# Fusion of heterogeneous bands and kernels in hyperspectral image processing

## TL;DR

This paper introduces a flexible hyperspectral image processing method that combines band grouping, diverse feature extraction, and multiple kernel learning to improve classification performance on benchmark datasets.

## Contribution

It extends visual clustering algorithms for supervised hyperspectral learning and proposes a novel feature fusion approach using different proximity metrics and kernels.

## Key findings

- Heterogeneous features and kernels generally improve performance.
- Contiguous or non-contiguous band grouping effectiveness is application-specific.
- The method outperforms related approaches on benchmark datasets.

## Abstract

Hyperspectral imaging is a powerful technology that is plagued by large dimensionality. Herein, we explore a way to combat that hindrance via non-contiguous and contiguous (simpler to realize sensor) band grouping for dimensionality reduction. Our approach is different in the respect that it is flexible and it follows a well-studied process of visual clustering in high-dimensional spaces. Specifically, we extend the improved visual assessment of cluster tendency and clustering in ordered dissimilarity data unsupervised clustering algorithms for supervised hyperspectral learning. In addition, we propose a way to extract diverse features via the use of different proximity metrics (ways to measure the similarity between bands) and kernel functions. The discovered features are fused with $l_{\infty}$-norm multiple kernel learning. Experiments are conducted on two benchmark datasets and our results are compared to related work. These datasets indicate that contiguous or not is application specific, but heterogeneous features and kernels usually lead to performance gain.