Information content vs. class separabilityat optimal spectral regions

S. E.Hosseini Aria, M. Menenti, B. G.H. Gorte

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

24 Downloads (Pure)

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.

Original languageEnglish
Title of host publication2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2013
PublisherIEEE
Number of pages4
Volume2013-June
ISBN (Electronic)9781509011193
DOIs
Publication statusPublished - 23 Oct 2017
Event5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing - Gainesville, United States
Duration: 26 Jun 201328 Jun 2013
Conference number: 5

Conference

Conference5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing
Abbreviated titleWHISPERS 2013
CountryUnited States
CityGainesville
Period26/06/1328/06/13

Keywords

  • Hyperspectral
  • Information content
  • Separability
  • Spectral region

Fingerprint Dive into the research topics of 'Information content vs. class separabilityat optimal spectral regions'. Together they form a unique fingerprint.

Cite this