Corn Rust Disease Recognition Image Dataset

Currently in agricultural production, corn rust disease is one of the main diseases affecting yield and quality. Facing the challenges of outbreaks at different locations and rapid spread, precise identification and real-time monitoring have become urgent solutions. Existing methods rely on manual operations, which are not only inefficient but also limited in recognition accuracy, unable to meet the demands of large-scale production. This dataset focuses on improving the technical level of corn rust disease recognition, supporting the intelligent upgrade of crop health management systems. Data is collected using drones and ground-based camera equipment under various weather conditions, covering different growth stages and regions to ensure data diversity. Quality control involves multiple rounds of annotation, consistency checks, and review by plant pathology experts to improve annotation accuracy. The annotation team consists of professionals with an agricultural science background, involving a team of 10 people. During preprocessing, color correction, size normalization, and background interference filtering are performed, and data is stored in a folder structure organized by region and time.