Table 16 Detailed classification test results for the Botswana Dataset in terms of Precision, Recall, and F1-Score. Testing was done with PCA 30 CEU-Net no-patching with a 75%/25% Training/Testing split
From: CEU-Net: ensemble semantic segmentation of hyperspectral images using clustering
Class Labels | Precision | Recall | f1-score | Support |
|---|---|---|---|---|
Water | 1.00 | 1.00 | 1.00 | 69 |
Hippo Grass | 1.00 | 1.00 | 1.00 | 19 |
Floodplain Grasses 1 | 1.00 | 0.98 | 0.99 | 62 |
Floodplain Grasses 2 | 0.93 | 1.00 | 0.96 | 51 |
Reeds 1 | 0.94 | 0.94 | 0.94 | 80 |
Riparian | 0.93 | 0.90 | 0.91 | 70 |
Firescar 2 | 1.00 | 0.97 | 0.98 | 64 |
Island Interior | 1.00 | 1.00 | 1.00 | 60 |
Acacia Woodlands | 0.99 | 0.92 | 0.95 | 75 |
Acacia Shrublands | 0.91 | 1.00 | 0.95 | 51 |
Acacia Grasslands | 1.00 | 0.99 | 0.99 | 80 |
Short Mopane | 0.84 | 1.00 | 0.91 | 36 |
Mixed Mopane | 0.97 | 0.90 | 0.93 | 68 |
Exposed Soils | 1.00 | 1.00 | 1.00 | 27 |
Accuracy | Â | Â | 0.96 | 812 |
Macro Average | 0.96 | 0.97 | 0.97 | 812 |
Weighted Average | 0.97 | 0.96 | 0.96 | 812 |