Real-Time Plant Disease Detection in Smart Agriculture Using a YOLO11-Based Deep Learning Model
Students & Supervisors
Student Authors
Supervisors
Abstract
Plant diseases are one of the biggest challenges to agriculture. They reduce the quality of the produce, reduce yield, and can lead to economic losses that are substantial. Early and accurate detection of diseases is very important as this helps farmers to respond quickly and not suffer huge losses. Traditional methods are dependent on visual observation, which is prone to being fatiguing, time-consuming, and inconsistent at the scale necessary for agriculture. Deep learning methods are faster and more consistent. Here, we adopted the YOLO11x model for detection of disease in four crucial crops, i.e., eggplant, chili, potato, and tomato. The model is trained and tested on a sizeable data set that includes diverse choices of plant disease images. We implemented data augmentation to make the system more resilient under diverse field conditions such as lighting and overlapping leaves. The model achieved a significant improvement in disease classification, reaching an accuracy of 99%. The results show that YOLO11x can potentially be an efficient plant disease detection system. It can promote precision agriculture and smart agriculture by helping farmers detect potential problems before they arise. The system can reduce damage to crops, optimize food production, and promote sustainable farming.
Keywords
Publication Details
- Type of Publication:
- Conference Name: International Conference on Computer and Information Technology
- Date of Conference: 19/12/2025 - 19/12/2025
- Venue: Long Beach Hotel, Cox's Bazar, Bangladesh
- Organizer: IEEE Bangladesh Section