Table 8. The Classification Accuracy (%) for the 500 DCT features extracted from different combination of CNNs used in Gastro-CADx using Dataset II.
Features | Linear | Quadratic | Cubic |
---|---|---|---|
ResNet+DarkNet | 98.1 | 98.4 | 98.5 |
AlexNet+DarkNet | 97.7 | 97.9 | 98 |
DenseNet+DarkNet | 48.7 | 49 | 49.2 |
AlexNet+ResNet | 98.2 | 98.5 | 98.6 |
AlexNet+DenseNet | 98.2 | 98.6 | 98.6 |
ResNet +DenseNet | 98.8 | 98.9 | 98.9 |
AlexNet+ResNet+DarkNet | 98.8 | 99 | 99.2 |
AlexNet+DenseNet+DarkNet | 98.6 | 98.7 | 98.7 |
ResNet +DenseNet+DarkNet | 98.6 | 98.9 | 98.9 |
AlexNet+ResNet +DenseNet | 99.6 | 99.6 | 99.6 |
AlexNet+ResNet +DenseNet+DarkNet | 98.7 | 99.5 | 99.6 |