Table 14 Fold − 4 Cross-validation performance of DAC-GAN with CKPF images.
Model | Accuracy (%) | Sensitivity (%) | Specificity (%) | Precision (%) | Recall (%) | F1-Score (%) | IoU (%) |
|---|---|---|---|---|---|---|---|
DenseNet121 | 78.31 | 76.47 | 79.17 | 76.97 | 76.47 | 76.67 | 60.53 |
VGG19 | 79.56 | 77.97 | 80.22 | 78.31 | 77.97 | 78.14 | 61.75 |
Inception | 80.35 | 78.63 | 81.06 | 79.15 | 78.63 | 78.89 | 63.22 |
XCeption | 81.39 | 79.42 | 82.14 | 80.10 | 79.42 | 79.76 | 64.29 |
MobileNet | 82.67 | 80.28 | 83.18 | 81.10 | 80.28 | 80.69 | 66.14 |
ResNet-50 | 83.82 | 81.21 | 84.63 | 82.03 | 81.21 | 81.62 | 67.79 |
EfficientNet-B0 | 85.53 | 83.10 | 86.28 | 84.02 | 83.10 | 83.56 | 70.02 |
EfficientNet-B4 | 87.27 | 84.75 | 87.99 | 85.62 | 84.75 | 85.18 | 72.43 |
ConvNeXt | 88.89 | 86.33 | 89.67 | 87.39 | 86.33 | 86.86 | 74.41 |
ViT CNN | 89.74 | 87.25 | 90.12 | 88.11 | 87.25 | 87.68 | 76.21 |
SwinT | 90.01 | 87.93 | 90.43 | 88.77 | 87.93 | 88.34 | 77.40 |
WGAN | 93.84 | 92.90 | 93.43 | 93.52 | 92.82 | 92.88 | 92.88 |
CGAN | 92.19 | 92.62 | 92.12 | 92.43 | 93.99 | 93.11 | 93.18 |
DAC-GAN | 99.80 | 99.86 | 99.91 | 99.83 | 99.86 | 99.84 | 99.66 |
