Scholarlink

A serious problem for agriculture, banana leaf disease is brought on by bacterial, viral, or fungal infections and can cause large crop losses. Worldwide farmers are seriously threatened by the recurrent incidence of diseases like Banana Bunchy Top Virus, Panama disease, and Black Sigatoka, which lower yields and compromise food security. In order to prevent extensive harm to banana crops, rapid handling and correct diagnosis of these diseases are essential. In order to protect farmers’ livelihoods, guarantee healthy crop production, and reduce financial losses in the agriculture industry, timely identification techniques are essential. This paper showcases a comparative analysis with other state-of-the-art models for Banana Leaf disease. Using a banana leaf disease image dataset, this research compares the proposed BananaLeaf-Net model to a wide range of CNN-based architectures, such as EfficientNet B0, EfficientNet B1, EfficientNet B2, EfficientNet B3, MobileNetV2,ResNet50, ResNet101, ResNet152V, and DenseNet201. This study examines the most recent Banana Leaf Disease classification algorithms in this context to increase classification accuracy; our proposed BananaLeaf-Net model outperforms base models with an exceptional accuracy of 97%.

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

BananaLeaf-Net: A Proposed Deep Learning Model for Accurate Classification of Banana Leaf Diseases

  • 章节

  • 发表日期：

    2025年

查看全文
  • Anika Saba Ibte Sum,
  • Anik Kumar Saha,
  • Kamruddin Md. Nur,
  • Khandaker Tabin Hasan

摘要

A serious problem for agriculture, banana leaf disease is brought on by bacterial, viral, or fungal infections and can cause large crop losses. Worldwide farmers are seriously threatened by the recurrent incidence of diseases like Banana Bunchy Top Virus, Panama disease, and Black Sigatoka, which lower yields and compromise food security. In order to prevent extensive harm to banana crops, rapid handling and correct diagnosis of these diseases are essential. In order to protect farmers’ livelihoods, guarantee healthy crop production, and reduce financial losses in the agriculture industry, timely identification techniques are essential. This paper showcases a comparative analysis with other state-of-the-art models for Banana Leaf disease. Using a banana leaf disease image dataset, this research compares the proposed BananaLeaf-Net model to a wide range of CNN-based architectures, such as EfficientNet B0, EfficientNet B1, EfficientNet B2, EfficientNet B3, MobileNetV2,ResNet50, ResNet101, ResNet152V, and DenseNet201. This study examines the most recent Banana Leaf Disease classification algorithms in this context to increase classification accuracy; our proposed BananaLeaf-Net model outperforms base models with an exceptional accuracy of 97%.