Joint bilateral filtering and spectral similarity-based sparse representation: A generic framework for effective feature extraction and data classification in hyperspectral imaging
Joint bilateral filtering and spectral similarity-based sparse representation: A generic framework for effective feature extraction and data classification in hyperspectral imaging
复制标题
联合双边滤波和基于光谱相似性的稀疏表示：高光谱成像中有效特征提取和数据分类的通用框架
DOI：
10.1016/j.patcog.2017.10.008
复制
发表时间：
2018-05-01
影响因子：
8
通讯作者：
Benediktsson, Jon Atli
中科院分区：
文献类型：
--
作者：
Qiao, Tong;Yang, Zhijing;Benediktsson, Jon Atli
高光谱图像的分类一直是一个具有挑战性的问题，在积极的研究多年，特别是由于极高的数据维数和有限数量的样本可用于训练。结果发现，高光谱图像分类可以普遍提高，只有当特征提取技术和分类器都解决了。本文提出了一种基于联合双边滤波和稀疏表示分类（SRC）的高光谱图像分类框架。通过采用第一主成分作为联合双边滤波器的引导图像，可以以最小的边缘模糊提取空间特征，从而提高带间图像的质量。由于这个原因，在这项工作中，联合双边滤波器的性能比传统的双边滤波器的性能更好。针对传统联合SRC方法的不足，提出了基于谱相似性的联合SRC（SS-JSRC）方法。通过将联合双边滤波和SS-JSRC结合在一起，所提出的分类框架的优越性被证明相对于HSI社区中常用的几种最先进的谱空间分类方法，具有更好的分类精度和Kappa系数。(C)2017爱思唯尔有限公司版权所有
Classification of hyperspectral images (HSI) has been a challenging problem under active investigation for years especially due to the extremely high data dimensionality and limited number of samples available for training. It is found that hyperspectral image classification can be generally improved only if the feature extraction technique and the classifier are both addressed. In this paper, a novel classification framework for hyperspectral images based on the joint bilateral filter and sparse representation classification (SRC) is proposed. By employing the first principal component as the guidance image for the joint bilateral filter, spatial features can be extracted with minimum edge blurring thus improving the quality of the band-to-band images. For this reason, the performance of the joint bilateral filter has shown better than that of the conventional bilateral filter in this work. In addition, the spectral similarity-based joint SRC (SS-JSRC) is proposed to overcome the weakness of the traditional JSRC method. By combining the joint bilateral filtering and SS-JSRC together, the superiority of the proposed classification framework is demonstrated with respect to several state-of-the-art spectral-spatial classification approaches commonly employed in the HSI community, with better classification accuracy and Kappa coefficient achieved. (C) 2017 Elsevier Ltd. All rights reserved.