Table 1 Mean (and standard deviation) for the different studied models without considering the control image to generate the feature vectors
From: DecoFungi: a web application for automatic characterisation of dye decolorisation in fungal strains
Network | ERT | KNN | LR | MLP | RF | SVM |
|---|---|---|---|---|---|---|
DenseNet | 91.4(1.7) | 84.0(3.3) | 90.1(2.5) | 57.3(10.4) | 87.3(2.1) | 33.3(4.7) |
GoogleNet | 92.4(2.1) | 49.2(3.8) | 89.4 (2.4) | 85.7 (5.9) | 89.4 (2.1) | 60.5(4.8) |
Inception v3 | 88.6(2.8) | 83.1(3.5) | 92.6(1.2) | 91.1(2.1) | 80.0(2.7) | 34.6(4.8) |
OverFeat | 89.5(2.5) | 85.8(4.0) | 91.2(2.5) | 91.7(2.3) | 85.8(4.0) | 92.5(2.3) |
Resnet 50 | 93.5(1.9) | 46.4(4.9) | 94.5(1.7) | 93.3(2.7) | 89.9(2.1) | 73.1(6.1) |
VGG16 | 89.9(2.3) | 79.1(3.1) | 91.7(1.8) | 89.8(2.8) | 82.5(2.2) | 31.3(4.9) |
VGG19 | 90.1(2.1) | 84.4(3.1) | 92.7(2.3) | 90.9(2.4) | 78.7(4.3) | 33.1(4.7) |
Xception v1 | 90.1(2.7) | 87.8(2.9) | 93.5(1.6) | 92.2(2.0) | 82.1(3.7) | 91.9(1.3) |