Scholarlink

Machine learning is now widely used in different fields, one of which is agriculture, where leaves and plant diseases can be detected and classified from images. This paper explores the use of machine learning techniques in leaf detection, focusing on four models: The most common are CNN, ResNet, MobileNet, as well as the VGG19 model. These are the models used in apple diseases, particularly in the identification and diagnosis of diseases on apple leaves, and they work very well. This paper also discusses how data pre-processing, feature extraction, and classification algorithms influenced the identification of the leaves. Also, the paper covers the advantages of using such applications as TensorFlow, Keras, and ChatGPT in machine learning projects, the improvement of the existing models, and the extensive diagnosis and treatment plan. Therefore, the aim is achieved, and the findings enhance disease diagnosis and control in agriculture for efficient farming.

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

Deep Learning Models for Accurate Leaf Detection and Disease Diagnosis in Agriculture

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Utkarsh Ranjan,
  • Sunil Pathak,
  • Bhupesh Kumar Singh,
  • Kamana

摘要

Machine learning is now widely used in different fields, one of which is agriculture, where leaves and plant diseases can be detected and classified from images. This paper explores the use of machine learning techniques in leaf detection, focusing on four models: The most common are CNN, ResNet, MobileNet, as well as the VGG19 model. These are the models used in apple diseases, particularly in the identification and diagnosis of diseases on apple leaves, and they work very well. This paper also discusses how data pre-processing, feature extraction, and classification algorithms influenced the identification of the leaves. Also, the paper covers the advantages of using such applications as TensorFlow, Keras, and ChatGPT in machine learning projects, the improvement of the existing models, and the extensive diagnosis and treatment plan. Therefore, the aim is achieved, and the findings enhance disease diagnosis and control in agriculture for efficient farming.