基于CNN和迁移学习的农作物病害识别方法研究

doi:10.12133/j.smartag.2019.1.3.201903-SA005

Smart Agriculture ›› 2019, Vol. 1 ›› Issue (3): 46-55.doi: 10.12133/j.smartag.2019.1.3.201903-SA005

基于CNN和迁移学习的农作物病害识别方法研究

李淼¹, 王敬贤^1,², 李华龙¹, 胡泽林¹, 杨选将^1,², 黄小平^1,², 曾伟辉¹, 张建^1,^*(), 房思思^1,²

^1. 中国科学院智能机械研究所智能农业与环境检测研究室，安徽合肥 230031
^2. 中国科学技术大学，安徽合肥 230026

收稿日期:2019-03-29 修回日期:2019-04-17 出版日期:2019-07-30
基金资助:
国家高技术研究发展863计划(2013AA102304)
作者简介:李淼（1955-）,女,研究员,研究方向：农业信息技术研究与应用,Email: mli@iim.ac.cn。
通信作者:

Method for identifying crop disease based on CNN and transfer learning

Li Miao¹, Wang Jingxian^1,², Li Hualong¹, Hu Zelin¹, Yang XuanJiang^1,², Huang Xiaoping^1,², Zeng Weihui¹, Zhang Jian^1,^*(), Fang Sisi^1,²

^1. Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, China
^2. University of Science and Technology of China, Hefei 230026, China

Received:2019-03-29 Revised:2019-04-17 Online:2019-07-30

摘要/Abstract

摘要：

互联网是一个巨大的资源库,也是一个丰富的知识库。针对农作物小样本引起的过拟合问题,本研究引入了知识迁移和深度学习的方法,采用互联网公开的ImageNet图像大数据集和PlantVillage植物病害公共数据集,以实验室的黄瓜和水稻病害数据集AES-IMAGE为对象开展相关的研究与试验。首先将批归一化算法应用于卷积神经网络CNN中的AlexNet和VGG模型,改善网络的过拟合问题;再利用PlantVillage植物病害数据集得到预训练模型,在改进的网络模型AlexNet和VGG模型上用AES-IMAGE对预训练模型参数调整后进行病害识别。最后,使用瓶颈层特征提取的迁移学习方法,利用ImageNet大数据集训练出的网络参数,将Inception-v3和Mobilenet模型作为特征提取器,进行黄瓜和水稻病害特征提取。本研究结合试验结果探讨了适用于农作物病害识别问题的最佳网络和对应的迁移策略,表明使用VGG网络参数微调的策略可获得的最高准确率为98.33%,使用Mobilenet瓶颈层特征提取的策略可获得96.8%的验证准确率。证明CNN结合迁移学习可以利用充分网络资源来克服大样本难以获取的问题,提高农作物病害识别效率。

关键词: CNN, 农作物病害, 过度拟合, 迁移学习, 参数微调, 特征提取器

Abstract:

The internet is a huge resource base and a rich knowledge base. Aiming at the problem of small agricultural samples, the utilization technology of network resources was studied in the research, which would provide an idea and method for the research and application of crop disease identification and diagnosis. The knowledge transfer and deep learning methods to carry out research and experiments on public data sets (ImageNet, PlantVillage) and laboratory small sample disease data (AES-IMAGE) were introduced: first the batch normalization algorithm was applied to the AlexNet and VGG of Convolutional Neural Network (CNN) models to improve the over-fitting problem of the network; second the transfer learning strategy using parameter fine-tuning: The PlantVillage large-scale plant disease dataset was used to obtain the pre-trained model. On the improved network (AlexNet, VGG model), the pre-trained model was adjusted by our small sample dataset AES-IMAGE to obtain the disease identification model of cucumber and rice; third the transfer learning strategy was used for the bottleneck feature extraction: using the ImageNet big dataset to obtain the network parameters, CNN model (Inception-v3 and Mobilenet) was used as feature extractor to extract disease features. This method requires only a quick identification of the disease on the CPU and does not require a lot of training time, which can quickly complete the process of disease identification on the CPU. The experimental results show that: first in the transfer learning strategy of parameter fine-tuning: the highest accuracy rate was 98.33%, by using the VGG network parameter fine-tuning strategy; second in the transfer learning strategy of bottleneck feature extraction, using the Mobilenet model for bottleneck layer feature extraction and identification could obtain 96.8% validation accuracy. The results indicate that the combination of CNN and transfer learning is effective for the identification of small sample crop diseases.

Key words: CNN, crop diseases, overfitting, transfer learning, parameter fine-tuning, feature extractor

中图分类号:

李淼, 王敬贤, 李华龙, 胡泽林, 杨选将, 黄小平, 曾伟辉, 张建, 房思思. 基于CNN和迁移学习的农作物病害识别方法研究[J]. 智慧农业, 2019, 1(3): 46-55.

Li Miao, Wang Jingxian, Li Hualong, Hu Zelin, Yang XuanJiang, Huang Xiaoping, Zeng Weihui, Zhang Jian, Fang Sisi. Method for identifying crop disease based on CNN and transfer learning[J]. Smart Agriculture, 2019, 1(3): 46-55.

参考文献

[1]	Mutka A M, Bart R S . Image-based phenotyping of plant disease symptom[J]. Frontiers in Plant Science, 2015, 5, article no. 734.
[2]	Pydipati R, Burks T F, Lee W S . Identification of citrus disease using color texture features and discriminant analysis[J]. Computers and Electronics in Agriculture, 2006, ( 52):49-59.
[3]	Lee W S, Burks T F, Pydipati R . Statistical and neural network classifiers for citrus disease detection using machine vision[J]. Transactions of the ASAE, 2005,48(48):2007-2010.
[4]	Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks [C]. International Conference on Neural Information Processing Systems. Curran Associates Inc. 2012: 1097-1105.
[5]	Brahimi M, Boukhalfa K, Moussaoui A . Deep learning for tomato diseases: classification and symptoms visualization[J]. Applied Artificial Intelligence, 2017: 1-17.
[6]	Mohanty S P, Hughes D P, Salathé Marcel . Using deep learning for image-based plant disease detection[J]. Frontiers in Plant Science, 2016,7:1-10.
[7]	Lee H, Eum S, Kwon H . Cross-domain CNN for hyperspectral image classification[J]. arXiv:1802.00093v2 [cs.CV] 2 May 2018.
[8]	Lee H, Kwon H . Going deeper with contextual CNN for hyperspectral image classification[J]. IEEE Trans Image Process, 2017,26(10):4843.
[9]	Khamparia A, Saini G, Gupta D, et al. Seasonal crops disease prediction and classification using deep convolutional encoder network[J]. Circuits Systems and Signal Processing , 2019(May).
[10]	Sun X, Mu S, Xu Y , et al. Image recognition of tea leaf diseases based on convolutional neural network[J]. 2019: arXiv: 1901. 02694.
[11]	Pan S J, Yang Q . A survey on transfer learning[J]. IEEE Transactions on Knowledge & Data Engineering, 2010,22(10):1345-1359.
[12]	Sladojevic S, Arsenovic M, Anderla A , et al. Deep neural networks based recognition of plant diseases by leaf image classification[J]. Computational Intelligence and Neuroscience, 2016, ( 6):1-11.
[13]	Srdjan S, Marko A, Andras A , et al. Deep neural networks based recognition of plant diseases by leaf image classification[J]. Computational Intelligence and Neuroscience, 2016,2016:1-11.
[14]	Torrey L, Shavlik J , Transfer learning[M]. Machine Learning Applications and Trends, 2009, 242-264. http://dx.doi.org/10.4018/978-1-60566-766-9.ch011.
[15]	Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift [C]. International Conference on International Conference on Machine Learning. JMLR.org, 2015: 448-456.
[16]	Lecun Y, Boser B, Denker J S , et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989,1(4):541-551.
[17]	Simonyan K, Zisserman A . Very deep convolutional networks for large-scale image recognition[J/OL]. ( 2015 -4-10)[2019-3-29]. https://arxiv.org/abs/1409.1556, 2014.
[18]	Deng J, Dong W, Socher R, et al. Imagenet: A large-scale hierarchical image database [C]. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR), 2009: 248-255.
[19]	Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision [C]. Computer Vision and Pattern Recognition. IEEE, 2016: 2818-2826.
[20]	Howard A G, Zhu M, Chen B , et al. MobileNets: Efficient convolutional neural networks for mobile vision applications[J]. 2017: arXiv:1704. 04861v1 [cs.CV], 2818-2826.

基于CNN和迁移学习的农作物病害识别方法研究

Method for identifying crop disease based on CNN and transfer learning

在线阅读

知网下载

本地下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	潘晨露, 张正华, 桂文豪, 马家俊, 严晨曦, 张晓敏. 融合ECA机制与DenseNet201的水稻病虫害识别方法[J]. 智慧农业(中英文), 2023, 5(2): 45-55.
[2]	李阳德, 马晓慧, 王骥. 基于轻量级MobileNet V3-YOLOv4的生长期菠萝成熟度分析[J]. 智慧农业(中英文), 2023, 5(2): 35-44.
[3]	朱海鹏, 张玉安, 李欢欢, 王建文, 杨英魁, 宋仁德. 基于改进残差网络模型的不同部位牦牛肉分类识别方法[J]. 智慧农业(中英文), 2023, 5(2): 115-125.
[4]	王亚鹏, 曹姗姗, 李全胜, 孙伟. 融合迁移学习和集成学习的自然背景下荒漠植物识别方法[J]. 智慧农业(中英文), 2023, 5(2): 93-103.
[5]	张文景, 蒋泽中, 秦立峰. 基于弱监督下改进的CBAM-ResNet18模型识别苹果多种叶部病害[J]. 智慧农业(中英文), 2023, 5(1): 111-121.
[6]	刘晓航, 张昭, 刘嘉滢, 张漫, 李寒, FLORES Paulo, 韩雄哲. 基于多种深度学习算法的田间玉米籽粒检测与计数[J]. 智慧农业(中英文), 2022, 4(4): 49-60.
[7]	张志博, 赵西宁, 高晓东, 张利, 杨孟豪. 基于改进Linknet网络的黄土高原苹果园精准提取[J]. 智慧农业(中英文), 2022, 4(3): 95-107.
[8]	何锐敏, 郑可锋, 尉钦洋, 张小斌, 张俊, 朱怡航, 赵懿滢, 顾清. 基于改进Mask R-CNN模型的工厂化养蚕蚕体识别与计数[J]. 智慧农业(中英文), 2022, 4(2): 163-173.
[9]	陈占琦, 张玉安, 王文志, 李丹, 何杰, 宋仁德. 基于迁移学习的多尺度特征融合牦牛脸部识别算法[J]. 智慧农业(中英文), 2022, 4(2): 77-85.
[10]	周巧黎, 马丽, 曹丽英, 于合龙. 基于改进轻量级卷积神经网络MobileNetV3的番茄叶片病害识别[J]. 智慧农业(中英文), 2022, 4(1): 47-56.
[11]	张小青, 邵松, 郭新宇, 樊江川. 田间玉米苗期高通量动态监测方法[J]. 智慧农业（中英文）, 2021, 3(2): 88-99.
[12]	魏靖, 王玉亭, 袁会珠, 张梦蕾, 王振营. 基于深度学习与特征可视化方法的草地贪夜蛾及其近缘种成虫识别[J]. 智慧农业（中英文）, 2020, 2(3): 75-85.
[13]	陈桂芬, 赵姗, 曹丽英, 傅思维, 周佳鑫. 基于迁移学习与卷积神经网络的玉米植株病害识别[J]. 智慧农业, 2019, 1(2): 34-44.