数据与计算发展前沿 ›› 2020, Vol. 2 ›› Issue (2): 111-119.doi: 10.11871/jfdc.issn.2096-742X.2020.02.009

• 专刊: 数据分析技术与应用 • 上一篇    下一篇

基于深度迁移学习的农业病害图像识别

陈雷,袁媛()   

  1. 中国科学院合肥智能机械研究所,安徽 合肥 230031
  • 收稿日期:2019-11-29 出版日期:2020-04-20 发布日期:2020-06-03
  • 通讯作者: 袁媛 E-mail:yuanyuan@iim.ac.cn
  • 作者简介:陈雷,中国科学院合肥智能机械研究所智能认知研究组,博士,副研究员,硕士生导师。发表SCI/EI收录论文30多篇。主要研究方向为人工智能、机器学习理论方法及在计算机视觉、自然语言处理与跨媒体计算中的应用。
    本文主要承担工作为基于深度迁移学习的农业病害图像识别方法与系统的整体框架设计,以及相关的机器学习模型优化方案研究。
    Chen Lei, received his Ph.D. degree from the Institute of Software, Chinese Academy of Sciences in 2010. He is the associate research fellow, master supervisor and the group leader in Intelligent Cognition Group, Institute of Intelligent Machines, Chinese Academy of Sciences. He has published more than 30 papers included in SCI/EI. His research interests include artificial intelligence, machine learning theory and application in computer vision, natural language processing and cross-media computing.
    In this paper he is mainly responsible for the overall framework research and the design of the deep transfer learning based agricultural disease image recognition method and related optimization strategies of machine learning models.
    E-mail: chenlei@iim.ac.cn|袁媛,中国科学院合肥智能机械研究所智能认知研究组,博士,副研究员。发表SCI/EI收录论文20多篇。主要研究方向为人工智能与模式识别。
    本文主要承担工作为农业病害图像处理、具体实验与数据分析。
    Yuan Yuan, received her Ph.D. degree from Anhui Agricultural University in 2013. She is the associate research fellow in Intelligent Cognition Group, Institute of Intelligent Machines, Chinese Academy of Sciences. Her research interests include artificial intelligence and pattern recognition. And she has published over 20 papers included in SCI/EI.
    In this paper she is mainly responsible for agricultural disease image processing, specific experiments execution and data analysis.
  • 基金资助:
    国家自然科学基金面上项目(31871521);中国科学院“十三五”信息化专项(XXH13505-03-104)

Image Recognition of Agricultural Diseases Based on Deep Transfer Learning

Chen Lei,Yuan Yuan()   

  1. Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, Anhui 230031, China
  • Received:2019-11-29 Online:2020-04-20 Published:2020-06-03
  • Contact: Yuan Yuan E-mail:yuanyuan@iim.ac.cn

摘要:

【目的】本文针对农业病害图像识别问题,探讨在不同数据规模条件下融合不同的机器学习方法,以提高农业病害图像识别准确率。【方法】重点围绕农业病害图像数据规模较小条件下的机器学习建模问题,引入深度迁移学习方法,通过具体实验探讨如何提高小样本条件下的建模效果。【结果】在高质量的农业病害图像数据集上,引入深度迁移学习方法能够有效提高农业病害图像识别准确率。【局限】在基于深度神经网络的机器学习方法中,农业病害图像数据集的质量及规模对于建模效果均有一定的影响,未来将进一步探索在数据质量和规模等方面具有更佳普适性的建模方法。【结论】在农业病害图像识别技术研究中,引入深度迁移学习方法能够有效提高小样本条件下的机器学习建模效果以及最终的病害图像识别准确率,可为后续构建各种农业病害图像识别系统平台提供良好的技术支撑。

关键词: 图像识别, 迁移学习, 深度学习, 农业病害, 大数据

Abstract:

[Objective] This paper focuses on the issue of image recognition of agricultural diseases and explores the integration of different machine learning methods under different data scales to improve the accuracy of agricultural disease image recognition. [Methods] Focusing on the problem of machine learning modeling under the condition of small scale of agricultural disease image data, the deep transfer learning method is introduced and some specific experiments are conducted to explore how to improve the modeling effect under the condition of small samples. [Results] On the high-quality agricultural disease image data set, the introduced deep transfer learning method can effectively improve the accuracy of agricultural disease image recognition. [Limitations] In the machine learning method based on deep neural networks, both the quality and the scale of agricultural disease images have certain influence on the modeling effect. In the future, we will further explore the modeling method with better universality in data quality and scale. [Conclusions] In the research of agricultural disease image recognition technology, the adaptation of deep transfer learning method can effectively improve the machine learning modeling effect and the final disease image recognition accuracy under the condition of small samples, which can provide good technical support for the subsequent construction of various agricultural disease image recognition systems.

Key words: image recognition, transfer learning, deep learning, agriculture diseases, big data