Abstract:
The emergence of artificial intelligence (AI) in agriculture has revolutionized the approach to plant health and disease control. Traditional methods of plant disease detection, often manual and time-consuming, are rapidly being replaced by AI-driven methods that promise greater accuracy and efficiency. This project aims to develop the detection and classification of plant diseases using advanced AI algorithms, based on previous research in this area. Previous work has shown the effectiveness of deep learning models, especially convolutional neural networks (CNNs), in identifying plant images from digital images with high accuracy. These models have been trained on extensive databases, allowing them to accurately distinguish between different types of diseases. However, challenges such as data scarcity, image quality, and environmental variability limit the use of these systems in real-world settings. Our project tries to solve this limitation by applying a powerful AI framework that combines advanced machine-learning techniques with large and high-quality databases. We developed a new classification algorithm that not only improves the accuracy of disease detection but also improves the model’s ability to generalize to different plant species and environmental conditions. Additionally, we incorporate interpretable AI elements to provide insight into the model’s decision-making process for trust and understanding among end users.
