Table 9 Model Comparisons on the grapes dataset.

From: Optimised MobileNet for very lightweight and accurate plant leaf disease detection

Model Name

Class

Train Acc.

Test Acc.

Precision

Recall

Sensitivity

Specificity

F1

MCC

Xception Network

Healthy

99.04

95.34

1.00

0.99

0.99

1.00

0.99

0.99

Esca

97.44

0.91

0.96

0.96

0.96

0.92

0.92

Black rot

93.33

0.91

0.95

0.95

0.96

0.92

0.92

Leaf Blight

95.94

0.89

0.93

0.93

0.92

0.89

0.89

Densenet-121

Healthy

98.88

96.91

0.98

0.97

0.97

0.98

0.97

0.97

Esca

98.50

0.92

0.97

0.97

0.97

0.93

0.93

Black rot

98.50

0.92

0.96

0.96

0.97

0.93

0.93

Leaf Blight

99.22

0.98

0.98

0.98

0.99

0.98

0.98

Alexnet

Healthy

99.58

97.84

0.98

0.98

0.98

0.99

0.98

0.97

Esca

98.79

0.98

0.98

0.98

0.99

0.98

0.98

Black rot

98.89

0.97

0.98

0.98

0.99

0.97

0.97

Leaf Blight

98.66

0.97

0.98

0.98

0.99

0.98

0.97

VGG-16

Healthy

97.06

89.75

0.97

0.89

0.89

0.99

0.93

0.91

Esca

93.19

0.83

0.91

0.91

0.93

0.87

0.83

Black rot

90.58

0.84

0.78

0.78

0.94

0.81

0.76

Leaf Blight

98.83

0.95

0.99

0.99

0.98

0.97

0.96

Resnet-50

Healthy

82.43

45.65

0.96

0.26

0.26

0.99

0.40

0.45

Esca

74.93

0.51

0.89

0.89

0.69

0.65

0.55

Black rot

57.22

0.32

0.57

0.57

0.57

0.41

0.28

Leaf Blight

76.73

0.91

0.02

0.02

0.99

0.04

0.13

EfficientNet B2

Healthy

76.56

26.59

0

0

0

1

  

Esca

26.59

0.26

1

1

0

0.42

 

Black rot

73.85

0

0

0

1

  

Leaf Blight

76.17

0

0

0

1

  

SoyNet Model

Healthy

99.22

93.30

0.98

0.98

0.98

0.99

0.98

0.97

Esca

94.95

0.94

0.85

0.85

0.98

0.90

0.87

Black rot

93.51

0.84

0.92

0.92

0.93

0.88

0.84

Leaf Blight

98.89

0.98

0.97

0.97

0.99

0.97

0.96

V\(^2\)PlantNet

Healthy

99.88

99.50

1.00

1.00

1.00

1.00

1.00

1.00

Esca

99.50

1.00

0.99

0.99

0.98

0.99

0.99

Black rot

99.66

0.99

0.99

0.99

0.99

0.99

0.99

Leaf Blight

99.94

0.99

1.00

1.00

0.96

0.99

0.97