMC两种改进方法。学习投影方向后,将所有基本核进行投影,生成判别组合核。DMKL实现了三个优点。首先,DMKL在对基本核的选择没有严格限制的情况下,可以大幅度提高分类性能。其次,高斯核的判别尺度、分类的有用波段和空间滤波器的竞争大小可以通过对相应权重进行排序来选择,其中较大的权重对应于最相关的权重。第三,DMKL通过需要更少的支持向量来减少计算负担。在两个高光谱数据集和一个多光谱数据集上进行了实验。实验结果表明,与现有的几种算法相比,本文提出的算法在光谱图像分类中具有较好的性能和较好的计算效率。
In this paper, we propose a discriminative multiple kernel learning (DMKL) method for spectral image classification. The core idea of the proposed method is to learn an optimal combined kernel from predefined basic kernels by maximizing separability in reproduction kernel Hilbert space. DMKL achieves the maximum separability via finding an optimal projective direction according to statistical significance, which leads to the minimum within-class scatter and maximum between-class scatter instead of a time-consuming search for the optimal kernel combination. Fisher criterion (FC) and maximum margin criterion (MMC) are used to find the optimal projective direction, thus leading to two variants of the proposed method, DMKL-FC and DMKL-MMC, respectively. After learning the projective direction, all basic kernels are projected to generate a discriminative combined kernel. Three merits are realized by DMKL. First, DMKL can achieve a substantial improvement in classification performance without strict limitation for selection of basic kernels. Second, the discriminating scales of a Gaussian kernel, the useful bands for classification, and the competitive sizes of spatial filters can be selected by ranking the corresponding weights, where the large weights correspond to the most relevant. Third, DMKL reduces the computational burden by requiring fewer support vectors. Experiments are conducted on two hyperspectral data sets and one multispectral data set. The corresponding experimental results demonstrate that the proposed algorithms can achieve the best performance with satisfactory computational efficiency for spectral image classification, compared with several state-of-the-art algorithms.
DOI: 10.1109/jstars.2015.2423278
发表时间: 2015-06
影响因子: 5.5
作者:
Sen Jia;Xiujun Zhang;Qingquan Li
通讯作者: Sen Jia;Xiujun Zhang;Qingquan Li
DOI: 10.1109/dicta.2008.42
发表时间: 2008-12
期刊: 2008 Digital Image Computing: Techniques and Applications
影响因子: --
作者:
Sen Jia;Y. Qian;Z. Ji
通讯作者: Sen Jia;Y. Qian;Z. Ji
DOI: 10.1007/s00500-014-1505-4
发表时间: 2016-12-01
期刊: SOFT COMPUTING
影响因子: 4.1
作者:
Jia, Sen;Xie, Yao;Zhu, Jiasong
通讯作者: Zhu, Jiasong
DOI: 10.1109/lgrs.2013.2273397
发表时间: 2014-03-01
影响因子: 4.8
作者:
Kim, Yongmin;Kim, Yongil
通讯作者: Kim, Yongil
DOI: 10.1080/014311699213622
发表时间: 1997
期刊: --
影响因子: --
作者:
Yang Hong;F. Meer;W. Bakker;Z. Tan
通讯作者: Yang Hong;F. Meer;W. Bakker;Z. Tan