Research Article
A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random Forest
Table 3
The comparison of overall accuracy and Kappa coefficient under different classifier algorithm of AVIRIS data.
| Comparative classification method | Run time (seconds) | Overall Accuracy (%) | Kappa Coefficient | T1 | T2 | T3 | T1 | T2 | T3 | T1 | T2 | T3 |
| Minimum distance classification algorithm | 7 | 10 | 11 | 65.46 | 63.06 | 65.21 | 0.6164 | 0.5895 | 0.6137 | Support vector machine classification algorithm | 62 | 72 | 86 | 78.47 | 80.17 | 82.35 | 0.7609 | 0.7704 | 0.8041 | Classification and regression trees (CART) | 17 | 21 | 26 | 75.04 | 78.0412 | 78.3285 | 0.7227 | 0.7557 | 0.7591 | This-algorithm classifies( 5% of the-labeled labels) | 16.21 | 16.63 | 17.69 | 82.98 | 84.19 | 85.35 | 0.8108 | 0.8234 | 0.8371 | This-algorithm classifies(10% labeled labels) | 20.65 | 21.10 | 22.72 | 85.85 | 86.81 | 87.36 | 0.8421 | 0.8528 | 0.8591 |
|
|