Scholarlink

One of the most important crops in agriculture, sugarcane, is susceptible to illnesses that lead to various diseases, which severely and strongly impact yield and quality. Early and accurate identification is necessary to minimize such losses and ensure food safety. Traditional methods, like manual observation, are labor-intensive with great chances of error. This research utilized deep learning techniques by five CNN architectures to identify diseases in sugarcane, such as ResNet50, VGG16, EfficientNetB3, EfficientNetB5, and InceptionV3. Among these, VGG16 performed well with 99.6%. Images from a publicly available dataset with 2569 images were used for the training, and were categorized into five categories: healthy leaves, rust, yellow leaf disease, mosaic, and red rot. This enables early identification, targeted treatment, and optimized crop management through the automation of disease detection. This not only enhances sugarcane productivity but also reduces environmental impact, ensuring economic stability for the farmers.

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

Sugarcane Leaf Disease Detection Using Deep Learning Approaches

  • 章节

  • 发表日期：

    2026年

查看全文
  • N. T. Renukadevi,
  • K. Saraswathi,
  • E. Roshini,
  • M. G. Lakshitha,
  • S. Prateeksha

摘要

One of the most important crops in agriculture, sugarcane, is susceptible to illnesses that lead to various diseases, which severely and strongly impact yield and quality. Early and accurate identification is necessary to minimize such losses and ensure food safety. Traditional methods, like manual observation, are labor-intensive with great chances of error. This research utilized deep learning techniques by five CNN architectures to identify diseases in sugarcane, such as ResNet50, VGG16, EfficientNetB3, EfficientNetB5, and InceptionV3. Among these, VGG16 performed well with 99.6%. Images from a publicly available dataset with 2569 images were used for the training, and were categorized into five categories: healthy leaves, rust, yellow leaf disease, mosaic, and red rot. This enables early identification, targeted treatment, and optimized crop management through the automation of disease detection. This not only enhances sugarcane productivity but also reduces environmental impact, ensuring economic stability for the farmers.