Table 6.
The accuracy (%) of the CNN models with image size = 128. The Accuracy Test Set was used for accuracy test for automatic identification of the five Korean softwoods
Species | LeNet | LeNet2 | LeNet3 | MiniVGGNet | MiniVGGNet2 | MiniVGGNet3 |
Cedar | 94.9 | 98.7 | 100.0 | 99.1 | 99.3 | 99.9 |
Cypress | 96.5 | 97.7 | 98.2 | 99.5 | 99.7 | 100.0 |
Korean Pine | 89.3 | 93.4 | 99.0 | 91.2 | 89.9 | 90.8 |
Korean Red Pine | 95.2 | 98.7 | 99.9 | 90.1 | 99.1 | 96.7 |
Larch | 94.7 | 98.3 | 99.6 | 96.0 | 99.3 | 100.0 |
Average | 94.1 | 97.4 | 99.3 | 95.2 | 97.5 | 97.5 |
Standard Deviation | 2.5 | 2.0 | 0.7 | 3.9 | 3.8 | 3.6 |