Plants · 2025 · 25 citations · 48 references
AgricultureCrop SciencesPlant SciencesCrop ImprovementMachine LearningVegetable ScienceAgricultural Machine VisionCrop ClassificationYield PredictionAutomated Image RecognitionCrop Disease ClassificationEvaluation MetricsHyperparameter OptimizationHyperparameter TuningLeaf Spot DiseasesLeaf Symptom RecognitionWeight Decay
The automated recognition of disease in tomato leaves can greatly enhance yield and allow farmers to manage challenges more efficiently. This study investigates the performance of YOLOv11 for tomato leaf disease recognition. All accessible versions of YOLOv11 were first fine-tuned on an improved tomato leaf disease dataset consisting of a healthy class and 10 disease classes. YOLOv11m was selected for further hyperparameter optimization based on its evaluation metrics. It achieved a fitness score of 0.98885, with a precision of 0.99104, a recall of 0.98597, and a mAP@.5 of 0.99197. This model underwent rigorous hyperparameter optimization using the one-factor-at-a-time (OFAT) algorithm, with a focus on essential parameters such as batch size, learning rate, optimizer, weight decay, momentum, dropout, and epochs. Subsequently, random search (RS) with 100 configurations was performed based on the results of OFAT. Among them, the C47 model demonstrated a fitness score of 0.99268 (a 0.39% improvement), with a precision of 0.99190 (0.09%), a recall of 0.99348 (0.76%), and a mAP@.5 of 0.99262 (0.07%). The results suggest that the final model works efficiently and is capable of accurately detecting and identifying tomato leaf diseases, making it suitable for practical farming applications.
48
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick et al. · arXiv (Cornell University) · 2015 · 18.2K citations · Full text
Random search for hyper-parameter optimization
James Bergstra, Yoshua Bengio · 2012 · 7.9K citations
On the importance of initialization and momentum in deep learning
Ilya Sutskever, James Martens, George E. Dahl et al. · 2013 · 3.5K citations