Crop Disease Prediction and Stage Risk Assessment using YOLOv11

The proposed research presents an efficient and reliable crop disease detection system using deep learning techniques. The system integrates MobileNetV2 for leaf validation and YOLOv11 for disease classification, ensuring that only relevant inputs are processed and accurately analyzed. The use of the PlantVillage dataset enabled the model to learn distinct disease patterns and achieve high accuracy. The experimental results demonstrate that the system performs effectively in identifying multiple crop diseases with a high level of precision. The implementation of a web-based application using Flask further enhances the usability of the system by allowing users to upload images and receive real-time predictions. This makes the system practical for deployment in agricultural environments. Overall, the proposed solution contributes to the field of precision agriculture by providing an automated, fast, and accurate method for crop disease detection. It has the potential to assist farmers in early diagnosis, reduce crop losses, and improve agricultural productivity.

1.      M. R. Kumar et al., “Deep Learning for Crop Disease Detection using YOLOv8,” IEEE Conference, June 2024. 2.       M. A. Patil and M. Manohar, “Potato Leaf Disease Identification using Hybrid Deep Learning Model,” IEEE Conference, Sept. 2023. 3.      A. S. Chakravarthy and S. Raman, “Early Blight Identification in Tomato Leaves using Deep Learning,” IEEE Conference, Feb. 2020. 4.      P. Sharma, Y. P. S. Berwal, and W. Ghai, “Performance analysis of deep learning CNN models for disease detection in plants using image segmentation,” International Journal of Advanced Research in Computer Science, vol. 11, no. 4, pp. 45–52, 2020.