Abstract
Hyperspectral imagery (HSI) clustering aims to assign pixel-wise data with large amount of spectral bands into different groups, where each group indicates one of land-cover objects existed in HSI. Without available label information in clustering task, the clustering performance heavily depends on the reliability of unsupervised feature learned from HSI. Nevertheless,when HSI data are corrupted with noise,the conventional feature learning methods often failed. To address this problem, in this paper, a dual graph-based robust unsupervised feature extraction framework for HSI is proposed to realize reliable clustering. Firstly, low-rank reconstruction and projected learning are incorporated into the proposed framework to improve the data quality and obtain their robust structures. Then, a novel learning schemes is designed to learn two reliable graphs from the above robust structures respectively. We show that the scheme can reveals the latent similarity relationships while removing the noise influence. Meanwhile, the two reliable graphs are also integrated into a comprehensive graph with consistent constraint. At last, a joint learning framework is proposed, in which the data quality improvement, reliable graphs and consistent graph are learned iteratively to benefit from each other. After that, the normalized cut technique is applied to the learned consistent graph to obtain the final unsupervised feature. Several experiments are conducted on the two public HIS datasets to show advantage of our proposed method against the existing methods.
Highlights
Hyperspectral image clustering is a fundamental issue in Hyperspectral imagery (HSI) analysis, which can be defined as the process of grouping each pixel into its corresponding group [1]–[3]
The graph regularization constraint is applied to NMF to learn the unsupervised local structure feature, which shows some improvement over the conventional NMF and ONMF in HSIs Clustering
In this paper, a robust unsupervised feature leaning method via dual graphs is proposed for reliable clustering on HSIs
Summary
Hyperspectral image clustering is a fundamental issue in HSI analysis, which can be defined as the process of grouping each pixel into its corresponding group [1]–[3]. The learning-based unsupervised feature extraction approaches attract much attention and achieves lots of successful applications in many areas by learning the low-dimensional projection space from unlabeled data themselves [14]–[17]. An orthogonal graph-regularized NMF method was presented in [26] In this method, the graph regularization constraint is applied to NMF to learn the unsupervised local structure feature, which shows some improvement over the conventional NMF and ONMF in HSIs Clustering. Graph-based unsupervised feature learning approaches have promising results in HSIs clustering problem than the conventional manifold learning methods. Towards the two issues, we proposed a novel graph-based robust unsupervised feature learning method for more reliability HSIs clustering.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
