Crops Disease Detection using Machine Learning Techniques and CNN

Abstract

Crop disease detection is crucial for food security and agricultural productivity. Traditional methods are time-consuming and rely on human expertise. This research proposes an automated system using machine learning techniques to accurately identify diseases affecting crops based on plant leaves. The system uses Machine learning algorithms to analyze images and classify them into healthy or diseased categories. A comprehensive dataset is used to train and validate the model, and transfer learning is employed to enhance performance. Attention mechanisms are incorporated to improve interpretability. The trained model shows promising results in accuracy, sensitivity, and specificity. The system is scalable and adaptable to different crops and diseases, making it applicable across various agricultural settings. This machine learning-based approach could revolutionize agricultural practices, reducing environmental impact and improving crop yields.