Zhang Jing, Geng Wenhao, Liang Xi, Li Jiafeng, Zhuo Li, Zhou Qianlan
Appl Opt. 2017 Jun 1;56(16):4785-4796. doi: 10.1364/AO.56.004785.
Although many content-based image retrieval systems have been developed, few studies have focused on hyperspectral remote sensing images. In this paper, a hyperspectral remote sensing image retrieval system based on spectral and texture features is proposed. The main contributions are fourfold: (1) considering the "mixed pixel" in the hyperspectral image, endmembers as spectral features are extracted by an improved automatic pixel purity index algorithm, then the texture features are extracted with the gray level co-occurrence matrix; (2) similarity measurement is designed for the hyperspectral remote sensing image retrieval system, in which the similarity of spectral features is measured with the spectral information divergence and spectral angle match mixed measurement and in which the similarity of textural features is measured with Euclidean distance; (3) considering the limited ability of the human visual system, the retrieval results are returned after synthesizing true color images based on the hyperspectral image characteristics; (4) the retrieval results are optimized by adjusting the feature weights of similarity measurements according to the user's relevance feedback. The experimental results on NASA data sets can show that our system can achieve comparable superior retrieval performance to existing hyperspectral analysis schemes.
尽管已经开发了许多基于内容的图像检索系统，但很少有研究关注高光谱遥感图像。本文提出了一种基于光谱和纹理特征的高光谱遥感图像检索系统。主要贡献有四点：（1）考虑高光谱图像中的“混合像素”，通过改进的自动像素纯度指数算法提取作为光谱特征的端元，然后用灰度共生矩阵提取纹理特征；（2）为高光谱遥感图像检索系统设计相似性度量，其中光谱特征的相似性用光谱信息散度和光谱角匹配混合度量来衡量，纹理特征的相似性用欧几里得距离来衡量；（3）考虑到人类视觉系统的能力有限，根据高光谱图像特征合成真彩色图像后返回检索结果；（4）根据用户的相关反馈调整相似性度量的特征权重，对检索结果进行优化。在NASA数据集上的实验结果表明，我们的系统能够实现与现有高光谱分析方案相当的卓越检索性能。
