欢迎访问《中国农学通报》，
中国农学通报

中国农学通报 ›› 2023, Vol. 39 ›› Issue (25): 147-154.doi: 10.11924/j.issn.1000-6850.casb2023-0216

• 农业信息·科技教育 • 上一篇    下一篇

融合注意力机制和多尺度卷积的小麦病害识别模型

卢筱伟(), 孟志青()   

  1. 浙江工业大学管理学院，杭州 310023
  • 收稿日期:2023-03-20 修回日期:2023-05-15 出版日期:2023-09-05 发布日期:2023-08-28
  • 通讯作者: 孟志青，男，1962年出生，浙江杭州人，教授，博士，研究方向为数据挖掘与优化理论。通信地址：310023 浙江省杭州市浙江工业大学屏峰校区，E-mail：mengzhiqing@zjut.edu.cn。
  • 作者简介:
    卢筱伟，男，1995年出生，浙江台州人，硕士研究生，研究方向为数据挖掘与机器学习。通信地址：310023 浙江省杭州市浙江工业大学屏峰校区，E-mail：。
  • 基金资助:
    国家自然科学基金项目“多凸规划目标罚函数的精确性理论与算法研究”(11871434)

Wheat Disease Recognition Model Integrating Attention Mechanism and Multi-scale Convolution

LU Xiaowei(), MENG Zhiqing()   

  1. School of Management, Zhejiang University of Technology, 310023
  • Received:2023-03-20 Revised:2023-05-15 Online:2023-09-05 Published:2023-08-28

RichHTML

3

PDF (PC)

35

摘要：

为解决小麦病害识别这一问题，提出基于深度卷积神经网络的分类识别技术。笔者将提出的方法与已有的小麦病害识别模型进行了比较和分析，并探讨深度学习技术在农业病害识别和监测领域的应用前景结果。实验结果表明，基于深度卷积神经网络的方法比传统的EfficientNet网络在准确率、精确率、召回率、F1等指标分别提升了3%、4%、5%、5%，可以有效识别小麦病害。通过消融实验验证了提出各部分的有效性，并且模型的收敛速度也显著优于现有的模型。该识别模型的提出为农业生产提供了有力的支持，有望成为未来农业病害识别和监测领域的主要技术手段之一。

关键词: 图像识别, 病害识别, 深度卷积神经网络, 注意力机制, 植物保护

Abstract:

Classification and recognition techniques based on deep convolutional neural networks are proposed to solve the wheat disease identification problem. In this paper, the proposed method is compared and analyzed against existing wheat disease recognition models, and the promising results of applying deep learning technology in agricultural disease identification and monitoring are discussed. The experimental results show that the method based on the deep convolutional neural network is 3%, 4%, 5%, and 5% higher than the traditional EfficientNet network in terms of accuracy, precision, recall, and F1, and can effectively identify wheat disease. We verified the effectiveness of the proposed components by ablation experiments, and the convergence speed of the model was significantly better than the existing models. The proposed identification model provides strong support for agricultural production and is expected to become one of the main technical tools in the field of agricultural disease identification and monitoring in the future.

Key words: image recognition, disease recognition, deep convolutional neural network, attention mechanism, crop protection