APPLE LEAF DIESEASE PREDICTION USING TRANSFER LEARNING

Computer Engineering

The automatic detection of diseases in plants is crucial for agricultural sustainability and economic stability. Traditional methods of disease identification,reliant on expert analysis, are slow and impractical for large- scale farms. Consequently, there's a pressing need for automated solutions that can efficiently monitor plant health, detect diseases early, and minimize crop degradation. To address this challenge, we propose an ensemble model comprising pre-trained deeplearning architectures: ResNet, VGG-16, and AlexNet.We employ an ensemble model consisting of ResNet, VGG-16, and AlexNet architectures, pre-trained on large-scale image datasets. This ensemble approach capitalizes on the strengths of each individual model to enhance overall performance. Additionally, we utilize image augmentation techniques to increase the diversity of training data and improve the model's robustness. Our model aims to classify apple tree leaves into several categories: healthy, affected by apple scab, apple cedar rust, or exhibiting multiple diseases. Our research demonstrates significant success, with our proposed model achieving an impressive 96.25% accuracy on thevalidation dataset. This model exhibits promising performance in identifying leaves affected by multiple diseases, achieving remarkable accuracy in this task. The deployment of our proposed model in the agricultural domain holds immense potential for revolutionizing disease detection and plant health monitoring practices. By providing accurate and timely identification of diseased plants, our model empowers farmers to take proactive measures, mitigating crop losses and bolstering agricultural productivity. Our research presents a robust and effective solution for automated disease detection in plants, leveraging deep learning and image augmentation techniques. With its high accuracy and applicability in real- world agricultural settings, our proposed model stands as a promising tool for enhancing crop management practices and ensuring food security

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.