19 November 2004 Hyperspectral ratio feature selection: agricultural product inspection example
Author Affiliations +
We describe a fast method for dimensionality reduction and feature selection of ratio features for classification in hyperspectral data. The case study chosen is to discriminate internally damaged almond nuts from normal ones. For this case study, we find that using the ratios of the responses in several wavebands provides better features than a subset of waveband responses. We find that use of the Euclidean Minimum Distance metric gives slightly better results than the more conventional Spectral Angle Mapper distance metric in a nearest neighbor classifier.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Songyot Nakariyakul, Songyot Nakariyakul, David Casasent, David Casasent, } "Hyperspectral ratio feature selection: agricultural product inspection example", Proc. SPIE 5587, Nondestructive Sensing for Food Safety, Quality, and Natural Resources, (19 November 2004); doi: 10.1117/12.568237; https://doi.org/10.1117/12.568237

Back to Top