Potato Leaf Disease Classification Using Federated Learning

Accurate classification of diseases in potato crops is vital for optimizing yield and ensuring crop health. We propose a generalized framework using Federated Learning (FL) for accurate classification of potato crop diseases. The dataset from Plant Village includes diverse potato leaf images with imbalanced class distributions. By incorporating FL, which enables collaborative model training without sharing raw data, we leverage the collective intelligence of distributed datasets while ensuring privacy. CNN as base model, achieves a 92% classification accuracy in the potato disease dataset through extensive experimentation and hyperparameter fine-tuning. Our approach addresses the challenge of an unbalanced dataset in potato disease classification and contributes to advances in precision agriculture. The framework can be adapted for other crop disease classification tasks, showcasing the potential of distributed learning in agriculture. Overall, our study demonstrates the effectiveness of FL in achieving accurate and scalable disease classification models in potato crops.