Research Article
A New Methodology for Spectral-Spatial Classification of Hyperspectral Images
Table 1
Class-specific accuracies in percentage for the ROSIS image by different classifiers.
| Class | Samples | Method | Train | Test | Pixel-wise SVM (%) | Three PCs (%) | (%) | (%) | (%) |
| C1 | 252 | 567 | 90.30 | 93.83 | 98.57 | 99.47 | 96.17 | C2 | 135 | 355 | 98.56 | 88.02 | 90.08 | 89.82 | 40.70 | C3 | 720 | 1697 | 92.29 | 98.56 | 98.51 | 98.59 | 96.44 | C4 | 1260 | 2961 | 92.82 | 98.41 | 98.59 | 98.59 | 89.54 | C5 | 91 | 214 | 99.41 | 99.63 | 99.41 | 99.48 | 98.74 | C6 | 198 | 463 | 70.00 | 78.70 | 79.33 | 80.13 | 96.23 | C7 | 173 | 323 | 68.65 | 73.42 | 99.67 | 100 | 86.47 | C8 | 644 | 1619 | 81.41 | 92.32 | 95.19 | 94.89 | 87.42 | C9 | 513 | 1125 | 96.52 | 98.31 | 99.58 | 99.68 | 55.12 |
|
|