Scholarlink

One of the most important industries for the existence of humanity is agriculture. The simultaneous spread of digitalization across all industries made it simpler to complete a variety of challenging activities. Digitalization and technological adaptation are essential for the agricultural sector to both the farmer and the customer will profit. Utilizing technology and routine monitoring makes it possible to spot illnesses in their very early stages and remove them to increase agricultural output. Our research gaps recognize the particular brinjal and corn leaf diseases. A technique for the identification and categorization of illnesses that affect corn and brinjal plants was put out in this work. The publically available, standardized, and trustworthy data set known as the Plant Village Dataset was taken into consideration for this scenario. For the segmentation of the image process the checkpoint method was used to categorize the diseases. The suggested methods have achieved a 96.44% of accuracy rate.

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

Revolutionizing Leaf Disease Management: Harnessing Machine Learning Strategies for Detection and Diagnosis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Simrin Fathima Syed,
  • Madhu Shukla,
  • Vipul Ladva

摘要

One of the most important industries for the existence of humanity is agriculture. The simultaneous spread of digitalization across all industries made it simpler to complete a variety of challenging activities. Digitalization and technological adaptation are essential for the agricultural sector to both the farmer and the customer will profit. Utilizing technology and routine monitoring makes it possible to spot illnesses in their very early stages and remove them to increase agricultural output. Our research gaps recognize the particular brinjal and corn leaf diseases. A technique for the identification and categorization of illnesses that affect corn and brinjal plants was put out in this work. The publically available, standardized, and trustworthy data set known as the Plant Village Dataset was taken into consideration for this scenario. For the segmentation of the image process the checkpoint method was used to categorize the diseases. The suggested methods have achieved a 96.44% of accuracy rate.