Table 15 Fold − 5 Cross-validation performance of DAC-GAN with CKPF images.
Model | Accuracy (%) | Sensitivity (%) | Specificity (%) | Precision (%) | Recall (%) | F1-Score (%) | IoU (%) |
|---|---|---|---|---|---|---|---|
DenseNet121 | 78.55 | 76.73 | 79.36 | 77.15 | 76.73 | 76.94 | 60.66 |
VGG19 | 79.74 | 78.12 | 80.45 | 78.45 | 78.12 | 78.28 | 61.81 |
Inception | 80.63 | 78.86 | 81.33 | 79.39 | 78.86 | 79.12 | 63.44 |
XCeption | 81.62 | 79.63 | 82.43 | 80.36 | 79.63 | 79.99 | 64.41 |
MobileNet | 82.79 | 80.49 | 83.39 | 81.28 | 80.49 | 80.88 | 66.31 |
ResNet-50 | 83.96 | 81.46 | 84.76 | 82.18 | 81.46 | 81.82 | 68.02 |
EfficientNet-B0 | 85.62 | 83.19 | 86.32 | 84.10 | 83.19 | 83.64 | 70.19 |
EfficientNet-B4 | 87.35 | 84.84 | 88.08 | 85.74 | 84.84 | 85.29 | 72.57 |
ConvNeXt | 88.98 | 86.38 | 89.73 | 87.46 | 86.38 | 86.91 | 74.63 |
ViT CNN | 89.85 | 87.33 | 90.13 | 88.18 | 87.33 | 87.75 | 76.37 |
SwinT | 90.10 | 88.00 | 90.45 | 88.84 | 88.00 | 88.42 | 77.56 |
WGAN | 94.81 | 93.80 | 93.11 | 92.82 | 93.80 | 93.82 | 93.83 |
CGAN | 93.59 | 92.52 | 92.99 | 93.53 | 92.19 | 92.51 | 92.58 |
DAC-GAN | 99.83 | 99.89 | 99.93 | 99.85 | 99.89 | 99.87 | 99.69 |
