Scholarlink

<p>The quantity and quality of production are impacted by the wide presence of illnesses in the tomato crop. Early disease identification utilizing a quick, dependable, non-destructive technology can help farmers combat the issue. To avoid this problem, existing work&#xa0;uses a Support Vector Machine (SVM), k-nearest neighbor (KNN), and Naïve Bayes to classify crop diseases. However, these methods do not perform well with large volume data and consume more computation time. To avoid this problem, this work introduced an improved framework for crop disease classification. In this work, image pre-processing is performed using a median filter. Image enhancement is done by using contour detection. Morphological analysis is computed by using morphological opening and closing operations. Foreground segmentation utilizing fuzzy c-means (FCM) clustering. Feature extraction is executed utilizing the Gray-Level Co-occurrence Matrix (GLCM). Diseases of the tomato crop are categorized utilizing artificial neural networks (ANN). Results demonstrate that the suggested technique produces better accuracy and precision for crop disease.</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

GLCM features and artificial neural network for tomato crop disease classification

  • 期刊论文

  • 发表日期：

    2025年9月17日

查看全文
  • B. Paulchamy,
  • Deepa Sundararajan,
  • T. Kanimozhi,
  • A. Senthilnathan,
  • Sivaram Murugan,
  • M. Thomas Jeyanth

摘要

The quantity and quality of production are impacted by the wide presence of illnesses in the tomato crop. Early disease identification utilizing a quick, dependable, non-destructive technology can help farmers combat the issue. To avoid this problem, existing work uses a Support Vector Machine (SVM), k-nearest neighbor (KNN), and Naïve Bayes to classify crop diseases. However, these methods do not perform well with large volume data and consume more computation time. To avoid this problem, this work introduced an improved framework for crop disease classification. In this work, image pre-processing is performed using a median filter. Image enhancement is done by using contour detection. Morphological analysis is computed by using morphological opening and closing operations. Foreground segmentation utilizing fuzzy c-means (FCM) clustering. Feature extraction is executed utilizing the Gray-Level Co-occurrence Matrix (GLCM). Diseases of the tomato crop are categorized utilizing artificial neural networks (ANN). Results demonstrate that the suggested technique produces better accuracy and precision for crop disease.