Scholarlink

<p>This paper investigates the performance of YOLOv8 classification models:&#xa0;YOLOv8n, YOLOv8s, and YOLOv8m for potato leaf disease classification. Two datasets were used: the Plant-Village (Potato) dataset collected under&#xa0;controlled environmental&#xa0;conditions and the Potato Leaf Disease Dataset captured under uncontrolled field conditions. The models were evaluated independently on each dataset and subsequently&#xa0;on a combined dataset to assess their robustness and generalization. The experimental results demonstrate strong classification performance across all datasets, with test accuracies of 90% on the Potato Leaf Disease Dataset collected under uncontrolled environmental conditions and 96% on the combined dataset. Compared with other models in the literature, including EfficientNetV2B3, MobileNetV3-Large, VGG-16, ResNet50, and DenseNet121, the YOLOv8n model achieved the best&#xa0;performance&#xa0;on the uncontrolled dataset, attaining 90% accuracy, 92% precision, 88% recall, and an F1-score of 90% on the uncontrolled dataset. On the combined dataset, YOLOv8m achieved 96% accuracy,&#xa0;96% precision, 94% recall, and F1-score of&#xa0;95%, demonstrating strong generalization and robustness under diverse imaging conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The Application of YOLOv8n, YOLOv8s, and YOLOv8m for Potato Leaf Diseases Classification

  • 期刊论文

  • 发表日期：

    2026年2月16日

查看全文
  • Eman H. Alkhammash

摘要

This paper investigates the performance of YOLOv8 classification models: YOLOv8n, YOLOv8s, and YOLOv8m for potato leaf disease classification. Two datasets were used: the Plant-Village (Potato) dataset collected under controlled environmental conditions and the Potato Leaf Disease Dataset captured under uncontrolled field conditions. The models were evaluated independently on each dataset and subsequently on a combined dataset to assess their robustness and generalization. The experimental results demonstrate strong classification performance across all datasets, with test accuracies of 90% on the Potato Leaf Disease Dataset collected under uncontrolled environmental conditions and 96% on the combined dataset. Compared with other models in the literature, including EfficientNetV2B3, MobileNetV3-Large, VGG-16, ResNet50, and DenseNet121, the YOLOv8n model achieved the best performance on the uncontrolled dataset, attaining 90% accuracy, 92% precision, 88% recall, and an F1-score of 90% on the uncontrolled dataset. On the combined dataset, YOLOv8m achieved 96% accuracy, 96% precision, 94% recall, and F1-score of 95%, demonstrating strong generalization and robustness under diverse imaging conditions.