Hyperspectral Image Classification with Support Vector Machines on Kernel Distribution Embeddings

TL;DR

This paper introduces a novel hyperspectral image classification method that combines spatial and spectral data using kernel distribution embeddings and support vector machines, achieving improved accuracy with reduced computational complexity.

Contribution

It presents a new framework that represents pixel neighborhoods as distributions in RKHS and integrates this with spectral information for enhanced classification performance.

Findings

Strong performance on hyperspectral datasets

Outperforms state-of-the-art methods

Reduced computational complexity

Abstract

We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data. The introduced method relies on a recently proposed framework for learning on distributions -- by representing them with mean elements in reproducing kernel Hilbert spaces (RKHS) and formulating a classification algorithm therein. In particular, we associate each pixel to an empirical distribution of its neighbouring pixels, a judicious representation of which in an RKHS, in conjunction with the spectral information contained in the pixel itself, give a new explicit set of features that can be fed into a suite of standard classification techniques -- we opt for a well-established framework of support vector machines (SVM). Furthermore, the computational complexity is reduced via random Fourier features formalism. We study the consistency and the convergence rates of the proposed method and the experiments demonstrate strong performance on hyperspectral data with gains in comparison to the state-of-the-art results.