Robust Core Tensor Dictionary Learning with Modified Gaussian Mixture Model for Multispectral Image Restoration
Robust Core Tensor Dictionary Learning with Modified Gaussian Mixture Model for Multispectral Image Restoration
复制标题
用于多光谱图像恢复的改进高斯混合模型的鲁棒核心张量字典学习
DOI：
10.32604/cmc.2020.09975
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Fu Peng
中科院分区：
文献类型：
--
作者：
Geng Leilei;Cui Chaoran;Guo Qiang;Niu Sijie;Zhang Guoqing;Fu Peng
多光谱遥感图像（MS-RSI）由于各种硬件条件的限制，使得现有多光谱相机的成像质量下降。本文提出了一种新的核心张量字典学习方法，采用鲁棒的修改高斯混合模型进行MS-RSI恢复。首先用三阶张量对多光谱图像进行建模，并对张量进行高阶奇异值分解。然后将MS-RSI恢复问题转化为最小稀疏核张量估计问题。为了提高核张量编码的准确性，利用图像的稀疏分布先验，将基于稳健修正高斯混合模型的核张量估计引入到该模型中。将该算法应用于MS-RSI图像恢复，实验结果表明，该算法能够更好地恢复图像纹理的清晰度，并且在主观图像质量和视觉感知方面都优于现有的几种最先进的多光谱图像恢复方法。
: The multispectral remote sensing image (MS-RSI) is degraded existing multi-spectral camera due to various hardware limitations. In this paper, we propose a novel core tensor dictionary learning approach with the robust modified Gaussian mixture model for MS-RSI restoration. First, the multispectral patch is modeled by three-order tensor and high-order singular value decomposition is applied to the tensor. Then the task of MS-RSI restoration is formulated as a minimum sparse core tensor estimation problem. To improve the accuracy of core tensor coding, the core tensor estimation based on the robust modified Gaussian mixture model is introduced into the proposed model by exploiting the sparse distribution prior in image. When applied to MS-RSI restoration, our experimental results have shown that the proposed algorithm can better reconstruct the sharpness of the image textures and can outperform several existing state-of-the-art multispectral image restoration methods in both subjective image quality and visual perception.
登录
查看更多内容
DOI：
10.1109/icassp.2019.8682281
发表时间：
2019-05
期刊：
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子：
--
作者：
Xiao Gong;Wei Chen
通讯作者：
Xiao Gong;Wei Chen
影响因子：
1.3
作者：
Oktay Canbaz;Önder Gürsoy;A. Gökce
通讯作者：
Oktay Canbaz;Önder Gürsoy;A. Gökce
DOI：
10.1016/j.cageo.2017.11.006
发表时间：
2018-02
期刊：
Comput. Geosci.
影响因子：
--
作者：
Pedro A. A. Penna-Pedro-A.-A.-Penna-35518717;N. Mascarenhas
通讯作者：
Pedro A. A. Penna-Pedro-A.-A.-Penna-35518717;N. Mascarenhas
DOI：
10.1007/s10586-018-1772-4
发表时间：
2019-05-01
影响因子：
4.4
作者：
Chen, Yuantao;Xiong, Jie;Zuo, Jingwen
通讯作者：
Zuo, Jingwen
影响因子：
2
作者：
Fatma Mallouli;Atef Masmoudi;A. Masmoudi;M. Abid
通讯作者：
Fatma Mallouli;Atef Masmoudi;A. Masmoudi;M. Abid