Loading...

Dimension reduction of remote sensing images by incorporating spatial and spectral properties

Dianat, R ; Sharif University of Technology

460 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.aeue.2009.10.001
  3. Abstract:
  4. A new and efficient dimension reduction method is introduced in this paper. The proposed method, almost the same as the well-known principal component analysis (PCA) method, enjoys the properties of uncorrelatedness of resulting components and orthogonality of transform coefficients. In addition, by incorporating spatial and spectral properties among image pixels, the method obtains more accurate classification results with less computational cost
  5. Keywords:
  6. Classification results ; Computational costs ; Dimension reduction ; Dimension reduction method ; Image pixels ; Orthogonality ; Remote sensing images ; Spectral properties ; Transform coefficients ; Image analysis ; Image reconstruction ; Remote sensing ; Wavelet transforms ; Principal component analysis
  7. Source: AEU - International Journal of Electronics and Communications ; Volume 64, Issue 8 , 2010 , Pages 729-732 ; 14348411 (ISSN)
  8. URL: http://www.sciencedirect.com/science/article/pii/S1434841109002556