Abstract:
Plant leaf diseases have recently become a major worry for farmers. This is a danger to both farmers and the country, which depends on agriculture. In this aspect, conventional identification techniques may not be very efficient. The country's agriculture industry is already suffering from a lack of sophisticated identification methods. In this project, my overarching goal is to use smart farming to battle plant diseases, such as those that impact trees and crops. This thesis focuses on applying deep learning for smart farming to identify diseases in plants from the Solanaceae family. The goal is to create an automated illness detection system that is accurate and effective, allowing for prompt treatments. Two deep-learning models are trained on a large dataset, and their performance is assessed. The results show that the suggested method is successful in locating illnesses, underscoring its potential to enhance agricultural operations. The project investigates the use of deep learning methods in disease diagnosis for plants belonging to the Solanaceae family with the goal of enabling early illness detection and intervention. The research demonstrates the efficacy of the recommended deep learning technique and its potential to improve agricultural practices by creating an effective system utilizing a substantial dataset.
Keywords: Smart farming, disease detection, deep learning, Solanaceae family, timely interventions, agricultural practices, automated illness detection.
