Print Email Facebook Twitter Information content vs. class separabilityat optimal spectral regions Title Information content vs. class separabilityat optimal spectral regions Author Hosseini Aria, S.E. (TU Delft Optical and Laser Remote Sensing) Menenti, M. (TU Delft Optical and Laser Remote Sensing) Gorte, B.G.H. (TU Delft Optical and Laser Remote Sensing) Date 2017-10-23 Abstract One of the main steps in hyperspectral image classification is the selection of bands that provide the best separability among classes. It is usually understood that the selected bands for classification must contain a large amount of information, and the correlation among selected bands should be small to avoid redundancy. At the same time for optimal classification, class separability should be at maximum value. The question arises whether the most informative spectral regions are really the same as the most discriminant ones for a given set of classes. Answering the question, we developed a new method named Spectral Region Splitting (SRS) to identify interesting spectral regions. This article concludes that the optimal informative and the optimal separable spectral regions are not identical. Furthermore, the cause of the difference is proven theoretically. Subject HyperspectralInformation contentSeparabilitySpectral region To reference this document use: http://resolver.tudelft.nl/uuid:6907bfba-5969-47b3-a15f-93964e2cfed8 DOI https://doi.org/10.1109/WHISPERS.2013.8080747 Publisher IEEE ISBN 9781509011193 Source 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013, 2013-June Event 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2013-06-26 → 2013-06-28, Gainesville, United States Part of collection Institutional Repository Document type conference paper Rights © 2017 S.E. Hosseini Aria, M. Menenti, B.G.H. Gorte Files PDF 08080747.pdf 291.75 KB Close viewer /islandora/object/uuid:6907bfba-5969-47b3-a15f-93964e2cfed8/datastream/OBJ/view