Table 14 Comparison of proposed network models on the accuracy scores with pretrained networks
From: Using transfer learning-based plant disease classification and detection for sustainable agriculture
Reference | Year of Publication | Classification and Feature extraction techniques | Plant pest or disease type | Reported accuracy (%) |
|---|---|---|---|---|
[70] | 2016 | fine-tuned DenseNet201+Inceptionv3+ResNet152+ VGG19 and AlexNet | Leaf diseases | 93.67 |
[54] | 2019 | 15-layer CNN | Tomato | 91.50 |
[48] | 2019 | SVM classifier + 7-layer | Rice | 95.48 |
[50] | 2020 | fine-tuned DenseNet-121 | Apples | 92.29 |
[51] | 2023 | Enhanced VGGNet-based Inception module | Potatoes | 91.83 |
[84] | 2023 | SVM classifier + CNN | Paddy | 91.45 |
[85] | 2023 | SMoGW-DCNN | Leaf diseases | 94.5 |
[86] | 2023 | GP2D2 | Paddy | 89.4 |
[87] | 2023 | Inception V3 model + Adam Optimizer | Basil and Mint Leaves | 70.89 |
Proposed model | PDDNet-EA | PlantVillage | 96.94 | |
PDDNet-LAE | PlantVillage | 97.79 | ||