Scholarlink

Corn is a widely cultivated plant in the world, and it is widely used as the primary source of food for humans, biofuels, livestock fodder, and raw materials for various manufacturing industries. It is an important crop that caters to most food requirements. Different varieties of corn are cultivated, like corn, sweet corn, waxy, dent, amylomaize, and flint. In corn production, plant diseases affect the yield, which needs to be identified quickly to plan the recursive course of action. Plant disease affects all these corns, which needs to be predicted early for remedial measures. In this paper, CNN and Inception-V3 models are used to improve the prediction of plant diseases and automate the prediction process through a computer vision model. These detection models automatically predict the disease symptoms from the plant leaves. The overall analysis shows that the proposed Inception-V3 outperforms other models, with a high accuracy of 98%.

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

Design and Implement a Transfer Learning Model for Disease Detection and Classification for Maize Leaf Dataset

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Kanakam Soujanya,
  • J. Jabez

摘要

Corn is a widely cultivated plant in the world, and it is widely used as the primary source of food for humans, biofuels, livestock fodder, and raw materials for various manufacturing industries. It is an important crop that caters to most food requirements. Different varieties of corn are cultivated, like corn, sweet corn, waxy, dent, amylomaize, and flint. In corn production, plant diseases affect the yield, which needs to be identified quickly to plan the recursive course of action. Plant disease affects all these corns, which needs to be predicted early for remedial measures. In this paper, CNN and Inception-V3 models are used to improve the prediction of plant diseases and automate the prediction process through a computer vision model. These detection models automatically predict the disease symptoms from the plant leaves. The overall analysis shows that the proposed Inception-V3 outperforms other models, with a high accuracy of 98%.