Table 2.
SVM maize-soybean diseased leaf identification model based on different spectral preprocessing methods.
| Model | Method | Training set classification recall/% | General accuracy |
Test set classification recall/% | General accuracy |
||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Maize normalcy |
Maize spot |
Maize rust |
Maize hybrid |
Soybean normalcy |
Soybean rust |
Maize normalcy |
Maize spot |
maize rust |
Maize hybrid |
Soybean normalcy |
Soybean rust |
||||
| SVM | SG | 100.0 | 88.7 | 77.3 | 47.0 | 100.0 | 92.3 | 84.2 | 100.0 | 86.2 | 84.0 | 44.1 | 100.0 | 86.4 | 80.0 |
| SNV | 97.4 | 84.0 | 86.7 | 61.8 | 98.7 | 94.9 | 87.8 | 100.0 | 72.0 | 68.0 | 68.8 | 100.0 | 100.0 | 83.3 | |
| MSC | 95.1 | 81.7 | 79.5 | 68.5 | 98.7 | 95.9 | 86.9 | 94.7 | 79.3 | 81.5 | 51.9 | 100.0 | 100.0 | 83.3 | |
| 1st Der | 100.0 | 90.7 | 86.7 | 67.6 | 100.0 | 89.9 | 89.6 | 100.0 | 84.0 | 72.0 | 71.9 | 100.0 | 100.0 | 86.7 | |