Tomato Maturity & Disease Prediction and Fertilizer Recommendations Using Deep Learning

Abstract

Artificial Intelligence (AI) is the domain that empowers machines to perform tasks such as learning, reasoning, and decision-making. Within AI, Deep Learning (DL) is a sub-domain that uses multi-layered neural networks to automatically extract features and patterns from complex data such as images. This has made DL a powerful tool in fields like agriculture, healthcare and automation. In existing system, they have been carried out on the precise and rapid prediction of tomato maturity using deep learning-based image recognition. The existing study successfully classified tomatoes into different maturity stages, enabling faster and more objective decision making compared to manual inspection. The work demonstrated the potential of computer vision for supporting the agricultural industry by improving harvesting efficiency and product quality. The main disadvantages of the existing system are that it only focused on tomato maturity detection and did not address plant health issues or provide guidance for disease management. To overcome these limitations, our proposed work integrates YOLO-based real-time image detection to not only identify tomato maturity but also detect common tomato plant diseases. Furthermore, the system recommends suitable fertilizers, pesticides and organic manure, making it a comprehensive decision-support tool for farmers.