Scholarlink

<p>Fruits are one of the most essential ingredients for the human body, and apples are considered the most nutritious fruit. In this study, we introduce a&#xa0;groundbreaking Apple Leaf Disease Segmentation System, using machine learning and computer vision technologies to boost the precision and efficiency of disease identification in apple leaves. A&#xa0;comprehensive dataset from Kaggle, comprising 200 high-resolution images, served as the foundation for training and validation. The training process adopted an 80–13–7% split for training, validation, and testing, respectively, ensuring a&#xa0;robust and well-validated model. The implementation of YOLOv8 segmentation technology marked a&#xa0;significant breakthrough, showing high accuracy in detecting and segmenting leaves affected by diseases. The training results revealed an impressive mean average precision (mAP) score of 0.97, underscoring the system’s ability to discern and categorize disease-ridden leaves with high confidence. Beyond the exceptional accuracy, the proposed system presents a&#xa0;timely solution for real-world applications in apple orchards. Its autonomous recognition of subtle anomalies in high-resolution images holds promise for rapid and nuanced disease identification. This technological advancement aims to streamline the workflow for apple growers and fortify the global apple industry against the persistent threat of leaf diseases. The fusion of machine learning, computer vision, and YOLOv8 segmentation technology in the Apple Leaf Disease Segmentation System signifies a&#xa0;leap forward in precision agriculture.</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

Automated Identification of Apple Leaf Diseases Under Field Conditions Using a High-Performance Deep Learning Framework

  • 期刊论文

  • 发表日期：

    2026年6月15日

查看全文
  • Chetan Sharma,
  • Priya Sharma,
  • Komal Sharma,
  • Shamneesh Sharma,
  • Hsin-Yuan Chen

摘要

Fruits are one of the most essential ingredients for the human body, and apples are considered the most nutritious fruit. In this study, we introduce a groundbreaking Apple Leaf Disease Segmentation System, using machine learning and computer vision technologies to boost the precision and efficiency of disease identification in apple leaves. A comprehensive dataset from Kaggle, comprising 200 high-resolution images, served as the foundation for training and validation. The training process adopted an 80–13–7% split for training, validation, and testing, respectively, ensuring a robust and well-validated model. The implementation of YOLOv8 segmentation technology marked a significant breakthrough, showing high accuracy in detecting and segmenting leaves affected by diseases. The training results revealed an impressive mean average precision (mAP) score of 0.97, underscoring the system’s ability to discern and categorize disease-ridden leaves with high confidence. Beyond the exceptional accuracy, the proposed system presents a timely solution for real-world applications in apple orchards. Its autonomous recognition of subtle anomalies in high-resolution images holds promise for rapid and nuanced disease identification. This technological advancement aims to streamline the workflow for apple growers and fortify the global apple industry against the persistent threat of leaf diseases. The fusion of machine learning, computer vision, and YOLOv8 segmentation technology in the Apple Leaf Disease Segmentation System signifies a leap forward in precision agriculture.