Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios
This work addresses forensic analysis by improving classification accuracy for blood-like substances, but it is incremental as it builds on existing genetic algorithm methods.
The study tackled hyperspectral image classification of blood-like substances by applying genetic algorithms for model and band selection, showing that GA-based optimization reduces bands and creates accurate classifiers outperforming grid search, with results depending on access to similar test data during optimization.
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.