Scholarlink

<p>This study introduces PapNet, an innovative deep learning model designed for the accurate identification and classification of papaya leaf diseases. Leveraging advanced architectural features including global average pooling, dense layers, and strategic use of batch normalization and dropout, PapNet demonstrates exceptional performance in distinguishing between various papaya leaf conditions. The model was trained and validated on a&#xa0;diverse dataset of papaya leaf images, encompassing multiple disease states—including anthracnose, bacterial spot, leaf curl, and ring spot—as well as healthy leaves, with a&#xa0;total of 2159 images. Transfer learning techniques and careful hyperparameter tuning were employed to optimize the model’s performance. Results show that PapNet achieves outstanding accuracy across all disease categories, with an overall accuracy exceeding 99.26% during testing. The model demonstrates high precision, recall, and F1 scores across all classes. Confusion matrix analysis reveals minimal misclassifications, highlighting the model’s robustness in differentiating between similar disease states. This research provides a&#xa0;highly accurate tool for the early diagnosis of papaya leaf diseases, achieving an overall accuracy of 99.26%, with potential applications in automated monitoring systems and decision support tools for papaya cultivation.</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

PapNet: An AI-Driven Approach for Early Detection and Classification of Papaya Leaf Diseases

  • 期刊论文

  • 发表日期：

    2025年7月18日

查看全文
  • Yonis Gulzar

摘要

This study introduces PapNet, an innovative deep learning model designed for the accurate identification and classification of papaya leaf diseases. Leveraging advanced architectural features including global average pooling, dense layers, and strategic use of batch normalization and dropout, PapNet demonstrates exceptional performance in distinguishing between various papaya leaf conditions. The model was trained and validated on a diverse dataset of papaya leaf images, encompassing multiple disease states—including anthracnose, bacterial spot, leaf curl, and ring spot—as well as healthy leaves, with a total of 2159 images. Transfer learning techniques and careful hyperparameter tuning were employed to optimize the model’s performance. Results show that PapNet achieves outstanding accuracy across all disease categories, with an overall accuracy exceeding 99.26% during testing. The model demonstrates high precision, recall, and F1 scores across all classes. Confusion matrix analysis reveals minimal misclassifications, highlighting the model’s robustness in differentiating between similar disease states. This research provides a highly accurate tool for the early diagnosis of papaya leaf diseases, achieving an overall accuracy of 99.26%, with potential applications in automated monitoring systems and decision support tools for papaya cultivation.