Work

Semantic-Guided Kernel Low-Rank Sparse Preserving Projections for Hyperspectral Image Dimensionality Reduction and Classification

Year: 2026

Type: article

Abstract: Hyperspectral images present significant challenges for conventional dimensionality reduction methods due to their high dimensionality, spectral redundancy, and complex spatial–spatial dependencies. While kernel-based sparse representation methods have shown promise in handling spectral non-linearities, they often fail to preserve spatial consistency and semantic discriminability during feature transformation. To address these limitations, we propose a novel semantic-guided kernel low-rank sparse preserving projection (SKLSPP) framework. Unlike previous approaches that primarily focus on spectral information, our method introduces three key innovations: a semantic-aware kernel representation that maintains discriminability through label constraints, a spatially adaptive manifold regularization term that preserves local pixel affinities in the reduced subspace, and an efficient optimization framework that jointly learns sparse codes and projection matrices. Extensive experiments on benchmark datasets demonstrate that SKLSPP achieves superior performance compared to state-of-the-art methods, showing enhanced feature discrimination, reduced redundancy, and improved robustness to noise while maintaining spatial coherence in the dimensionality-reduced features.

Source: Applied Sciences

DOI: 10.3390/app16010561

Authors: Junjun Li, Jinyan Hu, Lin Huang, Chao Hu, Meinan Zheng

Institution: Anhui University of Science and Technology

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,896

Funders: National Natural Science Foundation of China, Anhui University, Anhui University of Science and Technology