Table 3 The producer’s and user’s accuracy for each class using different datasets and algorithms
From: Potential use of hyperspectral data to classify forest tree species
| Â | Classification | |||||||
|---|---|---|---|---|---|---|---|---|
Support vector machine over 129 bands | Neural net over 36 bands | Maximum likelihood over first three principal component analysis bands | Maximum likelihood over first seven minimum noise fraction bands | |||||
Species | Producer’s accuracy (%) | User’s accuracy (%) | Producer’s accuracy (%) | User’s accuracy (%) | Producer’s accuracy (%) | User’s accuracy (%) | Producer’s accuracy (%) | User’s accuracy (%) |
Birch | 10.00 | 66.67 | 0.00 | 0.00 | 10.00 | 40.00 | 10.00 | 33.33 |
European beech | 86.00 | 52.44 | 76.00 | 59.38 | 84.00 | 76.36 | 100.00 | 70.42 |
Oak species | 68.00 | 82.93 | 80.00 | 55.56 | 92.00 | 85.19 | 94.00 | 95.92 |
Hornbeam | 10.00 | 100.00 | 0.00 | 0.00 | 70.00 | 63.64 | 60.00 | 100.00 |
European larch | 92.00 | 83.64 | 66.00 | 73.33 | 100.00 | 90.91 | 100.00 | 100.00 |
No-forest | 98.00 | 83.64 | 82.00 | 77.36 | 100.00 | 96.15 | 100.00 | 98.04 |
Scots pine | 94.00 | 94.00 | 94.00 | 71.21 | 98.00 | 100.00 | 98.00 | 100.00 |
Norway spruce | 40.00 | 88.89 | 0.00 | 0.00 | 95.00 | 100.00 | 90.00 | 100.00 |