Scholarlink

The progress of any country depends on its agricultural sector. In this context, “cash crops” refer to cotton and other significant crops. The vast majority of crop-damaging pathogens also impact cotton. The economic impact of cotton leaf diseases is substantial. To mitigate their impact, timely identification and intervention are critical. The current investigation introduces a deep-learning approach to forecast cotton leaf diseases by the pre-trained ResNet-50 convolutional neural network framework. In ResNet, layer training can now proceed significantly faster. Layer training can now proceed at a significantly faster pace. The proposed model incorporates ResNet-50 for bypass connections. The dataset contains images encompassing healthy and unhealthy cotton leaves. We test the suggested model using Kaggle’s Cotton Leaf and Disease datasets. The proposed approach outperforms the alternatives with an accuracy rate of 98.6%.

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

Prediction of Cotton Leaf Disease Using the ResNet Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Animesh Srivastava,
  • Nidhi,
  • Shivani Chauhan,
  • Vikash Sawan,
  • Navin Garg

摘要

The progress of any country depends on its agricultural sector. In this context, “cash crops” refer to cotton and other significant crops. The vast majority of crop-damaging pathogens also impact cotton. The economic impact of cotton leaf diseases is substantial. To mitigate their impact, timely identification and intervention are critical. The current investigation introduces a deep-learning approach to forecast cotton leaf diseases by the pre-trained ResNet-50 convolutional neural network framework. In ResNet, layer training can now proceed significantly faster. Layer training can now proceed at a significantly faster pace. The proposed model incorporates ResNet-50 for bypass connections. The dataset contains images encompassing healthy and unhealthy cotton leaves. We test the suggested model using Kaggle’s Cotton Leaf and Disease datasets. The proposed approach outperforms the alternatives with an accuracy rate of 98.6%.