Multi-spectral Image Denoising with Shared Dictionaries and Low-rank Representation
Multi-spectral Image Denoising with Shared Dictionaries and Low-rank Representation
复制标题
DOI：
10.1109/icassp.2019.8682281
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Xiao Gong;Wei Chen
中科院分区：
文献类型：
--
作者：
Xiao Gong;Wei Chen
多光谱图像作为一个三阶张量，具有几十个光谱波段，能够更真实地反映真实的场景。然而，在感知过程中，MSI经常被噪声破坏，这会降低更高级别的分类和识别任务的性能。在本文中，我们提出了一种新的张量字典学习方法的MSI去噪，其中两个共享的字典学习MSI组相似的块在空间域和频谱域，分别。此外，我们在学习的字典下对MSI组的表示实施低等级结构，这捕获了MSI中的潜在结构。我们的实验表明，该方法实现了最好的性能与国家的最先进的方法相比。
As a 3-order tensor, a multi-spectral image (MSI) has dozens of spectral bands, which can deliver more faithful representation for real scenes. However, MSIs are often corrupted by noise in the sensing process, which deteriorates the performance of higher-level classification and recognition tasks. In this paper, we propose a novel tensor dictionaries learning method for MSI denoising, where two shared dictionaries are learned from MSI groups of similar blocks in the spatial domain and the spectral domain, respectively. In addition, we enforce a low rank structure for the representations of MSI groups under the learned dictionaries, which captures the latent structure in MSIs. Our experiments demonstrate that the proposed method achieves the best performance in comparison with the state-of-the-art methods.