[1]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):18-23.[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,(01):18-23.[doi:doi:10.3969/j.issn.1000-4440.2020.01.003]
点击复制

基于卷积神经网络的玉米品种识别()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2020年01期
页码:
18-23
栏目:
遗传育种·生理生化
出版日期:
2020-02-29

文章信息/Info

Title:
Recognition of maize varieties based on convolutional neural network
作者:
徐岩; 刘林; 李中远; 高照; 李晓振
(山东科技大学电子信息工程学院，山东青岛266590)
Author(s):
XU Yan; LIU Lin; LI Zhong-yuan; GAO Zhao; LI Xiao-zhen
(College of Electronic Information Engineering, Shandong University of Science and Technology, Qingdao 266590, China)
关键词:
玉米; 品种识别; 卷积神经网络; Keras学习框架
Keywords:
maize; variety recognition; convolutional neural network; Keras learning framework
分类号:
TP391
DOI:
doi:10.3969/j.issn.1000-4440.2020.01.003
文献标志码:
A
摘要:
为了解决传统算法中人工提取特征的缺陷，提出了基于卷积神经网络的玉米品种识别算法。以登海518、浚单20和郑单958 3个玉米品种为研究对象，制作数据集并进行分类标签，分别标记为0、1、2。使用Keras学习框架搭建网络模型，包括1个输入层、5个连续的卷积池化结构、3个全连接层和1个输出层。卷积层提取有效的特征信息，结合Leaky ReLU激活函数传递至下一层，输出层采用Softmax函数实现玉米品种的识别。使用完成训练的模型对预测集进行预测。结果表明：登海518、浚单20、郑单958的识别率分别达到100.00%、93.99%、92.49%，平均识别率达到95.49%。
Abstract:
In order to overcome the shortcomings of artificial featur extraction in traditional algorithm, a maize variety recognition algorithm based on convolutional neural network was proposed in this study. Taking maize variety Denghai 518, Jundan 20 and Zhengdan 958 as the research objects, the data sets were created and classified with labels of 0, 1, and 2. Keras learning framework was selected to build the network model, which included one input layer, five continuous convolution pooling structures, three full connection layers and one output layer. The convolution layer extracted effective feature information and transmitted it to the next layer with Leaky ReLU activation function. The output layer used Softmax function to realize the identification of maize varieties. The prediction set was predicted by the completed training model. The prediction results showed that the recognition rates of Denghai 518, Jundan 20 and Zhengdan 958 were 100.00%, 93.99% and 92.49% respectively, with an average recognition rate of 95.49%.

参考文献/References:

[1]傅兆翔. 中国粮食消费现状分析及展望[J]. 农业展望,2017,13(5):91-94.
[2]王玉亮,刘贤喜,苏庆堂,等. 多对象特征提取和优化神经网络的玉米种子品种识别[J]. 农业工程学报, 2010,26(6): 199- 204.
[3]张云丽,韩宪忠,王克俭. 基于深度颜色特征的灰度直方图玉米品种识别研究[J]. 作物杂志, 2015(1):156-159.
[4]程洪,史智兴,冯娟,等. 基于玉米胚部特征参数优化的玉米品种识别研究[J]. 中国粮油学报, 2014, 29(6): 22-26.
[5]DENG L M , LUAN T , MA W J . Research on maize varieties recognition system based on image processing[J]. Applied Mechanics and Materials, 2013, 397-400:2335-2339.
[6]宁纪锋. 玉米品种的计算机视觉识别研究[D]. 咸阳:西北农林科技大学,2002:25-40.
[7]陈建,陈晓,李伟,等. 基于近红外光谱技术和人工神经网络的玉米品种鉴别方法研究[J]. 光谱学与光谱分析,2008 (8):1806-1809.
[8]杨蜀秦,宁纪锋,何东健. BP人工神经网络识别玉米品种的研究[J]. 西北农林科技大学学报(自然科学版), 2004,32(S1):162-164.
[9]程洪,史智兴,么炜,等. 基于支持向量机的玉米品种识别[J]. 农业机械学报, 2009, 40(3):180-183.
[10]BENGIO Y. Learning deep architectures for AI[J]. Foundations and Trends Machine Learning, 2009, 2(1):1-127.
[11]KRIZHEVSKY A, SUTSKEVER I, HINTON G. Image net classification with deep convolutional neural networks[C]//PEREIRA F, BUTGES C J C, BOTTOU L, et al. Advances in neural information processing systems 25. Lake Tahoe, Nevada, USA: Curran Associates Inc, 2012:1097-1105.
[12]SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2014, 14(9):1409-1556.
[13]SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//COHEN N, SHARIR O, SHASHUA A. 2015 IEEE conference on computer vision and pattern recognition (CVPR).Boston: IEEE, 2015:1-9.
[14]HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//COHEN N, SHARIR O, SHASHUA A. 2016 IEEE conference on computer vision and pattern recognition (CVPR). Las Vegas: IEEE, 2016:770-778.
[15]魏英姿,谭龙田,欧阳海飞,等. 玉米籽粒完整性识别的深度学习方法[J]. 沈阳理工大学学报, 2016, 35(4):1-6.
[16]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,2018,34(6):1378-1385.
[17]龚丁禧,曹长荣. 基于卷积神经网络的植物叶片分类[J].计算机与现代化,2014(4):12-15.
[18]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,2018,34(1):56-61.
[19]张顺,龚怡宏,王进军. 深度卷积神经网络的发展及其在计算机视觉领域的应用[J]. 计算机学报,2019,42(3):453-482.
[20]林大贵. TensorFlowo +Keras 深度学习人工智能实践应用[M]. 北京: 清华大学出版社, 2018: 67-107.

相似文献/References:

[1]宝华宾,梁帅强,吕远大,等.玉米籽粒蛋白含量Meta-QTL及候选基因分析[J].江苏农业学报,2016,(04):736.[doi:10.3969/j.issn.100-4440.2016.04.004]
　BAO Hua-bin,LIANG Shuai-qiang,LYU Yuan- da,et al.Analysis of meta-QTL and candidate genes related to protein concentration in maize grain[J].,2016,(01):736.[doi:10.3969/j.issn.100-4440.2016.04.004]
[2]印志同,秦秋霞,阚欣,等.玉米快速叶绿素荧光参数全基因组关联分析[J].江苏农业学报,2016,(04):746.[doi:10.3969/j.issn.100-4440.2016.04.005]
　YIN Zhi-tong,QIN Qiu-xia,KAN Xin,et al.Genome-wide association analysis of fast chlorophyll fluorescence parameters in maize[J].,2016,(01):746.[doi:10.3969/j.issn.100-4440.2016.04.005]
[3]岳海旺,陈淑萍,彭海成,等.玉米籽粒灌浆特性品种间比较[J].江苏农业学报,2016,(05):1043.[doi:10.3969/j.issn.1000-4440.2016.05.014]
　YUE Hai-wang,CHEN Shu-ping,PENG Hai-cheng,et al.Grain filling characteristics in maize materials[J].,2016,(01):1043.[doi:10.3969/j.issn.1000-4440.2016.05.014]
[4]周玲,梁帅强,林峰,等.玉米二态性 InDel 位点的鉴定和分子标记开发[J].江苏农业学报,2016,(06):1223.[doi:doi:10.3969/j.issn.1000-4440.2016.06.005]
　ZHOU Ling,LIANG Shuai-qiang,LIN Feng,et al.Biallelic InDel loci detection and molecular marker development in maize[J].,2016,(01):1223.[doi:doi:10.3969/j.issn.1000-4440.2016.06.005]
[5]刘朝茂,李成云.玉米与大豆间作对玉米叶片衰老的影响[J].江苏农业学报,2017,(02):322.[doi:doi:10.3969/j.issn.1000-4440.2017.02.013]
　LIU Chao-mao,LI Cheng-yun.Effects of maize/soybean intercropping on maize leaf senescence[J].,2017,(01):322.[doi:doi:10.3969/j.issn.1000-4440.2017.02.013]
[6]江彬,毕银丽,申慧慧,等.氮营养与AM真菌协同对玉米生长及土壤肥力的影响[J].江苏农业学报,2017,(02):327.[doi:doi:10.3969/j.issn.1000-4440.2017.02.014]
　JIANG Bin,BI Yin-li,SHEN Hui-hui,et al.Synergetic effects of Arbuscular mycorrhizal fungus and nitrogen on maize growth and soil fertility[J].,2017,(01):327.[doi:doi:10.3969/j.issn.1000-4440.2017.02.014]
[7]李国锋,葛敏,吕远大.Opaque2转录因子对玉米α-醇溶蛋白基因家族成员表达的影响[J].江苏农业学报,2015,(06):1224.[doi:doi:10.3969/j.issn.1000-4440.2015.06.006]
　LI Guo-feng,GE Min,L Yuan-da.Differential expression of α-zein family genes regulated by Opaque2 transcription factor[J].,2015,(01):1224.[doi:doi:10.3969/j.issn.1000-4440.2015.06.006]
[8]管莉,张阿英.CaM 与 ZmCCaMK 相互作用参与 BR 诱导的玉米叶片抗氧化防护[J].江苏农业学报,2015,(01):10.[doi:10.3969/j.issn.1000-4440.2015.01.002]
　GUAN Li,ZHANG A-ying.CaM-ZmCCaMK interaction involved in brassinosteroid-induced antioxidant defense in leaves of maize[J].,2015,(01):10.[doi:10.3969/j.issn.1000-4440.2015.01.002]
[9]王元琮,何冰,林峰,等.调控玉米阻止授粉后叶片衰老的QTL定位[J].江苏农业学报,2017,(04):747.[doi:doi:10.3969/j.issn.1000-4440.2017.04.004]
　WANG Yuan-cong,HE Bing,LIN Feng,et al.QTL mapping for pollination-prevention on leaf senescence[J].,2017,(01):747.[doi:doi:10.3969/j.issn.1000-4440.2017.04.004]
[10]田礼欣,李丽杰,刘旋,等.外源海藻糖对盐胁迫下玉米幼苗根系生长及生理特性的影响[J].江苏农业学报,2017,(04):754.[doi:doi:10.3969/j.issn.1000-4440.2017.04.005]
　TIAN Li-xin,LI Li-jie,LIU Xuan,et al.Root growth and physiological characteristics of salt-stressed maize seedlings in response to exogenous trehalose[J].,2017,(01):754.[doi:doi:10.3969/j.issn.1000-4440.2017.04.005]

备注/Memo

备注/Memo:
收稿日期：2019-06-11基金项目：国家自然科学基金项目(11547037、11604181)；山东省研究生教育创新计划项目(01040105305)；海信山东冰箱有限公司研发中心资助项目作者简介：徐岩（1970-），男，山东汶上人，博士，教授，博士生导师，主要从事计算机视觉、图像识别与信号处理等方面的研究工作。(E-mail)xuyan@sdust.edu.cn
更新日期/Last Update: 2020-03-13