期刊
DISPLAYS
卷 74, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.displa.2022.102218
关键词
Hyperspectral cubes reconstruction; Computed tomography imaging spectrometer (CTIS) images; Convolutional neural networks
类别
资金
- Independent Research Fund Denmark [DFF 6108-00623]
- Vil-lum Foundation
- Danish Ministry of Higher Education and Science (CenSec)
- Innovation Fund Denmark (IFD) [1044-00053B]
- eScience center at SDU
In this study, a novel method utilizing CNNs is proposed for reconstructing hyperspectral cubes from CTIS images. The constructed CNNs demonstrate higher precision and shorter reconstruction time compared to existing algorithms. Furthermore, the network can handle different types of real-world images simultaneously.
A novel method, utilizing convolutional neural networks (CNNs), is proposed to reconstruct hyperspectral cubes from computed tomography imaging spectrometer (CTIS) images. Current reconstruction algorithms are usually subject to long reconstruction times and mediocre precision in cases of a large number of spectral channels. The constructed CNNs deliver higher precision and shorter reconstruction time than a sparse expectation maximization algorithm. In addition, the network can handle two different types of real-world images at the same fime-specifically ColorChecker and carrot spectral images are considered. This work paves the way toward real-time reconstruction of hyperspectral cubes from CTIS images.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据