Table 2.
Plant pest and disease literature according to the conventional techniques
| Classification and Feature extraction techniques | Plant pest or disease type | Reported accuracy (%) | Reference |
|---|---|---|---|
| SVM classifier +7-layer CNN | Rice | 95.48 | [48] |
| Fine tuning GoogLeNet | Plant pest | 98.00 | [49] |
| (fine-tuning) DenseNet-121 | Apples | 92.29 | [50] |
| Improved VGGNet-centred Inception module | Maize | 91.83 | [51] |
| Dilated convolution + Inception module | 14 different plants | 99.37 | [52] |
| Fine-tuning VGG19, ResNet152, DenseNet201, Inceptionv3, and AlexNet | Leaf diseases | 93.67 | [53] |
| 15-layer CNN architectures | Tomatoes | 91.50 | [54] |
| fine-tuning VGG16 | Tea | 90.00 | [55] |
| (fine-tuning) ResNet50, ResNet152, VGG16, ResNet101, Inceptionv4 and DenseNet121 | Plant Leaf diseases | 99.75 | [56] |
| 9-layer CNNs | Plant Leaf diseases | 96.46 | [57] |
| faster R-CNN model | Sugar beets | 95.48 | [58] |
| GoogleNet, AlexNet, ResNet, and VGGNet (fine-tuning) | Corns | 94.22 | [59] |
| Modified ResNet50 | Wheat | 98.00 | [60] |
| fine-tuning GoogleNet | Corns | 76.00 | [61] |
| 13-layer CNN | Soybeans | 99.32 | [62] |
| BPNN + GLCM and AlexNet | Leaf diseases | 93.85 | [63] |
| 7-layer CNN architecture | Rice | 95.48 | [64] |
| fine-tuning AlexNet, GoogleNet | Tomatoes | 99.18 | [65] |
| ResNet50, VGG19, VGG16, Inceptionv3 (fine-tuning) | Apples | 90.40 | [66] |
| SVM Classifier + Inceptionv3 | Cassava | 93.00 | [67] |
| fine-tuning LeNet | Banana | 99.72 | [68] |
| Modified AlexNet | Apples | 97.92 | [69] |
| fine-tuning CaffeNet | Leaf diseases | 96.30 | [70] |
| Modified VGGNet | Cucumber | 82.30 | [71] |
| GoogleNet and AlexNet (fine-tuning) | Leaf diseases | 99.35 | [72] |