AGROVISION: AI-Powered Pest and Disease Detection System

Agriculture remains one of the most important sectors supporting global food security and rural livelihoods. However, crop productivity is significantly affected by pests and plant diseases, which lead to major economic losses for farmers each year. According to recent agricultural studies, approximately 20–40% of global crop production is lost annually due to pests and plant diseases if proper monitoring and timely treatment are not implemented. Traditional methods of identifying plant diseases rely heavily on manual inspection performed by farmers or agricultural experts, which can be time-consuming, labor-intensive, and sometimes inaccurate when early symptoms are difficult to observe with the naked eye. Therefore, there is an increasing need for intelligent technological solutions that can assist farmers in detecting plant health issues at an early stage and taking appropriate preventive actions. Recent advancements in Artificial Intelligence (AI), Machine Learning (ML), and computer vision technologies have opened new opportunities for developing automated crop monitoring systems capable of identifying pests and diseases with high accuracy. Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated remarkable performance in image recognition tasks and are widely used for plant disease classification from leaf images [1]. These models can learn complex visual patterns such as leaf discoloration, spots, texture variations, and structural damage that are typically associated with plant infections. This paper presents AGROVISION, an intelligent AI-based pest and disease detection system designed to support smart