A GENETIC ALGORITHM BASED FEATURE EXTRACTION TECHNIQUE FOR HYPERSPECTRAL IMAGERY

  • Ryu Byong Tae (School of Information and Communication Eng.) ;
  • Kim Choon-Woo (School of Information and Communication Eng.) ;
  • Kim Hakil (School of Information and Communication Eng.) ;
  • Lee Kyu Sung (Dept. of Geoinformatic Engineering Inha University)
  • Published : 2005.10.01

Abstract

Hyperspectral data consists of more than 200 spectral bands that are highly correlated. In order to utilize hyperspectral data for classification, dimensional reduction or feature extraction is desired. By applying feature extraction, computational complexity of classification can be reduced and classification accuracy may be improved. In this paper, a genetic algorithm based feature extraction technique is proposed. Measure from discriminant analysis is utilized as optimization criterion. A subset of spectral bands is selected by genetic algorithm. Dimension of feature space is further reduced by linear transformation. Feasibility of the proposed technique is evaluated with AVIRIS data.

Keywords