Unsupervised Spatial-spectral Hyperspectral Image Reconstruction and Clustering with Diffusion Geometry

TL;DR

This paper introduces DSIRC, an unsupervised algorithm that enhances hyperspectral image analysis by combining spatial reconstruction with diffusion geometry-based clustering, leading to improved segmentation accuracy.

Contribution

The work presents a novel unsupervised method that integrates spatial-spectral reconstruction with diffusion geometry for effective hyperspectral image clustering.

Findings

Significant noise reduction through shape-adaptive reconstruction.

Improved clustering accuracy over existing methods.

Effective identification of high-purity, high-density pixels as cluster exemplars.

Abstract

Hyperspectral images, which store a hundred or more spectral bands of reflectance, have become an important data source in natural and social sciences. Hyperspectral images are often generated in large quantities at a relatively coarse spatial resolution. As such, unsupervised machine learning algorithms incorporating known structure in hyperspectral imagery are needed to analyze these images automatically. This work introduces the Spatial-Spectral Image Reconstruction and Clustering with Diffusion Geometry (DSIRC) algorithm for partitioning highly mixed hyperspectral images. DSIRC reduces measurement noise through a shape-adaptive reconstruction procedure. In particular, for each pixel, DSIRC locates spectrally correlated pixels within a data-adaptive spatial neighborhood and reconstructs that pixel's spectral signature using those of its neighbors. DSIRC then locates high-density, high-purity pixels far in diffusion distance (a data-dependent distance metric) from other high-density, high-purity pixels and treats these as cluster exemplars, giving each a unique label. Non-modal pixels are assigned the label of their diffusion distance-nearest neighbor of higher density and purity that is already labeled. Strong numerical results indicate that incorporating spatial information through image reconstruction substantially improves the performance of pixel-wise clustering.