Comparison of Traditional and Recent Unsupervised Band Selection Approaches in Hyperspectral Images


KARACA A. C. , Gullu M. K.

24th Signal Processing and Communication Application Conference (SIU), Zonguldak, Turkey, 16 - 19 May 2016, pp.785-788 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/siu.2016.7495857
  • City: Zonguldak
  • Country: Turkey
  • Page Numbers: pp.785-788
  • Keywords: Band selection, dimensionality reduction, hyperspectral imaging, CLASSIFICATION, ACCURACY

Abstract

In this paper, well-known traditional band selection methods which are used in hyperspectral imaging, namely, Maximum-Variance Principal Component Analysis (MVPCA), Maximum-SNR Principal Component Analysis (MSNRPCA), k-means, k-medoids, and recently proposed Automatic Band Selection (ABS) and Band Column Selection (BCS) approaches are compared. To assess the band selection performance of the methods, the change of classification performance by the number of selected bands is used. Performances of the methods are evaluated on three hyperspectral data sets and obtained results are compared in this paper.