...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Kernel Fused Representation-Based Classifier for Hyperspectral Imagery
【24h】

Kernel Fused Representation-Based Classifier for Hyperspectral Imagery

机译：基于核融合表示的高光谱图像分类器

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this letter, we propose a kernel fused representation-based classifier (KFRC) for hyperspectral images (HSIs), which combines sparse representation (SR) and collaborative representation (CR) into a unified kernel representation-based classification framework. First, we present two individual kernel methods, i.e., kernel SR (KSR) and kernel CR (KCR), which kernelize the representation methods by projecting the samples into a high-dimensional kernel space to improve the samples separability between different classes. Once obtaining the two kernel representation coefficients, KFRC attempts to achieve a balance between KSR and KCR via an adjusting parameter theta in the kernel residual domain. Subsequently, the class label of each test sample is determined by the minimum residual for each class. Experimental results on two HSIs demonstrate the proposed kernel fused method performs better than the other state-of-the-art representation-based classifiers.
机译：在这封信中，我们提出了一种用于高光谱图像（HSI）的基于核融合表示的分类器（KFRC），该分类器将稀疏表示（SR）和协作表示（CR）组合成一个统一的基于核表示的分类框架。首先，我们介绍了两种单独的内核方法，即内核SR（KSR）和内核CR（KCR），它们通过将样本投影到高维内核空间中来改进表示方法，以提高不同类之间的样本可分离性。一旦获得两个内核表示系数，KFRC就会尝试通过内核残差域中的调整参数theta在KSR和KCR之间取得平衡。随后，每个测试样品的类别标签由每个类别的最小残留量确定。在两个HSI上的实验结果表明，所提出的核融合方法比其他最新的基于表示的分类器性能更好。

著录项

  • 来源
    《IEEE Geoscience and Remote Sensing Letters》 |2017年第5期|684-688|共5页
  • 作者

    Le Gan; Peijun Du; Junshi Xia; Yaping Meng;

  • 作者单位

    Key Laboratory for Satellite Mapping Technology and Applications of National Administration of Surveying, Mapping and Geoinformation of China, Nanjing University, Nanjing, China;

    Key Laboratory for Satellite Mapping Technology and Applications of National Administration of Surveying, Mapping and Geoinformation of China, Nanjing University, Nanjing, China;

    Research Center for Advanced Science and Technology, The University of Tokyo, Tokyo, Japan;

    Key Laboratory for Satellite Mapping Technology and Applications of National Administration of Surveying, Mapping and Geoinformation of China, Nanjing University, Nanjing, China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Kernel; Dictionaries; Training; Hyperspectral imaging; Collaboration; Gallium nitride;

    机译：内核;词典;培训;高光谱成像;协作;氮化镓;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号