Table 6.
SVM maize-soybean diseased leaf identification model based on different feature extraction 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 | CARS | 100.0 | 91.7 | 85.7 | 83.6 | 100.0 | 98.6 | 93.6 | 100.0 | 92.9 | 76.7 | 74.1 | 100.0 | 93.5 | 88.0 |
| SPA | 100.0 | 77.1 | 84.9 | 82.3 | 100.0 | 91.9 | 89.6 | 100.0 | 70.0 | 92.6 | 76.2 | 100.0 | 88.5 | 87.3 | |
| PCA | 96.1 | 84.0 | 73.2 | 62.8 | 98.7 | 91.7 | 84.4 | 95.8 | 84.0 | 72.4 | 54.5 | 100.0 | 82.1 | 81.3 | |