Scholarlink

<p>This study addresses the critical issue of automated plant disease detection, offering a solution to enhance agricultural productivity and mitigate losses. Traditional disease detection methods involve labour-intensive manual scouting and visual inspection, which are time-consuming and prone to errors. In response to these challenges, this research harnesses advanced image processing and machine learning algorithms to develop an automated mechanism for disease detection in cultivated plants. Local Binary Pattern (LBP) is used for texture feature extraction, and Decision Tree, Random Forest, Logistic Regression, Gradient Boosting, Naive Bayes, and KNN are used for detection. Deep learning techniques, specifically Faster R-CNN with the ResNet50 deep feature extractor, are utilised to detect and classify various plant diseases. The proposed system is trained and tested on a diverse dataset encompassing a wide range of plant species and disease types. Our system identifies plant diseases through the images of plant leaves, provide accurate information to farmers.</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

A Progressive Hierarchical Model for Plant Disease Diagnosis

  • 期刊论文

  • 发表日期：

    2025年1月24日

查看全文
  • Parveen Dhoundiyal,
  • Vikrant Sharma,
  • Satvik Vats,
  • Priyanshu Rawat

摘要

This study addresses the critical issue of automated plant disease detection, offering a solution to enhance agricultural productivity and mitigate losses. Traditional disease detection methods involve labour-intensive manual scouting and visual inspection, which are time-consuming and prone to errors. In response to these challenges, this research harnesses advanced image processing and machine learning algorithms to develop an automated mechanism for disease detection in cultivated plants. Local Binary Pattern (LBP) is used for texture feature extraction, and Decision Tree, Random Forest, Logistic Regression, Gradient Boosting, Naive Bayes, and KNN are used for detection. Deep learning techniques, specifically Faster R-CNN with the ResNet50 deep feature extractor, are utilised to detect and classify various plant diseases. The proposed system is trained and tested on a diverse dataset encompassing a wide range of plant species and disease types. Our system identifies plant diseases through the images of plant leaves, provide accurate information to farmers.