Corn Leaf Disease Recognition Dataset

Current agriculture faces challenges of low disease detection efficiency and low recognition accuracy. Traditional manual detection methods are time-consuming, labor-intensive, and prone to errors. Existing automated detection solutions often rely on small-scale datasets, making it difficult to adapt to diverse disease manifestations. This dataset aims to provide a comprehensive corn leaf disease recognition dataset to support the training and evaluation of object detection algorithms. The dataset includes annotated images of various common diseases, aiming to improve the accuracy and efficiency of agricultural disease recognition. Data collection uses high-resolution cameras under natural light conditions to ensure image quality. To ensure data quality, multiple rounds of annotation and expert review processes are adopted to ensure annotation consistency and accuracy. Data is stored in JPEG format and organized using standard folder structures for easy subsequent use and management.