Scholarlink

<p>Tomato plant diseases significantly impact agricultural productivity, posing a challenge for sustainable crop management. This study proposes a deep learning-based framework for accurate and automated detection of tomato plant diseases using the Inception v4 convolutional neural network (CNN) and YOLOv8 (You Only Look Once, version 8) object detection model. A curated dataset of tomato plant images, encompassing various diseases such as bacterial spot, early blight, late blight, and leaf mold, alongside healthy samples, was developed for training and evaluation. The Inception v4 CNN is employed for feature extraction and classification, while YOLOv8 is utilized for real-time disease detection and localization. Experimental results demonstrate that the combined use of Inception v4 and YOLOv8 achieves a classification accuracy of 96% and a mean Average Precision (mAP@0.5) of 86% for leaf disease detection with precision and recall improving by 5.3% and 4.8%, respectively, compared to existing methods. The proposed model highlights the potential of deep learning techniques to enhance early disease diagnosis, enabling farmers to take timely and effective measures to mitigate crop losses.</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

Deep learning based plant health disease detection in tomatoes using inception v4 convolutional neural network and YOLO V8

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月22日

查看全文
  • B. Sowmya,
  • S. Guruprasad

摘要

Tomato plant diseases significantly impact agricultural productivity, posing a challenge for sustainable crop management. This study proposes a deep learning-based framework for accurate and automated detection of tomato plant diseases using the Inception v4 convolutional neural network (CNN) and YOLOv8 (You Only Look Once, version 8) object detection model. A curated dataset of tomato plant images, encompassing various diseases such as bacterial spot, early blight, late blight, and leaf mold, alongside healthy samples, was developed for training and evaluation. The Inception v4 CNN is employed for feature extraction and classification, while YOLOv8 is utilized for real-time disease detection and localization. Experimental results demonstrate that the combined use of Inception v4 and YOLOv8 achieves a classification accuracy of 96% and a mean Average Precision (mAP@0.5) of 86% for leaf disease detection with precision and recall improving by 5.3% and 4.8%, respectively, compared to existing methods. The proposed model highlights the potential of deep learning techniques to enhance early disease diagnosis, enabling farmers to take timely and effective measures to mitigate crop losses.