Improvement of Hyperspectral Classification Accuracy with Limited Training Data Using Meanshift Segmentation


ÖZDEMİR O. B., ÇETİN Y.

22nd IEEE Signal Processing and Communications Applications Conference (SIU), Trabzon, Turkey, 23 - 25 April 2014, pp.1794-1797 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Trabzon
  • Country: Turkey
  • Page Numbers: pp.1794-1797
  • Keywords: Hyperspectral Classification, Support Vector Machines, Meanshift Segmentation, Pattern Search
  • Middle East Technical University Affiliated: Yes

Abstract

In this study, the performance of hyperspectral classification algorithms with limited training data investigated. Support Vector Machines (SVM) with Gaussian kernel is used. Principle Component Analysis (PCA) is employed for preprocessing and meanshift segmentation is used to incorporate spatial information with spectral information to observe the effect spatial information. Pattern search algorithm is used to optimize meanshift segmentation parameters. The performance of the algorithm is demonstrated on high resolution Pavia University hyperspectral data.