Kent Mixture Model for Hyperspectral Clustering via Cosine Pixel Coordinates on Spherical Manifolds

Modern hyperspectral imaging sensor technology provides detailed spectral and spatial in-formation that enables precise analysis of land cover usage. From a research point of view, traditional widely used statistical models are often limited in the sense that they do not in-corporate some of the useful angle information contained in the feature vectors, and hence alternative modeling methods are required. In the study to be presented, the use of cosine angle information and its embedding onto a spherical manifold is investigated. The trans-formation of hyperspectral images onto a unit hyperspherical manifold is achieved by using the recently proposed spherical local embeddings approach. Spherical local embeddings is a method that computes high-dimensional local neighborhood preserving coordinates of data on constant curvature manifolds. We further develop a novel Kent mixture model for unsu-pervised classification of embedded cosine pixel coordinates. A Kent distribution is one of the natural models for multivariate data on a spherical manifold. Parameters for the mode