Unsupervised Spatial-spectral Hyperspectral Image Reconstruction and Clustering with Diffusion Geometry
This work addresses the need for unsupervised machine learning algorithms to analyze large quantities of coarse-resolution hyperspectral images in natural and social sciences, representing an incremental advancement.
The paper tackles the problem of partitioning highly mixed hyperspectral images by introducing the DSIRC algorithm, which reduces noise through shape-adaptive reconstruction and uses diffusion geometry for clustering, resulting in substantial performance improvements in pixel-wise clustering.
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.