Table 11.
Cucumber Vegetable classification using AI.
| Authors | AI Methods | Dataset | Disease | Accuracy |
|---|---|---|---|---|
| (Lin et al., 2019b) | U-Net | Kaggle dataset | Powdery mildew | U-Net =83.45% |
| (Khan et al., 2020) | Multi-class SVM | Northwest A&F university (self-collected) | Downy mildew, bacterial angular, corynespora, scab, gray mold, anthracnose, and powdery mildew | SVM=98.08% |
| (Zhang et al., 2019) | GPDCNN | Yangling Agricultural zone Chine (Self-collected) | Anthracnose, gray mold, angular leaf spot, and black spot | GPDCNN =94.65% |
| (Zhang et al., 2017) | SVM, KSSNN, TF, PLI and SR | Northwest A&F university (self-collected) | Downy mildew, anthracnose, and powdery mildew | SR=85.7% |
| (Kianat et al., 2021) | Quadratic SVM | Northwest A&F university (self-collected) | Angular leaf spot, blight, anthracnose, and corynespora | SVM=93.50% |
| (Zhang et al., 2020) | EfficientNet-B4-Ranger | Vegetable area in Jingyang China (self-collected) | Powdery mildew, downy mildew, and healthy | EfficientNet-B4-Ranger =96% |
| (Wang et al., 2021) | DUNet | Xiaotangshan National Precision Agriculture Research (self-collected) | Healthy, downy mildew, powdery mildew, and virus disease | DUNet=92.85% |