Table 1 Summary of the related works using the DL and ML techniques
From: Plant disease detection and classification techniques: a comparative study of the performances
Author(s) | Type(s) of plant | Used model(s)/Algorithms/Technique(s) | Accuracy % |
|---|---|---|---|
[1] | ✓ Soybean | ✓ YoloV5 ✓ InceptionV3 ✓ CNN | ✓ 98.75 ✓ 97.00 ✓ 97.00 |
[3] | ✓ Banana | ✓ CNN | ✓ 93.45 |
[4] | ✓ Rice | ✓ ResNet 50 ✓ ResNet101 ✓ DenseNet161 ✓ DenseNet169 | ✓ 91.68 ✓ 92.50 ✓ 95.74 ✓ 94.98 |
[5] | ✓ Tomato | ✓ PCA, Linear SVM | ✓ 88.67 |
[6] | ✓ Potato ✓ Tomato ✓ Strawberry ✓ Corn ✓ Grape ✓ Apple | ✓ LR ✓ KNN ✓ CNN ✓ SVM | ✓ 66.4 ✓ 54.5 ✓ 53.4 ✓ 98.0 |
[7] | ✓ Apple ✓ Corn ✓ Grapes ✓ Potato ✓ Sugarcane ✓ Tomato | ✓ CNN | ✓ 96.5 |
[8] | ✓ Tomato | ✓ CNN and LQV | ✓ 86.00 |
[9] | ✓ Rice | ✓ InceptionResNetV2 ✓ Xception ✓ ResNet50 ✓ MobileNet ✓ InceptionV3 | ✓ 98.9 ✓ 97.65 ✓ 97.00 ✓ 96.65 ✓ 95.85 |
[12] | ✓ Turmeric | ✓ VGG-16 | ✓ 96.24 |
[13] | ✓ Different plant leaf species | ✓ SVM | ✓ 92.4 |
[14] | ✓ Tomato ✓ Pepper ✓ Potato | ✓ CNN | ✓ 98.029 (for testing) ✓ 98.29 (for training) |
[25] | ✓ Rice | ✓ DCNN | ✓ 99.7 |
[26] | ✓ Tomato | ✓ CNN | ✓ 99.64 |
[29] | ✓ Rice ✓ Apple ✓ Bean ✓ Potato ✓ Tomato | ✓ DenseNet-121 | ✓ 98.00 ✓ 96.00 ✓ 94.00 ✓ 95.00 ✓ 97.00 |
[33] | ✓ Tomato | ✓ AlexNet with TL ✓ AlexNet with FE | ✓ 89.69 with an 80/20 and 88.45% with a 70/30 ratios ✓ 93.4 with an 80/20 and 92.11% with a 70/30 ratios |
[39] | ✓ Rice | ✓ TL ✓ CNN + TL ✓ ANN ✓ ECNN + GA | ✓ 80.00 ✓ 85.00 ✓ 90.00 ✓ 95.00 |
[40] | ✓ Different plant leaf species | ✓ LR ✓ SVM ✓ KNN ✓ RF ✓ NB ✓ CNN | ✓ 71.89 ✓ 75.76 ✓ 82.17 ✓ 97.12 ✓ 81.12 ✓ 98.43 |
[41] | ✓ Rice | ✓ DenseNet169 ✓ Xception (fine-tuned TL) | ✓ 99.66 ✓ 99.99 |
[42] | ✓ Different plant leaf species | ✓ C-GAN ✓ CNN ✓ SGD ✓ ACO-CNN | ✓ 99.6 ✓ 99.97 ✓ 85.00 ✓ 99.98 |
[43] | ✓ Different plant leaf species | ✓ EfficientB5Net ✓ InceptionV3Net ✓ DenseNet201 ✓ AlexNet ✓ ResNet152 ✓ VGG19Net ✓ PPLC-Net | ✓ 94.512 ✓ 96.347 ✓ 95.481 ✓ 89.548 ✓ 95.728 ✓ 92.695 ✓ 99.702 |
[44] | ✓ Tomato | ✓ 2-DCNN | ✓ 96.00 |
[45] | ✓ Apple ✓ Corn ✓ Cotton ✓ Grape ✓ Pepper ✓ Rice | ✓ Dilated TL and EL | ✓ 99.10 |
[46] | ✓ Lemon ✓ Banana ✓ Beans ✓ Rose | ✓ SVM with the proposed algorithm | ✓ 95.71 |
[47] | ✓ Tomato | ✓ EL based DL | ✓ 96.00 |
[48] | ✓ Tomato | ✓ ResNet50-CBAM + SVM | ✓ 97.20 |
[49] | ✓ Tomato | ✓ Faster-RCNN (RESNET-34) | ✓ 99.97 |
[51] | ✓ Ginger | ✓ CNN | ✓ 95.2 |
[52] | ✓ Different plant leaf species | ✓ DCNN with YOLOv7 | ✓ 99.50 |
[53] | ✓ Cotton | ✓ CNN | ✓ 100 and 90 for identification and classification respectively |
[54] | ✓ Coffee | ✓ DT with BPNN | ✓ 94.5 |
[55] | ✓ Tomato | ✓ GAR | ✓ 96.70 |
[56] | ✓ Tomato | ✓ Customized U-Net | ✓ 98.12 |
[57] | ✓ Coffee | ✓ TL through Mobilnet ✓ Resnet50 | ✓ 97.01 ✓ 99.89 |
[58] | ✓ Tomato | ✓ U-Net and Modified U-Net | ✓ 99.97 (binary class) ✓ 99.22 (Multi-Class (6)) ✓ 99.91 (Multi-Class (10)) |
[59] | ✓ Tomato | ✓ KNN ✓ SVM | ✓ 99.92 ✓ 99.90 |
[60] | ✓ Olive | ✓ MobiRes-Net ✓ ResNet50 ✓ MobileNet | ✓ 97.08 ✓ 94.86 ✓ 95.63 |
[61] | ✓ Rice | ✓ PlantDet | ✓ 98.53 |
[62] | ✓ Different plant leaf species | ✓ DenseNet-77 | ✓ 99.98 |
[63] | ✓ Tomato | ✓ DCNN | ✓ 98.49 |
[64] | ✓ Tomato | ✓ A multinomial LR | ✓ 97.00 |
[65] | ✓ Canola ✓ Corn ✓ Wild radish | ✓ K-FLBPCM | ✓ 98.63 |
[66] | ✓ Tea | ✓ GLCM with Harris ✓ and SVM | ✓ 97.48 |
[67] | ✓ Turmeric | ✓ KMC, GLCM, GLCM, and SVM | ✓ 91.61 |
[68] | ✓ Tomato | ✓ CNN | ✓ 94.00 |
[69] | ✓ Maize | ✓ SVM ✓ NB ✓ KNN ✓ DT ✓ RF | ✓ 77.56 ✓ 77.46 ✓ 76.16 ✓ 74.35 ✓ 79.23 |
[70] | ✓ Rice | ✓ TL (InceptionV3, MobileNetV2 and DenseNet121) | ✓ 96.42 |
[71] | ✓ Tomato | ✓ ResNet101,VGG16,VGG19,GoogleLeNet, AlexNet, ResNet50 | ✓ 94.6 |
[72] | ✓ Tomato | ✓ MobileNetV2 | ✓ 99.30 |
[73] | ✓ Apple ✓ Blueberry ✓ Cherry ✓ Corn ✓ Grape ✓ Orange ✓ Peach ✓ Pepper bell ✓ Potato ✓ Raspberry ✓ Soybean ✓ Squash ✓ Strawberry ✓ Tomato | ✓ InceptionV3 ✓ InceptionResnetV2 ✓ MobileNetV2 ✓ EfficientNetB0 | ✓ 98.42 ✓ 99.11 ✓ 97.02 ✓ 99.56 |
[74] | ✓ Tomato | ✓ SE-ResNet50 | ✓ 96.81 |
[75] | ✓ Tomato | ✓ OpenCV | ✓ 98.00 |
[76] | ✓ Tomato | ✓ DNN | ✓ 86.18 |
[77] | ✓ Tomato | ✓ GoogleNet, AlexNet, Inception V3,ResNet 18,ResNet 50 | ✓ 99.72 |
[78] | ✓ Tomato | ✓ AlexNet | ✓ 76.1 |
[79] | ✓ Tomato | ✓ MobileNet V2 | ✓ 90.00 |
[80] | ✓ Tomato | ✓ Hybrid SVM | ✓ 92.37 |
[81] | ✓ Apple ✓ Blueberry ✓ Cherry ✓ Corn ✓ Grape ✓ Orange ✓ Peach ✓ Pepper ✓ Potato ✓ Raspberry ✓ Soybean ✓ Squash ✓ Strawberry ✓ Tomato | ✓ DCNN | ✓ 96.46 |
[82] | ✓ Tomato | ✓ Multiclass SVM | ✓ 94.00 |
[83] | ✓ Tomato | ✓ TL based DCNN | ✓ 99.55 |
[84] | ✓ Tomato | ✓ VGG16 ✓ InceptionV3 ✓ MobileNet | ✓ 91.2 ✓ 63.40 ✓ 63.75 |
[85] | ✓ Tomato | ✓ CNN in PlantVillage dataset ✓ CNN other than the PlantVillage dataset ✓ A traditional ML with KNN ✓ VGG16 | ✓ 98.4 ✓ 98.7 ✓ 94.9 ✓ 93.5 |
[87] | ✓ Citrus | ✓ GLCM, k-means, SVM | ✓ 90.00 |
[90] | ✓ Rice | ✓ Vgg16 ✓ Vgg19 ✓ ResNet50 ✓ ResNet50v2 ✓ ResNet101v2 | ✓ 70.42 ✓ 73.60 ✓ 51.99 ✓ 61.60 ✓ 86.79 |
[91] | ✓ Rice | ✓ SVM, DCNN | ✓ 97.5 |
[93] | ✓ Grape | ✓ KMC and SVM | ✓ 88.89 |
[94] | ✓ Soybean | ✓ SIFT and SVM | ✓ 93.79 |
[95] | ✓ Maize ✓ Grape ✓ Apple ✓ Tomato | ✓ MobileNet50 ✓ PDDNN | ✓ 74.90 ✓ 86.00 |
[96] | ✓ Cotton | ✓ DCNN | ✓ 96.00 |
[98] | ✓ Tomato | ✓ AlexNet ✓ SqueezeNet | ✓ 95.65 ✓ 94.30 |
[99] | ✓ Tomato | ✓ CNN | ✓ 97.00 |
[105] | ✓ Rice | ✓ CNN | ✓ 92.46 |
[110] | ✓ Guava | ✓ DCNN | ✓ 98.74 |
[112] | ✓ Apple ✓ Blueberry ✓ Cherry ✓ Corn ✓ Grape ✓ Orange ✓ Peach ✓ Pepper bell ✓ Potato ✓ Raspberry ✓ Soybean ✓ Squash ✓ Strawberry ✓ Tomato | ✓ CNN | ✓ 99.35 |
[113] | ✓ Cotton | ✓ ANN | ✓ 80.00 |
[114] | ✓ Different plant leaf species | ✓ ANN | ✓ 92.00 |
[119] | ✓ Groundnut | ✓ Back propagation | ✓ 97.00 |
[121] | ✓ Phyllanthus Elegans | ✓ MLP ✓ RBF | ✓ 90.15 ✓ 98.85 |
[122] | ✓ Cotton ✓ Soybeans | ✓ ANN | ✓ 83.00 ✓ 80.00 |
[123] | ✓ Potato ✓ Tomato ✓ Pepper bell | ✓ CNN, Bayesian algorithm | ✓ 98.90 |
[124] | ✓ Grapes | ✓ Hybrid CNN | ✓ 98.70 |
[125] | ✓ Strawberry | ✓ FL | ✓ 96.00 |
[126] | ✓ Apple | ✓ PR | ✓ 90.00 |
[128] | ✓ Maize | ✓ CNN | ✓ 96.76 |
[132] | ✓ Different plant leaf species | ✓ NB | ✓ 97.00 |
[134] | ✓ Rice ✓ Potato | ✓ CNN | ✓ 99.58 ✓ 97.66 |
[136] | ✓ Guava | ✓ CNN | ✓ 95.61 |
[137] | ✓ Potato | ✓ KMC and GLCM | ✓ 95.99 |
[138] | ✓ Beans | ✓ MobileNet | ✓ 92.00 |
[139] | ✓ Maize | ✓ GoogleNet ✓ Cifa10 | ✓ 98.90 ✓ 98.80 |
[140] | ✓ Onion | ✓ DCNN | ✓ 85.47 |
[142] | ✓ Rice | ✓ ADSNN-BO | ✓ 94.65 |
[143] | ✓ Tomato | ✓ RF | ✓ 95.00 |
[144] | ✓ Different plant leaf species | ✓ KMC and CNN | ✓ 92.60 |
[145] | ✓ Sugarcane | ✓ SVM | ✓ 95.00 |
[146] | ✓ Cassava | ✓ ANN and KNN | ✓ 90.00 |
[147] | ✓ Tomato ✓ Potato ✓ Rice ✓ Pepper bell | ✓ ML and DL | ✓ 99.4 for binary class ✓ 99.2 for multiclass |
[148] | ✓ Maize | ✓ YOLOv3-tiny ✓ YOLOv4 ✓ YOLOv5s ✓ YOLOv7s ✓ YOLOv8n | ✓ 69.40 ✓ 97.50 ✓ 88.23 ✓ 93.30 ✓ 99.04 |
[149] | ✓ Rice | ✓ ADLWNN | ✓ 98.17 |
[150] | ✓ Cofee | ✓ KDE + ResNet50 | ✓ 98.00 |
[151] | ✓ Apple ✓ Rice ✓ Corn ✓ Grape | ✓ Res-ATTEN | ✓ 99.00 ✓ 99.00 ✓ 94.00 ✓ 97.00 |
[152] | ✓ Maiz ✓ Potato ✓ Tomato | ✓ DeepPlantNe DL | ✓ 98.49 (in eight classes) and 99.85 (in three classes) |
[153] | ✓ Apple ✓ Maize ✓ Cherry ✓ Corn/Maze ✓ Grape ✓ Peach ✓ Potato ✓ Cassava | ✓ PDD-Net | ✓ 93.79 (in PlantVillege dataset) ✓ 86.98 (only for Casava) |
[154] | ✓ Tomato | ✓ CNN | ✓ 99.60 |
[155] | ✓ Sugarcane | ✓ DNSVM | ✓ 97.78 |
[156] | ✓ Palm | ✓ ResNet | ✓ 99.62 (for the original dataset) and 100% (for the augmented dataset) |
[157] | ✓ Maize | ✓ RF | ✓ 80.68 |
[158] | ✓ Mini-leaves ✓ Sugarcane | ✓ SSM-Net | ✓ 92.7 ✓ 94.30 |
[159] | ✓ Vegetables | ✓ KMC | ✓ 95.16 |
[160] | ✓ Weed | ✓ Histogram analysis ✓ SIFT | 95.00 ✓ 99.00 |
[161] | ✓ Rice | ✓ TL | ✓ 99.64 |