Scholarlink

Plant diseases present a serious threat to all forms of life. Early detection is vital, which allows farmers to take prompt action, improving both their response and productivity. Our research centers on 5 main rice leaf diseases: bacterial leaf blight, leaf blast, brown spot, leaf scald, and narrow brown spot, along with a category for healthy leaves. Additionally, we examine two types of betel leaves categorized as healthy and unhealthy. This study proposes an innovative deep ensemble model that combines the EfficientNetV2L, InceptionResNetV2, and Xception architectures. This model addresses issues of underfitting and performance by utilizing advanced techniques, including Global Average Pooling, L2 regularization, data augmentation, batch normalization, preprocessing, dropout, PReLU activation, and multiple dense layers. This robust approach surpasses existing models by managing both underfitting and overfitting, while delivering superior performance.

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

Optimizing Plant Disease Detection with a Novel Deep Ensemble Framework

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Rydhm Beri,
  • Parul Sachdeva

摘要

Plant diseases present a serious threat to all forms of life. Early detection is vital, which allows farmers to take prompt action, improving both their response and productivity. Our research centers on 5 main rice leaf diseases: bacterial leaf blight, leaf blast, brown spot, leaf scald, and narrow brown spot, along with a category for healthy leaves. Additionally, we examine two types of betel leaves categorized as healthy and unhealthy. This study proposes an innovative deep ensemble model that combines the EfficientNetV2L, InceptionResNetV2, and Xception architectures. This model addresses issues of underfitting and performance by utilizing advanced techniques, including Global Average Pooling, L2 regularization, data augmentation, batch normalization, preprocessing, dropout, PReLU activation, and multiple dense layers. This robust approach surpasses existing models by managing both underfitting and overfitting, while delivering superior performance.