Hyperspectral Image Classification Using Iterative Auto-Weighted Dimension Reduction


SAKARYA U.

2022 IEEE Mediterranean and Middle-East Geoscience and Remote Sensing Symposium, M2GARSS 2022, Virtual, Online, Turkey, 7 - 09 March 2022, pp.94-97 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/m2garss52314.2022.9840287
  • City: Virtual, Online
  • Country: Turkey
  • Page Numbers: pp.94-97
  • Keywords: auto-weighted local discriminant analysis, dimension reduction, Hyperspectral image classification
  • Yıldız Technical University Affiliated: Yes

Abstract

© 2022 IEEE.In hyperspectral image classification task, achieving suitable dimension reduction is important to obtain desired classification performance. There are dozens of approaches to achieve this process. In this paper, a supervised auto-weighted dimension reduction method is applied on hyperspectral images for classification purposes. The proposed method examines auto-weighted condition with a view to analyzing the effects on hyperspectral images. Comparative experimental studies are realized in order to demonstrate the advantage and disadvantage of the used method.