International Journal of Computer Techniques Volume 12 Issue 4 | Deep Learning with YOLO for Smart Agriculture: A Review of Plant Leaf Disease Detection
Deep Learning with YOLO for Smart Agriculture: A Review of Plant Leaf Disease Detection
Authors:
Dr. R.P. Ponnusamy, Principal, Madha Engineering College, Chennai
Dr. V. Hema, Principal, Swami Dayananda College of Arts & Science, Manjakkudi, Thiruvarur
Dr. T. Nagarathinam, Assistant Professor, Department of Computer Science, Swami Dayananda College of Arts & Science
Dr. K. Arulmozhi, Assistant Professor, Department of Computer Science, Swami Dayananda College of Arts & Science
Emails: hema.rengamani78@gmail.com, atnaga123@gmail.com, balajianjali2004@gmail.com
Journal: International Journal of Computer Techniques (IJCT)
Volume: 12 | Issue: 4 | Publication Date: July – August 2025
ISSN: 2394-2231 | Journal URL: https://ijctjournal.org/
Abstract
This paper reviews the evolution and application of YOLO (You Only Look Once) models for plant leaf disease detection. From YOLOv1 to YOLOv11, innovations in architecture have enabled real-time, high-accuracy detection across crops like tomato, rice, maize, tea, and apple. The study highlights challenges such as dataset limitations and hardware constraints, and explores emerging trends including attention mechanisms and pest detection.
Keywords
YOLO, Deep Learning, Plant Disease Detection, Smart Agriculture, Object Detection, CNN, Real-Time Monitoring, Crop Health, Precision Farming
Conclusion
YOLO-based models have revolutionized plant disease detection with real-time capabilities and high accuracy. Despite challenges in deployment and generalization, the integration of advanced techniques and hardware optimization positions YOLO as a key tool in smart agriculture. Future work may focus on expanding datasets, improving field robustness, and integrating with IoT platforms.
References
Includes 19 references from CVPR, ECCV, IEEE, arXiv, and agricultural technology conferences covering YOLO versions, CNN architectures, and crop-specific detection studies.
3 comments