Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Addressing the label-scarcity problem in hyperspectral classification, this work develops a graph-based semi-supervised framework using a tripartite composite kernel that explicitly decouples pairwise coordinate distances from local spectral-spatial context. Disentangling geometric spatial proximity from patch-level spectral statistics enforces solution smoothness across the image graph without blurring distinct spectral signatures. Empirical evaluations on real-world hyperspectral benchmarks show consistent classification improvements over standard dual-kernel baselines while isolating the relative functional contributions of spectral versus spatial priors.
Standard hyperspectral models conflate contextual neighborhood statistics with pure physical distance, but isolating relative pixel coordinates into a dedicated third kernel yields superior graph-based classification under strict label constraints.
The classification of hyperspectral images (HIs) still presents several challenges. One of them is the difficulty to obtain a large set of labeled samples to train the classifier. Semi-supervised learning methods have received much attention recently, as they require the initial labeling of a reduced number of image pixels and lead to very good results for practical application. One of the open problems in graph-based semi-supervised HI classification is the need to consider relative spatial relationship between pixels in the image to improve the smoothness of the solution. Kernel-based approaches using composite kernels have led to very good results, in which one kernel addresses the spectral properties of the pixels while a second kernel addresses some spatial properties. Most available solutions employ a spectral-spatial kernel which considers the spectral properties of a spatial region about each pixel. This work proposes a composite kernel approach that includes a third kernel dealing exclusively with the relative spatial position of the pixels. Experiments with real HI images show that the use of the new spatial kernel has led to improved classification results when compared to those previously reported in the literature. These results also shed some light on the relative contributions of the spectral and spectral-spatial kernels in semi-supervised HI classification.