From: Using transfer learning-based plant disease classification and detection for sustainable agriculture
Feature extraction approaches | Classification techniques | Plant pest or disease type | Reported accuracy (%) | Reference |
---|---|---|---|---|
Texture features | SVM | Tea | 93.33 | [36] |
Texture and Color features | SVM | Soybean | 90.00 | [37] |
GLCM | SVM | Five leaf disease | 95.70 | [34] |
Gabor wavelets transform and gray-level co-occurrence matrix | KNN | 93.0 | [35] | |
Local binary pattern | SVM | Grape | 96.60 | [38] |
color features + GLCM | PNN | Potato | 92.00 | [39] |
Color, shape, and texture feature | Classification tree | Tomatoes | 97.30 | [40] |
Color feature + GLCM | SVM | Grapes | 88.89 | [41] |
Local binary pattern + Zernike moment | SVM | Apples | 95.94 | [42] |
Texture and color and feature | BPNN | Groundnut | 97.41 | [43] |
Color, shape, and texture feature | PNN | Cucumber | 91.08 | [44] |
Scale-invariant feature transforms | SVM | Soybeans | 93.79 | [45] |
Color feature + GLCM method | SVM | Fungal diseases | 83.83 | [46] |
Shape + Color features | – | Paddy | 94.70 | [47] |