Real-Time Multiclass Detection of Citrus Leaf Diseases Using an Enhanced YOLOv11 Architecture

Finding rapid and precise methods of identifying diseases is necessary in order to safeguard agricultural yield in today’s global issues of food security. Citrus is a crucial crop in the Pakistani economy, which has decreasing productivity and quality due to foliar diseases. Conventional detection assessment requires manual work, and opinion. The proposed paper develops a Citrus Multiple Leaf Disease Detection system based on YOLOv11 architecture in real-time. To create and develop the CLDD dataset, 812 pictures and 3727 samples of citrus canker, greasy spot, and leaf miner illnesses in the Okara orchards in Punjab, Pakistan have been used. The data set was more appropriate to be generalized by data augmentation, when it had been prepared and annotated. The YOLOv11 model showed remarkable results with a precision of 79.9% and recall of 77.4% and mean Average Precision 81.2% mAP50. This system supports real-time applications by processing photos in 10.5 ms. Ablation research showed that increasing model robustness requires a CSPDarknet53 backbone, a PANet neck, and sophisticated augmentation approaches. Most disease classes performed well; however, citrus greasy spot showed slight variation due to environmental factors and similar illness symptoms. Class-enriched fine-tuning and the construction of artificial datasets should be improved for future use. The findings show that deep learning frameworks can automatically detect citrus illnesses in real time, enabling accurate agricultural solutions for Pakistan and other locations.