[1]杨晋丹,杨涛,苗腾,等.基于卷积神经网络的草莓叶部白粉病病害识别[J].江苏农业学报,2018,(03):527-532.[doi:doi:10.3969/j.issn.1000-4440.2018.03.007]
　YANG Jin-dan,YANG Tao,MIAO Teng,et al.Recognition of powdery mildew disease of strawberry leaves based on convolutional neural network[J].,2018,(03):527-532.[doi:doi:10.3969/j.issn.1000-4440.2018.03.007]
点击复制

基于卷积神经网络的草莓叶部白粉病病害识别()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2018年03期
页码:
527-532
栏目:
植物保护
出版日期:
2018-06-25

文章信息/Info

Title:
Recognition of powdery mildew disease of strawberry leaves based on convolutional neural network
作者:
杨晋丹; 杨涛; 苗腾; 朱超; 沈秋采; 彭宇飞; 梅珀彰; 党雨晴
（沈阳农业大学信息与电气工程学院，辽宁沈阳110161）
Author(s):
YANG Jin-dan; YANG Tao; MIAO Teng; ZHU Chao; SHEN Qiu-cai; PENG Yu-fei; MEI Po-zhang; DANG Yu-qing
(College of Information and Electric Engineering, Shenyang Agricultural University, Shenyang 110161,China)
关键词:
卷积神经网络; 草莓白粉病; 病害识别; 采样层构建方法
Keywords:
convolutional neural network; strawberry powdery mildew; disease recognition; sampling layer construction method
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2018.03.007
文献标志码:
A
摘要:
针对计算机视觉下草莓叶部白粉病病害的识别，提出了一种基于卷积神经网络的病害识别模型。首先，设计了3种网络深度（经过3、4和5次卷积操作）与3种卷积核（5×5、3×3,5×5、3×3混合）交叉组合共9种不同网络深度与卷积核尺寸的卷积神经网络结构；其次，分别选择了4种采样层构建方法（均值池化、最大值池化、中间值池化和混合池化）；最后，进行了9组训练集与测试集不同比例的模型识别。结果表明，基于混合池化的CNN-9模型（卷积核尺寸5×5，3×3；卷积神经网络深度11）表现最好，对草莓叶部白粉病病害的正确识别率达到98.61%。该方法可较好地实现草莓叶部白粉病病害的识别，且图像预处理步骤简单，易推广，可用于草莓白粉病病害的实时监测。
Abstract:
A disease recognition model based on convolutional neural network was proposed for the recognition of strawberry leaf powdery mildew disease under computer vision. Firstly, a total of nine different types of network depth and convolution kernel size consisting of cross combination of three types of network depth (through three, four and five convolution operation) and three types of convolution kernel (5×5 and 3×3, 5×5 and 3×3 mixed) were designed. Secondly, four kinds of sampling layer construction method (average pooling, max pooling, median pooling and mixed max-average pooling) were chosen. Finally, nine model recognition tests consisting of different ratio of training set and test set were performed. The results showed that the CNN-9 model based on mixed max-average pooling was the best, and the correct recognition rate of strawberry leaf powdery mildew disease was 98.61%. This method can better identify strawberry leaf powdery disease, and the image preprocessing is simple and easy to popularize, and it can be used for real-time monitoring of strawberry powdery mildew.

参考文献/References:

[1]国亚文,娄文生,王晓宇. 草莓白粉病发生特点及防治技术[J]. 农业与技术,2005(1):127-132.
[2]赵玉霞,王克如,白中英,等. 贝叶斯方法在玉米叶部病害图像识别中的应用[J]. 计算机工程与应用,2007(5):193-195.
[3]王娜,王克如,谢瑞芝,等. 基于Fisher判别分析的玉米叶部病害图像识别[J]. 中国农业科学,2009,42(11):3836-3842.
[4]张善文,张传雷. 基于局部判别映射算法的玉米病害识别方法[J]. 农业工程学报,2014,30(11):167-172.
[5]朱景福,李雪. 玉米叶片病害彩色图像识别的降维和聚类方法[J]. 江苏农业科学,2016,44(7):350-354.
[6]谢泽奇,张会敏,张善文,等. 基于颜色特征和属性约简的黄瓜病害识别方法[J]. 江苏农业学报,2015,31(3):526-530.
[7]吴娜,李淼,陈晟，等. 基于融合多特征图切割的作物病害图像自动分割[J]. 农业工程学报,2014,30(17):212-219.
[8]刘立波,周国民. 基于多层感知神经网络的水稻叶瘟病识别方法[J]. 农业工程学报,2009,25(S2):213-217.
[9]管泽鑫,唐健,杨保军,等. 基于图像的水稻病害识别方法研究[J]. 中国水稻科学,2010,24(5):497-502.
[10]张飞云. 基于提升小波和学习向量量化神经网络的小麦病害图像识别[J]. 江苏农业科学,2013,41(5):103-106.
[11]PATIL S P, ZAMBRE M R S. Classification of cotton leaf spot disease using support vector, machine[J]. International Journal of Engineering Research & Applications, 2014, 4(5):92-77.
[12]牛冲. 基于图像处理的草莓病害识别方法研究[D].太原:太原理工大学,2016.
[13]HAMED H A, ELNAZ J H, DOMENEC P. A practical approach for detection and classification of traffic signs using convolutional neural networks[J]. Robotics and Autonomous Systems,2016,84:97-112.
[14]YU S, JIA S, XU C. Convolutional neural networks for hyperspectral image classification[J]. Neurocomputing, 2017, 219: 88-98.
[15]BAI X, SHI B, ZHANG C, et al. Text/non-text image classification in the wild with convolutional neural networks[J]. Pattern Recognition, 2017, 66: 437-446.
[16]SUN J, XIAO Z, XIE Y. Automatic multi-fault recognition in TFDS based on convolutional neural network[J]. Neurocomputing, 2017, 222: 127-136.
[17]周云成,许童羽,郑伟,等.基于深度卷积神经网络的番茄主要器官分类识别方法[J].农业工程学报,2017,33(15):219-226.
[18]王璨,武新慧,李志伟.基于卷积神经网络提取多尺度分层特征识别玉米杂草[J].农业工程学报,2018,34(5):144-151.
[19]李艳. 基于改进CNN的马铃薯病害识别算法[J]. 信息通信,2017(6):46-48.
[20]刘阗宇,冯全. 基于卷积神经网络的葡萄叶片检测[J]. 西北大学学报(自然科学版), 2017, 47 (4):505-512.
[21]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,2016,6:1-11.
[22]MOHANTY S P, HUGHES D P, SALATH M. Using deep learning for image-based plant disease detection[J]. Frontiers in Plant Science, 2016,7:1-10.
[23]王振,高茂庭. 基于卷积神经网络的图像识别算法设计与实现[J]. 现代计算机(专业版), 2015(20):61-66.
[24]常祥,杨明. 基于改进的卷积神经网络的图像分类性能[J]. 重庆理工大学学报(自然科学),2017,31(3):110-115.
[25]LEE C Y, GALLAGHER P, TU Z. Generalizing pooling functions in CNNs: mixed, gated, and tree[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 863-875.

相似文献/References:

[1]张善文,谢泽奇,张晴晴.卷积神经网络在黄瓜叶部病害识别中的应用[J].江苏农业学报,2018,(01):56.[doi:doi:10.3969/j.issn.1000-4440.2018.01.008]
　ZHANG Shan-wen,XIE Ze-qi,ZHANG Qing-qing.Application research on convolutional neural network for cucumber leaf disease recognition[J].,2018,(03):56.[doi:doi:10.3969/j.issn.1000-4440.2018.01.008]
[2]丁承君,刘强,田军强,等.信息物理系统事件驱动下的农业气象监测系统[J].江苏农业学报,2018,(04):825.[doi:doi:10.3969/j.issn.1000-4440.2018.04.016]
　DING Cheng-jun,LIU Qiang,TIAN Jun-qiang,et al.Agro-meteorological monitoring system based on event-driven modeling of cyber-physical system[J].,2018,(03):825.[doi:doi:10.3969/j.issn.1000-4440.2018.04.016]
[3]许伟栋,赵忠盖.基于卷积神经网络和支持向量机算法的马铃薯表面缺陷检测[J].江苏农业学报,2018,(06):1378.[doi:doi:10.3969/j.issn.1000-4440.2018.06.025]
　XU Wei-dong,ZHAO Zhong-gai.Potato surface defects detection based on convolution neural networks and support vector machine algorithm[J].,2018,(03):1378.[doi:doi:10.3969/j.issn.1000-4440.2018.06.025]
[4]孙云云,江朝晖,董伟,等.基于卷积神经网络和小样本的茶树病害图像识别[J].江苏农业学报,2019,(01):48.[doi:doi:10.3969/j.issn.1000-4440.2019.01.007]
　SUN Yun-yun,JIANG Zhao-hui,DONG Wei,et al.Image recognition of tea plant disease based on convolutional neural network and small samples[J].,2019,(03):48.[doi:doi:10.3969/j.issn.1000-4440.2019.01.007]
[5]王振,张善文,王献锋.基于改进全卷积神经网络的黄瓜叶部病斑分割方法[J].江苏农业学报,2019,(05):1054.[doi:doi:10.3969/j.issn.1000-4440.2019.05.008]
　WANG Zhen,ZHANG Shan-wen,WANG Xian-feng.Method for segmentation of cucumber leaf lesions based on improved full convolution neural network[J].,2019,(03):1054.[doi:doi:10.3969/j.issn.1000-4440.2019.05.008]
[6]徐岩,刘林,李中远,等.基于卷积神经网络的玉米品种识别[J].江苏农业学报,2020,(01):18.[doi:doi:10.3969/j.issn.1000-4440.2020.01.003]
　XU Yan,LIU Lin,LI Zhong-yuan,et al.Recognition of maize varieties based on convolutional neural network[J].,2020,(03):18.[doi:doi:10.3969/j.issn.1000-4440.2020.01.003]
[7]张善文,邵彧,齐国红,等.基于多尺度注意力卷积网络的作物害虫检测[J].江苏农业学报,2021,(03):579.[doi:doi:10.3969/j.issn.1000-4440.2021.03.005]
　ZHANG Shan-wen,SHAO Yu,QI Guo-hong,et al.Crop pest detection based on multi-scale convolutional network with attention[J].,2021,(03):579.[doi:doi:10.3969/j.issn.1000-4440.2021.03.005]
[8]袁红春,王敏,刘慧,等.基于特征交互与卷积网络的渔场预测模型[J].江苏农业学报,2021,(06):1501.[doi:doi:10.3969/j.issn.1000-4440.2021.05.019]
　YUAN Hong-chun,WANG Min,LIU Hui,et al.Fishing ground prediction model based on feature interaction and convolutional network[J].,2021,(03):1501.[doi:doi:10.3969/j.issn.1000-4440.2021.05.019]
[9]李婕,李毅,张瑞杰,等.无人机遥感影像在油菜品种识别中的应用[J].江苏农业学报,2022,38(03):675.[doi:doi:10.3969/j.issn.1000-4440.2022.03.013]
　LI Jie,LI Yi,ZHANG Rui-jie,et al.Application of UAV remote sensing image in rape variety identification[J].,2022,38(03):675.[doi:doi:10.3969/j.issn.1000-4440.2022.03.013]
[10]翟先一,魏鸿磊,韩美奇,等.基于改进YOLO卷积神经网络的水下海参检测[J].江苏农业学报,2023,(07):1543.[doi:doi:10.3969/j.issn.1000-4440.2023.07.011]
　ZHAI Xian-yi,WEI Hong-lei,HAN Mei-qi,et al.Underwater sea cucumber identification based on improved YOLO convolutional neural network[J].,2023,(03):1543.[doi:doi:10.3969/j.issn.1000-4440.2023.07.011]

备注/Memo

备注/Memo:
收稿日期：2018-01-22 基金项目：国家自然科学基金项目（31501217） 作者简介：杨晋丹（1994-），女，山西应县人，硕士，研究方向为计算机技术在农业领域中的应用。(E-mail)997394351@qq.com 通讯作者：杨涛，(E-mail)328748306@qq.com
更新日期/Last Update: 2018-07-04