Development of a Mobile-Based Corn Leaf Disease Detection Application Using YOLOv11

Abstract

Corn is a critical crop for agricultural production and food security. However, it is susceptible to several foliar diseases that can adversely impact its growth and quality. Traditional visual assessment methods are often labour-intensive and prone to inaccuracies. This study proposes a Corn Leaf Disease Detection System that utilizes convolutional neural networks (CNNs) and compares the performance of the YOLOv8, YOLOv9, and YOLOv11 models. The methodology involves acquiring high-quality images of corn leaves affected by diseases such as Northern Leaf Blight and Common Rust. These images undergo a pre-processing phase to enhance their quality and are standardized for input into the detection model. The CNN is employed for detailed classification, while YOLOv11 is implemented for real-time detection. Among the tested models, YOLOv11 demonstrated the highest overall F1-score of 0.93, with a precision of 0.94 and recall of 0.92 at epoch 100. These results substantiate the system’s operational efficiency and robustness.