Scholarlink

This paper introduces a segmented image dataset focused on tomato leaves, designed to expedite the detection of infected areas through a combination of K-means clustering and MobileNet-V3 architecture. Through segmentation, the dataset divides images into distinct regions, facilitating targeted analysis of potentially infected areas. K-means clustering enables the grouping of pixels based on similarity, aiding in the isolation of affected regions. The utilization of MobileNet-V3, a convolutional neural network (CNN) optimized for mobile and embedded devices, enhances the computational efficiency necessary for rapid analysis. By providing this segmented dataset, we aim to offer a resource that accelerates the identification and analysis of infected areas in tomato leaves. The fusion of K-means clustering and MobileNet-V3 technology holds promise for quicker and more precise diagnosis, contributing to improved agricultural practices by enabling early intervention and mitigation of crop diseases. This dataset stands to significantly advance the field of agricultural diagnostics, benefiting farmers, and researchers alike. Our dataset contains total ten classes of disease in tomato plant and 1000 images for each class of disease.

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-Based Tomato Plant Disease Detection Using TomatoDoc Dataset: Agricultural Applications

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ahmad Ashraf Zargar,
  • Debendra Muduli,
  • Mridul Mayankeyshwar,
  • Mamata Wagh,
  • Lookinder Kumar

摘要

This paper introduces a segmented image dataset focused on tomato leaves, designed to expedite the detection of infected areas through a combination of K-means clustering and MobileNet-V3 architecture. Through segmentation, the dataset divides images into distinct regions, facilitating targeted analysis of potentially infected areas. K-means clustering enables the grouping of pixels based on similarity, aiding in the isolation of affected regions. The utilization of MobileNet-V3, a convolutional neural network (CNN) optimized for mobile and embedded devices, enhances the computational efficiency necessary for rapid analysis. By providing this segmented dataset, we aim to offer a resource that accelerates the identification and analysis of infected areas in tomato leaves. The fusion of K-means clustering and MobileNet-V3 technology holds promise for quicker and more precise diagnosis, contributing to improved agricultural practices by enabling early intervention and mitigation of crop diseases. This dataset stands to significantly advance the field of agricultural diagnostics, benefiting farmers, and researchers alike. Our dataset contains total ten classes of disease in tomato plant and 1000 images for each class of disease.