Comparison of VCA and GAEE algorithms for Endmember Extraction

TL;DR

This paper compares genetic algorithms, including a novel IVF-enhanced version, with existing methods like VCA for endmember extraction in hyperspectral images, demonstrating improved accuracy and performance.

Contribution

It introduces a genetic algorithm with IVF module for endmember extraction and compares it with VCA and traditional algorithms, showing superior results.

Findings

Proposed genetic algorithms outperform VCA and traditional methods.

IVF module enhances the optimization process.

Experimental results confirm improved accuracy and efficiency.

Abstract

Endmember Extraction is a critical step in hyperspectral image analysis and classification. It is an useful method to decompose a mixed spectrum into a collection of spectra and their corresponding proportions. In this paper, we solve a linear endmember extraction problem as an evolutionary optimization task, maximizing the Simplex Volume in the endmember space. We propose a standard genetic algorithm and a variation with In Vitro Fertilization module (IVFm) to find the best solutions and compare the results with the state-of-art Vertex Component Analysis (VCA) method and the traditional algorithms Pixel Purity Index (PPI) and N-FINDR. The experimental results on real and synthetic hyperspectral data confirms the overcome in performance and accuracy of the proposed approaches over the mentioned algorithms.