[Retracted] Hybrid Feature-Based Disease Detection in Plant Leaf Using Convolutional Neural Network, Bayesian Optimized SVM, and Random Forest Classifier

Table 8

Comparative results.

Methods	Method used	Accuracy	Precision	Sensitivity	F1-score
Ahmad et al. (2020) [41]	Tomato plant leaf disease detection from PlantVillage database using CNN	—	84.5%	90.6%	87.6%
Kaur et al. (2021) [42]	Bell pepper, potato, and tomato plant leaf disease detection from PlantVillage database using LBP, GLCM, SIFT, and Gabor features with ensemble classifier	95.66%	—	—	—
Rao et al. (2020) [43]	Various plants leaf disease detection from PlantVillage database using GLCM, complex Gabor filter, curvelet, and image moments features with neuro-fuzzy logic classifier	93.18%	—	—	—
Zong et al. (2020) [44]	Apple leaf disease detection from PlantVillage database using DenseNet-121 deep convolution network	93.71%	—	—	—
Sujatha et al. (2021) [45]	Various plants leaf disease detection from PlantVillage database using deep convolution network (VGG-16)	89.5%	—	—	—
Chen et al. (2020) [46]	Rice plant leaf disease detection from Plant Village database using dense net pretrained on ImageNet
Inception module of convolutional neural network	94.07%	—	—	—
Proposed Bayesian optimized SVM	Various plants leaf disease detection from PlantVillage database using deep convolution network and Bayesian optimized SVM classifier	92.2%	95.1%	73.4%	82.85%
Random forest classifier	Various plants leaf disease detection from PlantVillage database using hybrid features and random forest classifier	96.1%	95.9%	88.6%	92.1%