We propose a state-of-the-art framework that consists of 4 deep models which are VGG16, EfficientNetB0, DenseNet121, and ResNet152-V2 implemented in a stage-wise approach.
Our Dataset link here Dataset is a particular data set that we have created for ourselves is a merging of the five datasets BrACoL , JMuBEN, JMuBEN2 , RoCoL , and LiCoLe
Dataset | Diseases | Citation |
---|---|---|
BrACoL | Healthy, CLR , Cercospora Leaf Spots (CLS) , Phoma Leaf Spots (PLS) , Coffee Leaf Miner (CLM) | Esgario, J. G., Krohling, R. A., & Ventura, J. A. (2020) "Deep learning for classification and severity estimation of coffee leaf biotic stress" Computers and Electronics in Agriculture 169, 105162. doi:10.1016/j.compag.2019.105162 |
JMuBEN | Cercospora Leaf Spot(CLS), Coffee Leaf Rust(CLR), Phoma Leaf Spot(PLS) | Jepkoech, Jennifer & Mugo, David & Kenduiywo, Benson & Too, Edna. (2021). Arabica coffee leaf images dataset for coffee leaf disease detection and classification. Data in Brief. 36. 107142. 10.1016/j.dib.2021.107142. |
JMuBEN2 | Healthy, Coffee Leaf Miner(CLM) | Jepkoech, Jennifer & Mugo, David & Kenduiywo, Benson & Too, Edna. (2021). Arabica coffee leaf images dataset for coffee leaf disease detection and classification. Data in Brief. 36. 107142. 10.1016/j.dib.2021.107142. |
RoCoL | Coffee Leaf Rust (CLR), Red Spider Mites (RSM) | Parraga-Alava, Jorge; Cusme, Kevin; Loor, Angélica; Santander, Esneider (2019), “RoCoLe: A robusta coffee leaf images dataset ” Mendeley Data, V2, doi: 10.17632/c5yvn32dzg.2 |
LiCoLe | Healthy , CLR , Sooty Molds (SM) | Montalbo, Francis Jesmar Perez; Hernandez, Alexander Arsenio (2020) "Classifying Barako coffee leaf diseases using deep convolutional models" International Journal of Advances in Intelligent Informatics (IJAIN) [S.l.], v. 6, n. 2, p. 197-209, july 2020. ISSN 2548-3161. doi: 10.26555/ijain.v6i2.495 |
- VGG16
- EfficientNetB0
- DenseNet121
- ResNet152-V2
Here is some research that helped us in this work