Scholarlink

One of fruit that is high in nutrients worldwide in the apple. Controlling apple fruit diseases is one of the most important factors in the development of apples. Apple fruit diseases can cause significant losses, both in terms of quantity and quality of the harvest of the fruit industry. Early detection of diseases in apple leaves can help prevent losses in apple production. Identification of apples is often done manually, namely by looking at the object directly, of course this takes a very long time and is less effective when the amount of apple data is quite large with limited resources. This study used an image dataset consisting of 13,689 images of diseased leaves with 4 disease classes and 1 healthy leaf class. The four disease classes are Scab, Powdery Mildew, Apple Rust, Frog Eye Leaf Spot, and the healthy leaf class is Healthy Leaf. In this research, disease detection was carried out on apple leaves using the Convolutional Neural Network (CNN) model using EfficientNet architecture, obtaining the highest accuracy value of 98%.

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

Use of Convolutional Neural Network (CNN) with EfficientNet Model for Disease Detection in Apple Leaves

  • 章节

  • 发表日期：

    2026年

查看全文
  • Julius Salim,
  • Kezia Asmaradita,
  • Maria Susan Anggreainy,
  • Ajeng Wulandari,
  • Meily Zanetta,
  • Michael Kristianto,
  • Muhammad Fauzi

摘要

One of fruit that is high in nutrients worldwide in the apple. Controlling apple fruit diseases is one of the most important factors in the development of apples. Apple fruit diseases can cause significant losses, both in terms of quantity and quality of the harvest of the fruit industry. Early detection of diseases in apple leaves can help prevent losses in apple production. Identification of apples is often done manually, namely by looking at the object directly, of course this takes a very long time and is less effective when the amount of apple data is quite large with limited resources. This study used an image dataset consisting of 13,689 images of diseased leaves with 4 disease classes and 1 healthy leaf class. The four disease classes are Scab, Powdery Mildew, Apple Rust, Frog Eye Leaf Spot, and the healthy leaf class is Healthy Leaf. In this research, disease detection was carried out on apple leaves using the Convolutional Neural Network (CNN) model using EfficientNet architecture, obtaining the highest accuracy value of 98%.