Anchor-Level Spectral–Spatial Graph Clustering for Hyperspectral Images

Hyperspectral image (HSI) clustering aims to partition pixels into distinct clusters by leveraging spectral and spatial features, thereby providing crucial support for the interpretation and information extraction of hyperspectral data. However, due to high spectral variability, complex spatial distribution, and noise interference, HSI clustering still faces considerable challenges. Graph-based clustering represents a prominent learning framework and achieves competitive performance on HSI analysis. However, most existing methods ignore spatial information and suffer from high computational cost, rendering them incapable of effectively dealing with large-scale HSIs. To address the aforementioned challenges, this paper proposes an anchor-level spectral–spatial graph clustering (ASSGC) model for HSIs. The proposed ASSGC employs a band-wise median strategy within each superpixel to generate representative anchors to suppress noise and outlier effects. A novel distance metric is designed to integrate spectral features and spatial positions to effectively identify neighbors and construct a spectral–spatial joint affinity matrix at the anchor-level, thereby reducing computational burden and memory consumption. Subsequently, spectral clustering is applied to obtain anchor labels, which are propagated to the corresponding superpixels to achieve full-image clustering. Experiments on four HSI datasets yield ACC of 64.13% on Indian Pines, 71.33% on Pavia University, 87.86% on Salinas, and 99.23% on Salinas A, demonstrating that the proposed ASSGC outperforms several existing state-of-the-art methods while maintaining low time complexity.