Spectral region identification versus individual channel selection in supervised dimensionality reduction of hyperspectral image data

Abstract

Hyperspectral images may be applied to classify objects in a scene. The redundancy in hyperspectral data implies that fewer spectral features might be sufficient for discriminating the objects captured in a scene. The availability of labeled classes of several areas in a scene paves the way for a supervised dimensionality reduction, i.e., using a discrimination measure between the classes in a scene to select spectral features. We show that averaging adjacent spectral channels and using wider spectral regions yield a better class separability than the selection of individual channels from the original hyperspectral dataset. We used a method named spectral region splitting (SRS), which creates a new feature space by averaging neighboring channels. In addition to the common benefits of channel selection methods, the algorithm constructs wider spectral regions when it is useful. Using different class separability measures over various datasets resulted in a better discrimination between the classes than the best-selected channels using the same measure. The reason is that the wider spectral regions led to a reduction in intraclass distances and an improvement in class discrimination. The overall classification accuracy of two hyperspectral scenes gave an increase of about two-percent when using the spectral regions determined by applying SRS.