Scholarlink

<p>Timely detection of plant leaf diseases is critical for effective crop management and enhanced agricultural productivity. This study presents a deep learning-based method for the automatic identification of plant leaf diseases using a customized Convolutional Neural Network (CNN) model. The research utilizes the New Plant Diseases Dataset, comprising 70,295 training images and 17,572 validation images spanning 38 distinct foliage leaf disease classes. Image preprocessing steps such as rescaling and normalization were performed prior to model training. The proposed CNN model achieved high classification performance, with an overall accuracy of 99.29%, precision of 99.29%, recall of 99.28%, and an F1-score of 99.28%, outperforming other pre-trained models such as VGG16, ResNet50, DenseNet201, MobileNetV2, and Xception. The high performance of the model can make it an ideal diagnostic tool for farmers to take timely actions to prevent crop loss.</p>

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

Automated Convolutional Neural Network Based Framework for Plant Leaf Disease Diagnosis

  • 期刊论文

  • 发表日期：

    2026年4月17日

查看全文
  • Komalpreet Kaur,
  • Hardeep Kaur

摘要

Timely detection of plant leaf diseases is critical for effective crop management and enhanced agricultural productivity. This study presents a deep learning-based method for the automatic identification of plant leaf diseases using a customized Convolutional Neural Network (CNN) model. The research utilizes the New Plant Diseases Dataset, comprising 70,295 training images and 17,572 validation images spanning 38 distinct foliage leaf disease classes. Image preprocessing steps such as rescaling and normalization were performed prior to model training. The proposed CNN model achieved high classification performance, with an overall accuracy of 99.29%, precision of 99.29%, recall of 99.28%, and an F1-score of 99.28%, outperforming other pre-trained models such as VGG16, ResNet50, DenseNet201, MobileNetV2, and Xception. The high performance of the model can make it an ideal diagnostic tool for farmers to take timely actions to prevent crop loss.