Plant Leaf Disease Detection Using Transfer Learning Approach

Plant diseases are a significant hazard to feeding a growing population, but timely detection is challenging due to a lack of infrastructure in many world regions. Finding and detecting plant illness is essential in agricultural production. It takes a great deal of time and effort to find the disease. The agricultural sector can also reap the benefits of machine learning and deep learning. There has been a recent rise in the use of ML & DL techniques in plant disease identification. In this paper, we applied a transfer learning technique for plant disease prediction. We used a 'plant village' dataset with augmentation collected from Kaggle. This abstract presents a comprehensive plant leaf disease detection approach using transfer learning. The proposed method leverages pre-trained deep learning models to extract relevant features from plant leaf images, thereby enhancing the detection accuracy and reducing the need for extensive labelled data. The key components of this approach include data acquisition, pre-processing, model selection, and evaluation. The proposed approach was evaluated using various metrics, including accuracy, precision, recall, and F1 score. The results demonstrated that transfer learning significantly enhanced the models' ability to differentiate between healthy and diseased leaves, with high accuracy and reduced false positives. Moreover, the model's ability to generalise across different plant species and disease types was assessed, highlighting its versatility.