欢迎您访问《智慧农业(中英文)》官方网站! English

Smart Agriculture ›› 2019, Vol. 1 ›› Issue (2): 34-44.doi: 10.12133/j.smartag.2019.1.2.201812-SA007

• 信息感知与获取 • 上一篇    下一篇

基于迁移学习与卷积神经网络的玉米植株病害识别

陈桂芬*(), 赵姗, 曹丽英, 傅思维, 周佳鑫   

  1. 吉林农业大学信息技术学院,长春 130118
  • 收稿日期:2018-12-20 修回日期:2019-04-15 出版日期:2019-04-30
  • 基金资助:
    国家“863”项目(2006AA10A309);国家星火计划(2015GA660004);吉林省重点科技研发项目(20180201073SF);吉林省科技厅科技引导计划(20160412034XH)
  • 通信作者:

Corn plant disease recognition based on migration learning and convolutional neural network

Chen Guifen*(), Zhao Shan, Cao Liying, Fu Siwei, Zhou Jiaxin   

  1. School of Information Technology, Jilin Agricultural University, Changchun, 130118, China
  • Received:2018-12-20 Revised:2019-04-15 Online:2019-04-30

摘要:

大数据背景下产生了海量图像数据,传统的图像识别方法识别玉米植株病害准确率较低,已远远不能满足需求。卷积神经网络作为深度学习中的常用算法被广泛用于处理机器视觉问题,能自动识别和提取图像特征。因此,本研究提出一种基于数据增强与迁移学习相结合的卷积神经网络识别玉米植株病害模型。该算法首先通过数据增强方法增加数据,以提高模型的泛化性和准确率;再构建基于迁移学习的卷积神经网络模型,引入该模型的训练方式,提取病害图片特征,加速卷积神经网络的训练过程,降低网络的过拟合程度;最后将该模型运用到从农田采集的玉米病害图片,进行玉米病害的精确识别。识别试验结果表明:使用数据增强与迁移学习的卷积神经网络优化算法对玉米主要病害(玉米大斑病、小斑病、灰斑病、黑穗病及瘤黑粉病)的平均识别准确度达96.6%,和单一的卷积神经网络相比,精度提高了25.6%,处理每张图片时间为0.28s,比传统神经网络缩短了将近10倍。本算法的精确度和训练速度上比传统卷积神经网络有明显提高,为玉米等农作物植株病害的识别提供了新方法。

关键词: 深度学习, 卷积神经网络, 迁移学习, 数据增强, 玉米病害识别

Abstract:

Corn is one of the most important food crops in China, and the occurrence of disease will result in serious yield reduction. Therefore, the diagnosis and treatment of corn disease is an important link in corn production. Under the background of big data, massive image data are generated. The traditional image recognition method has a low accuracy in identifying corn plant diseases, which is far from meeting the needs. With the development of artificial intelligence and deep learning, convolutional neural network, as a common algorithm in deep learning, is widely used to deal with machine vision problems. It can automatically identify and extract image features. However, in image classification, CNN still has problems such as small sample size, high sample similarity and long training convergence time. CNN has the limitations of expression ability and lack of feedback mechanism, and data enhancement and transfer learning can solve the corresponding problems. Therefore, this research proposed an optimization algorithm for corn plant disease recognition based on the convolution neural network recognition model combining data enhancement and transfer learning. Firstly, the algorithm preprocessed the data through the data enhancement method to expand the data set, so as to improve the generalization and accuracy of the model. Then, the CNN model based on transfer learning was constructed. The Inception V3 model was adopted through transfer learning to extract the image characteristics of the disease while keeping the parameters unchanged. In this way, the training process of the convolutional neural network was accelerated and the over-fitting degree of the network was reduced. The extracted image features were used as input of the CNN to train the network, and finally the recognition results were obtained. Finally, the model was applied to the pictures of corn diseases collected from the farmland to accurately identify five kinds of corn diseases. Identification test results showed that using data to enhance the CNN optimization algorithm and the migration study on the average recognition accuracy main diseases of com (spot, southern leaf blight, gray leaf spot, smut, gall smut) reached 96.6%, which compared with single CNN, has greatly improved the precision and identification precision by 25.6% on average. The average processing time of each image was 0.28 s, shortens nearly 10 times than a single convolution neural network. The experimental results show that the algorithm is more accurate and faster than the traditional CNN, which provides a new method for identification of corn plant diseases.

Key words: deep learning, convolutional neural network, transfer learning, data enhancement, identification of corn disease

中图分类号: