Page 198 - Handbook of Deep Learning in Biomedical Engineering Techniques and Applications

Chapter 6 Plant leaf disease classification based on feature selection 187

Table 6.12 Performance comparison of all models.

Models
Class 1 2 3 4
AlexNet w/o transfer learning Recall 1.00 0.33 1.00 0.33
Precision 0.76 0.80 1.00 0.75
F1-score 0.86 0.47 1.00 0.46
VGG16 w/o transfer learning Recall 0.92 0.42 0.89 0.44
Precision 0.69 0.63 1.00 1.00
F1-score 0.79 0.50 0.94 0.62
ResNet-18 w/o transfer learning Recall 0.59 0.74 1.00 0.67
Precision 0.67 0.74 0.87 0.75
F1-score 0.63 0.74 0.93 0.71
ResNet-50 w/o transfer learning Recall 0.97 0.07 0.85 0.00
Precision 0.58 1.00 0.92 0.00
F1-score 0.72 0.13 0.88 0
AlexNet with transfer learning Recall 0.94 0.75 1.00 0.15
Precision 0.76 0.71 0.90 1.00
F1-score 0.84 0.73 0.95 0.27
VGG16 with transfer learning Recall 0.93 0.50 0.97 0.33
Precision 0.72 0.80 1.00 0.36
F1-score 0.81 0.62 0.98 0.35
ResNet-18 with transfer learning Recall 0.97 0.68 0.77 0.44
Precision 0.68 1.00 1.00 0.80
F1-score 0.80 0.81 0.87 0.57
ResNet-50 with transfer learning Recall 1.00 0.31 1.00 0.56
Precision 0.74 1.00 1.00 0.63
F1-score 0.85 0.47 1.00 0.59
MLP Recall 0.97 0.65 0.82 0.50
Precision 0.74 1.00 0.95 0.57
F1-score 0.84 0.79 0.88 0.53
MLP, multilayer perceptron.

References
[1] R. Yamashita, M. Nishio, R.K.G. Do, K. Togashi, Convolutional neural
networks: an overview and application in radiology, Insights Imaging
(2018), https://doi.org/10.1007/s13244-018-0639-9.
[2] M.H. Saleem, J. Potgieter, K.M. Arif, Plant disease detection and
classification by deep learning, Plants (2019), https://doi.org/10.3390/
plants8110468.