Speaker
Description
Abstract
Plant diseases are a major constraint to crop productivity and food security, often causing substantial economic losses worldwide. Early and accurate detection of plant diseases is critical for effective management and mitigation, yet traditional methods rely heavily on manual inspection and expert knowledge, which can be time-consuming, inconsistent, and inaccessible to many farmers. This study proposes an artificial intelligence (AI)-based approach for the early detection of plant diseases using image recognition techniques. High-resolution images of healthy and diseased leaves were collected from multiple sources, including field surveys and publicly available datasets, and underwent preprocessing steps such as resizing, normalization, and data augmentation to improve model robustness. A convolutional neural network (CNN) was developed to classify the images into different disease categories, and the model was trained and evaluated using standard performance metrics including accuracy, precision, recall, and F1-score. The results demonstrated that the model can accurately identify multiple plant diseases with high reliability, providing a faster and more consistent diagnostic method compared to traditional approaches. To enhance usability, the trained model was integrated into a mobile application that allows farmers to capture leaf images and receive immediate diagnostic feedback, facilitating timely interventions and informed decision-making. This approach combines machine learning, computer vision, and mobile technology to improve plant health monitoring, reduce crop losses, and support sustainable agricultural practices. The study highlights the potential of digital and AI-driven tools to transform plant protection strategies, promote precision agriculture, and empower farmers, especially in resource-limited rural areas. The proposed framework is scalable and adaptable, offering opportunities for expansion to multiple crops and disease types, thereby contributing to smarter, technology-driven agricultural systems.
Key words: Artificial Intelligence (AI), Convolutional Neural Networks (CNN), Image Recognition, Precision Agriculture, Sustainable Farming
