Hyperspectral Image Classification via Fusing Correlation Coefficient and Joint Sparse Representation

Hyperspectral Image Classification via Fusing Correlation Coefficient and Joint Sparse Representation
复制标题

通过融合相关系数和联合稀疏表示的高光谱图像分类

DOI:
10.1109/lgrs.2017.2787338
复制
发表时间:
2018-01
影响因子:
4.8
通讯作者:
Wu Jianhui
Wu Jianhui
中科院分区:
工程技术2区
文献类型:
--
作者:
Tu Bing;Zhang Xiaofei;Kang Xudong;Zhang Guoyun;Wang Jinping;Wu Jianhui

文献摘要

参考文献

被引文献

相似文献

基于联合稀疏表示(JSR)的分类器假设局部窗口中的像素可以由训练样本构建的字典联合稀疏地表示。每个像素的类别标签可以根据表示残差来确定。然而,一旦每个像素的局部窗口包含来自不同类别的像素,JSR分类器的性能可能会严重下降。由于相关系数(CC)能够有效地度量不同像素之间的光谱相似性,本文提出了一种融合CC和JSR的分类方法,该方法试图利用训练样本和测试样本之间的类内相似性,同时减少类间干扰。首先,计算训练样本和测试样本之间的CCS。然后,使用基于JSR的分类器来获取不同像素的表示残差。最后,引入正则化参数$\lambda$来实现JSR和CC之间的平衡。在印第安松数据集上的实验结果表明,与其他广泛使用的分类器相比,该方法具有较好的性能。
The joint sparse representation (JSR)-based classifier assumes that pixels in a local window can be jointly and sparsely represented by a dictionary constructed by the training samples. The class label of each pixel can be decided according to the representation residual. However, once the local window of each pixel includes pixels from different classes, the performance of the JSR classifier may be seriously decreased. Since correlation coefficient (CC) is able to measure the spectral similarity among different pixels efficiently, this letter proposes a new classification method via fusing CC and JSR, which attempts to use the within-class similarity between training and test samples while decreasing the between-class interference. First, the CCs among the training and test samples are calculated. Then, the JSR-based classifier is used to obtain the representation residuals of different pixels. Finally, a regularization parameter $\lambda $ is introduced to achieve the balance between the JSR and the CC. Experimental results obtained on the Indian Pines data set demonstrate the competitive performance of the proposed approach with respect to other widely used classifiers.
DOI: 10.1109/tgrs.2012.2201730
发表时间: 2013-01-01
影响因子: 8.2
作者:
Chen, Yi;Nasrabadi, Nasser M.;Tran, Trac D.
通讯作者: Tran, Trac D.
一种新的高光谱遥感影像稀疏子空间聚类算法
DOI: 10.1109/lgrs.2016.2625200
发表时间: 2017
影响因子: 4.8
作者:
Han Zhai;Hongyan Zhang;Liangpei Zhang;Pingxiang Li;Antonio Plaza
通讯作者: Antonio Plaza
用于高光谱图像的基于内核融合表示的分类器
DOI: 10.1109/lgrs.2017.2671852
发表时间: 2017-03
影响因子: 4.8
作者:
Gan Le;Du Peijun;Xia Junshi;Meng Yaping
通讯作者: Meng Yaping
具有边缘保留滤波的光谱空间高光谱图像分类
DOI: 10.1109/tgrs.2013.2264508
发表时间: 2014-05-01
影响因子: 8.2
作者:
Kang, Xudong;Li, Shutao;Benediktsson, Jon Atli
通讯作者: Benediktsson, Jon Atli
用于从城市高光谱图像中提取和分类目标的自适应均值漂移分析方法
DOI: 10.1109/tgrs.2008.2002577
发表时间: 2008-12-01
影响因子: 8.2
作者:
Huang, Xin;Zhang, Liangpei
通讯作者: Zhang, Liangpei