Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios

TL;DR

This paper explores using genetic algorithms to optimize hyperspectral image classification models for blood-like substances, demonstrating improved accuracy and band reduction in forensic scenarios with both same and different image data.

Contribution

It introduces a GA-based approach for band selection and model optimization in hyperspectral classification, outperforming traditional grid search methods in forensic applications.

Findings

GA reduces the number of spectral bands needed.

GA-optimized classifiers outperform grid search models.

Access to similar test data during optimization improves accuracy.

Abstract

This study is focused on applying genetic algorithms (GA) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectra differences. In our experiments we compare GA with a classic model optimisation through grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that during model optimisation it has access to examples similar to test data. We illustrate this with experiment highlighting the importance of a validation set.