Cart (Loading....) | Create Account
Close category search window
 

back to article  |  Figures
All Figures

Optimized Laplacian SVM With Distance Metric Learning for Hyperspectral Image Classification

Figure 1

Figure 1
KSC dataset. (a) RGB composite image of three bands. (b) Groundtruth map.

Figure 2

Figure 2
University of Pavia dataset. (a) RGB composite image of three bands. (b) Groundtruth map.

Figure 3

Figure 3
Value of eq. (8) as a function of the number of iteration for four pairs of land cover types. (a) In the KSC dataset; (b) In the Pavia dataset.

Figure 4

Figure 4
Similarity matrix generated by (left) RBF and (right) the learned similarity metric weights. (a) Graminoid,/Spartina in the KSC (20 samples per class); (b) Willow,/CP-Hammock in the KSC (20 samples per class); (c) Asphlt/Metal-sheet in the Pavia (10 samples per class); (d) Bare-soil,/Brick in the Pavia (10 samples per class).

Figure 5

Figure 5
Experimental results for (top row) the KSC dataset and (bottom row) the Pavia dataset. (Left) Overall Accuracy (OA, in percent) and (right) Kappa statistic as a function of the number of labeled training samples.

Need Help?


IEEE Advancing Technology for Humanity About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2014 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.