Scholarlink

This paper proposes a unique way for mint plant disease diagnosis that improves accuracy by employing the You Only Look Once (YOLO) algorithm with deep reinforcement learning. The YOLO method is used to extract differentiating traits from mint plant photos, portraying both healthy and damaged plant portions properly. This data is then analysed by a deep reinforcement learning system to identify diseases precisely. Extensive tests on a large collection of mint plant photos with annotated disease conditions proved the usefulness of the suggested technique. The results demonstrated a significant improvement in illness diagnosis accuracy when compared to conventional approaches. The YOLO method was successful in recognizing substantial trends, and the reinforcement learning component improved the detection process even further. This study has the potential to change mint plant disease diagnosis in the agricultural industry by offering a dependable approach for early disease identification. This enables swift action to limit disease spread and increase agricultural productivity. The research lays the path for comparable applications in other domains of agriculture.

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

Enhancing Mint Plant Disease Detection Accuracy Through Deep Reinforcement Learning with YOLO Algorithm

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • V. Manikandan,
  • P. Dinesh,
  • M. Chantilyan,
  • C. Gomathi

摘要

This paper proposes a unique way for mint plant disease diagnosis that improves accuracy by employing the You Only Look Once (YOLO) algorithm with deep reinforcement learning. The YOLO method is used to extract differentiating traits from mint plant photos, portraying both healthy and damaged plant portions properly. This data is then analysed by a deep reinforcement learning system to identify diseases precisely. Extensive tests on a large collection of mint plant photos with annotated disease conditions proved the usefulness of the suggested technique. The results demonstrated a significant improvement in illness diagnosis accuracy when compared to conventional approaches. The YOLO method was successful in recognizing substantial trends, and the reinforcement learning component improved the detection process even further. This study has the potential to change mint plant disease diagnosis in the agricultural industry by offering a dependable approach for early disease identification. This enables swift action to limit disease spread and increase agricultural productivity. The research lays the path for comparable applications in other domains of agriculture.