基于Caffe卷积神经网络的大豆病害检测系统

doi:10.3969/j.issn.1004-1524.2019.07.19

浙江农业学报 ›› 2019, Vol. 31 ›› Issue (7): 1177-1183.DOI: 10.3969/j.issn.1004-1524.2019.07.19

基于Caffe卷积神经网络的大豆病害检测系统

蒋丰千^1,2, 李旸^1,2,*, 余大为^1,2, 孙敏^1,2, 张恩宝^1,2

1.安徽农业大学信息与计算机学院,安徽合肥 230036;
2.农业农村部农业物联网技术集成与应用重点实验室,安徽合肥 230036

收稿日期:2018-12-29 出版日期:2019-07-25 发布日期:2019-08-07
通讯作者: *李旸,E-mail: ly-and@qq.com
作者简介:蒋丰千(1994—),男,安徽滁州人,硕士研究生,主要研究方向为农业物联网技术、智能农业信息技术。E-mail: 2898983067@qq.com
基金资助:
国家农业开发土地治理基金(国农办〔2012〕3号)

Soybean disease detection system based on convolutional neural network under Caffe framework

JIANG Fengqian^1,2, LI Yang^1,2,*, YU Dawei^1,2, SUN Min^1,2, ZHANG Enbao^1,2

1. School of Information & Computer Science, Anhui Agriculture University, Hefei 230036, China;
2.Key Laboratory of Technology Integration and Application in Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Hefei 230036, China

Received:2018-12-29 Online:2019-07-25 Published:2019-08-07

摘要/Abstract

摘要： 以常见的大豆病害图片为样本,研究分析了大豆的叶斑病、花叶病、霜霉病和灰斑病,并利用卷积神经网络技术设计了针对大豆的病害检测系统。通过对病害图片的二值化和轮廓分割等预处理来获得神经网络模型的训练集,并在此基础上对模型进行了多方面的优化,利用Caffe框架对优化后的网络模型进行了识别率等方面的实验验证。此外,为提高模型使用的便捷性,本实验使用了Qt软件为该系统设计了人机交互界面,从而进一步实现了数据可视化。

关键词: 大豆病害, 卷积神经网络, Caffe框架, 交互界面, 数据可视化

Abstract: The diseases such as leaf spot, mosaic, downy mildew and gray spot of soybean were analysed, and then a soybean disease identification system based on convolutional neural network was proposed. The training set of the neural network model was obtained by the pretreatments including binarization of disease images and extraction of target regions, moreover, the accuracy of the model was improved, and the model and related parameters were simulated under the Caffe framework. Furthermore, in order to improve the ease and reliability of the system in use, the human-computer interaction interface was designed by using Qt software. The data visualization was further realized.

Key words: soybean diseases, convolution neural network, Caffe, interactive interface, data visualization

中图分类号:

蒋丰千, 李旸, 余大为, 孙敏, 张恩宝. 基于Caffe卷积神经网络的大豆病害检测系统[J]. 浙江农业学报, 2019, 31(7): 1177-1183.

JIANG Fengqian, LI Yang, YU Dawei, SUN Min, ZHANG Enbao. Soybean disease detection system based on convolutional neural network under Caffe framework[J]. , 2019, 31(7): 1177-1183.

参考文献

[1] 张云龙, 来智勇, 景旭, 等. 基于改进BP神经网络的大豆病害检测[J]. 农机化研究, 2015, 37(2): 79-82.
ZHANG Y L, LAI Z Y, JING X, et al.Soybean diseases detection based on improved BP neural network[J]. Journal of Agricultural Mechanization Research, 2015, 37(2): 79-82.(in Chinese with English abstract)
[2] 陈兵旗, 郭学梅, 李晓华. 基于图像处理的小麦病害诊断算法[J]. 农业机械学报, 2009, 40(12): 190-195.
CHEN B Q, GUO X M, LI X H.Image diagnosis algorithm of diseased wheat[J]. Transactions of the Chinese Society for Agricultural Machinery, 2009, 40(12): 190-195.(in Chinese with English abstract)
[3] 关海鸥, 许少华, 谭峰. 基于遗传模糊神经网络的植物病斑区域图像分割模型[J]. 农业机械学报, 2010, 41(11): 163-167.
GUAN H O, XU S H, TAN F.Image segmentation model of plant lesion based on genetic algorithm and fuzzy neural network[J]. Transactions of the Chinese Society for Agricultural Machinery, 2010, 41(11): 163-167.(in Chinese with English abstract)
[4] 马晓丹, 关海鸥, 祁广云, 等. 基于改进级联神经网络的大豆叶部病害诊断模型[J]. 农业机械学报, 2017, 48(1): 163-168.
MA X D, GUAN H O, QI G Y, et al.Diagnosis model of soybean leaf diseases based on improved cascade neural network[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(1): 163-168.(in Chinese with English abstract)
[5] 关海鸥, 杜松怀, 李春兰, 等. 基于有限脉冲反应和径向基神经网络的触电信号识别[J]. 农业工程学报, 2013, 29(8): 187-194.
GUAN H O, DU S H, LI C L, et al.Recognition of electric shock signal based on FIR filtering and RBF neural networks[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(8): 187-194.(in Chinese with English abstract)
[6] 关海鸥, 黄燕. 大豆病斑智能识别无损预处理及其特征提取方法的研究[J]. 河北农业大学学报, 2010, 33(5): 123-127.
GUAN H O, HUANG Y.Study on the method of non-loss pre-processing and feature extraction for intelligent recognition of soybean diseased spots[J]. Journal of Agricultural University of Hebei, 2010, 33(5): 123-127.(in Chinese with English abstract)
[7] 苏博, 刘鲁, 杨方廷. 基于灰色关联分析的神经网络模型[J]. 系统工程理论与实践, 2008, 28(9): 98-104.
SU B, LIU L, YANG F T.Research of artificial neural network forecasting model based on grey relational analysis[J]. Systems Engineering-Theory & Practice, 2008, 28(9): 98-104.(in Chinese with English abstract)
[8] 刘园园. 基于卷积神经网络的花卉图像分类算法的研究[D]. 北京:华北电力大学,2017.
LIU Y Y.Research on flower classification via convolutional neural network[D]. Beijing: North China Electric Power University, 2017. (in Chinese with English abstract)
[9] ZAMAN F, WONG Y P, NG B Y.Density-based denoising of point cloud[M]//ZAMAN F, WONG Y P, NG B Y. eds. 9th International Conference on Robotic, Vision, Signal Processing and Power Applications. Singapore: Springer Singapore, 2016: 287-295.
[10] HINTON G E, OSINDERO S, TEH Y W.A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[11] LIU B, YU X C, ZHANG P Q, et al.A semi-supervised convolutional neural network for hyperspectral image classification[J]. Remote Sensing Letters, 2017, 8(9): 839-848.
[12] 常亮, 邓小明, 周明全, 等. 图像理解中的卷积神经网络[J]. 自动化学报, 2016, 42(9): 1300-1312.
CHANG L, DENG X M, ZHOU M Q, et al.Convolutional neural networks in image understanding[J]. Acta Automatica Sinica, 2016, 42(9): 1300-1312.(in Chinese with English abstract)
[13] XU S W, YANG Z Y, WU W Y.Algorithm of 3D reconstruction based on point cloud segmentation denoising[C]//The 2nd International Conference on Information Science and Engineering, 2010 2nd International Conference on Information Science and Engineering (ICISE), Hangzhou, China, 2010.
[14] 孙志军, 薛磊, 许阳明, 等. 深度学习研究综述[J]. 计算机应用研究, 2012, 29(8): 2806-2810.
SUN Z J, XUE L, XU Y M, et al.Overview of deep learning[J]. Application Research of Computers, 2012, 29(8): 2806-2810.(in Chinese with English abstract)
[15] FEI B W, AKBARI H, HALIG L V.Hyperspectral imaging and spectral-spatial classification for cancer detection[C]//2012 5th International Conference on BioMedical Engineering and Informatics, 2012 5th International Conference on Biomedical Engineering and Informatics (BMEI), Chongqing, China, 2012.
[16] 林万洪, 薛亮. RBF网络做函数逼近的改进研究[J]. 装备指挥技术学院学报, 2006, 17(2): 84-87.
LIN W H, XUE L.Research on approximation of function by improved RBF networks[J]. Journal of the Academy of Equipment Command & Technology, 2006, 17(2): 84-87.(in Chinese with English abstract)
[17] GULCEHRE C, MOCZULSKI M, DENIL M, et al. Noisy activation functions[EB/OL].(2016-04-03)[2018-11-28]https://arxiv.org/abs/1603.00391v3.
[18] KETKAR N.Deep learning with Python[M]. Berkeley, CA: Apress, 2017.

基于Caffe卷积神经网络的大豆病害检测系统

Soybean disease detection system based on convolutional neural network under Caffe framework

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	鲍烈, 王曼韬, 刘江川, 文波, 明月. 基于卷积神经网络的小麦产量预估方法[J]. 浙江农业学报, 2020, 32(12): 2244-2252.
[2]	金秀, 卢杰, 傅运之, 王帅, 许高健, 李绍稳. 基于深度卷积神经网络的小麦赤霉病高光谱病症点分类方法[J]. 浙江农业学报, 2019, 31(2): 315-325.
[3]	张善文, 黄文准, 尤著宏. 基于物联网和深度卷积神经网络的冬枣病害识别方法[J]. 浙江农业学报, 2017, 29(11): 1868-1874.