Hyperspectral Band Selection for Anomaly Detection: The Role of Data Gaussianity

Merav Huber-Lerner, Ofer Hadar, Stanley R. Rotman, Revital Huber-Shalem

Research output: Contribution to journalArticlepeer-review

18 Scopus citations


We evaluate the anomaly detection performance of a hyperspectral detection algorithm based on selecting specific bands of the hyperspectral cube. The best bands to be chosen are, as expected, based on the degree that the resulting target and background signatures differ from one another, which is determined by the target energy in the whitened space. In addition, we show that the closer the background distribution resembles a Gaussian model, the better the band performs in the detection algorithm. A comparison is made between choosing bands on the basis of their similarity to Gaussian distribution and one based on minimum variance. Examples are provided both on theoretical simulations and on experimental data.

Original languageEnglish
Article number7335561
Pages (from-to)732-743
Number of pages12
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Issue number2
StatePublished - 1 Feb 2016


  • Gaussianity measure
  • Reed Xiaoli (RX) algorithm
  • hyperspectral imaging (HSI)
  • target energy

ASJC Scopus subject areas

  • Computers in Earth Sciences
  • Atmospheric Science


Dive into the research topics of 'Hyperspectral Band Selection for Anomaly Detection: The Role of Data Gaussianity'. Together they form a unique fingerprint.

Cite this