Hyperspectral Images Classification and Dimensionality Reduction using spectral interaction and SVM classifier

TL;DR

This paper introduces a novel spectral interaction-based filter method combined with SVM for effective dimensionality reduction and accurate classification of hyperspectral images, demonstrated on multiple datasets.

Contribution

The paper proposes the Max Relevance Max Synergy (MRMS) algorithm, a new filter approach that optimizes band selection by evaluating spectral relevance, redundancy, and synergy for hyperspectral image classification.

Findings

MRMS outperforms existing band selection methods in accuracy.

The approach reduces computational complexity and improves classification robustness.

Experimental results on three datasets validate the effectiveness of MRMS.

Abstract

Over the past decades, the hyperspectral remote sensing technology development has attracted growing interest among scientists in various domains. The rich and detailed spectral information provided by the hyperspectral sensors has improved the monitoring and detection capabilities of the earth surface substances. However, the high dimensionality of the hyperspectral images (HSI) is one of the main challenges for the analysis of the collected data. The existence of noisy, redundant and irrelevant bands increases the computational complexity, induce the Hughes phenomenon and decrease the target's classification accuracy. Hence, the dimensionality reduction is an essential step to face the dimensionality challenges. In this paper, we propose a novel filter approach based on the maximization of the spectral interaction measure and the support vector machines for dimensionality reduction and classification of the HSI. The proposed Max Relevance Max Synergy (MRMS) algorithm evaluates the relevance of every band through the combination of spectral synergy, redundancy and relevance measures. Our objective is to select the optimal subset of synergistic bands providing accurate classification of the supervised scene materials. Experimental results have been performed using three different hyperspectral datasets: "Indiana Pine", "Pavia University" and "Salinas" provided by the "NASA-AVIRIS" and the "ROSIS" spectrometers. Furthermore, a comparison with the state of the art band selection methods has been carried out in order to demonstrate the robustness and efficiency of the proposed approach. Keywords: Hyperspectral images, remote sensing, dimensionality reduction, classification, synergic, correlation, spectral interaction information, mutual inform