[1]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):48-55.[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,(01):48-55.[doi:doi:10.3969/j.issn.1000-4440.2019.01.007]
点击复制

基于卷积神经网络和小样本的茶树病害图像识别()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年01期
页码:
48-55
栏目:
植物保护
出版日期:
2019-02-26

文章信息/Info

Title:
Image recognition of tea plant disease based on convolutional neural network and small samples
作者:
孙云云1; 江朝晖1; 董伟2; 张立平2; 饶元1; 李绍稳1
(1.安徽农业大学信息与计算机学院，安徽合肥230036；2.安徽省农业科学院农业经济与信息研究所，安徽合肥230036)
Author(s):
SUN Yun-yun1; JIANG Zhao-hui1; DONG Wei2; ZHNAG Li-ping2; RAO Yuan1; LI Shao-wen1
(1.School of Information and Computer Science, Anhui Agricultural University, Hefei 230036, China;2.Institute of Agricultural Economics and Information, Anhui Academy of Agricultural Sciences, Hefei 230036, China)
关键词:
茶叶病害; 图像识别; 卷积神经网络; 小样本
Keywords:
tea plant leaf disease; image recognition; convolutional neural network; small samples
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2019.01.007
文献标志码:
A
摘要:
以常见且特征相似的茶轮斑病、炭疽病和云纹叶枯病为对象，研究在小样本情况下利用卷积神经网络进行病害图像识别问题。运用7种模式的预处理方法对茶树叶部病害图像样本进行处理，并采用AlexNet经典网络模型进行学习实验，比较、分析其训练及识别效果。结果显示，模式7训练模型精度为933%，平均测试准确率为90%，且对茶轮斑病、炭疽病和云纹叶枯病的正确区分率分别为85%、90%和85%，在预测值和真实值一致性方面优于其他预处理方法。在小样本情况下，该预处理方法可有效区分、识别3种易混病害，且识别精度高，性能好。
Abstract:
Three kinds of common and similar tea diseases including pestalotiopsis theae, tea anthracnose and tea brown blight have been identified by the convolutional neural network(CNN) under the condition of small samples. Seven preprocessing modes were designed and used to process original tea plant leaf disease images automatically. The classic AlexNet network model was used to carry out the learning experiment, and the training and recognition effect was compared and analyzed. The result showed that the accuracy of training model under mode 7 was 93.3%, and the average test accuracy was 90%. And the correct recognition rates of the three diseases (pestalotiopsis theae, tea anthracnose and tea brown blight) were 85%, 90% and 85%, respectively, which were superior to the conventional pretreatment methods in terms of consistency between the predicted value and the true value. In the case of small samples, the proposed pretreatment method can effectively distinguish and identify three kinds of similar diseases, and has high recognition accuracy and good performance.

参考文献/References:

[1]刘威，袁丁，郭桂义，等. 茶树炭疽病病原鉴定[J]. 南方农业学报 ，2017，48（3）：448-453.
[2]王国君，陈利军，熊建伟，等．对茶树炭疽病病菌具拮抗怍用根际促生细菌的分离、筛选及鉴定[J]．江苏农业科学，2017，45(11)：76-78.
[3]张强,杨云祥,唐方圆,等. 茶树主要病害及防治措施研究[J]. 中国农业信息, 2015(12):80-81.
[4]赖军臣,李少昆,明博,等. 作物病害机器视觉诊断研究进展[J]. 中国农业科学, 2009, 42(4):1215-1221.
[5]赵建敏,薛晓波，李琦．基于机器视觉的马铃薯病害识别系统[J]．江苏农业科学，2017，45(2)：198-202.
[6]李彦冬,郝宗波,雷航. 卷积神经网络研究综述[J]. 计算机应用, 2016, 36(9):2508-2515.
[7]MOHANTY S P, HUGHES D P, SALATH M. Using deep learning for image-based plant disease detection [J]. Frontiers in Plant Science, 2016, 22(7):1-10.
[8]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, 34(3):527-532.
[9]CRUZ A C, LUVISI A, BELLIS L D, et al. Vision-based plant disease detection system using transfer and deep learning[C]. Spokane, Washington: American Society of Agricultural and Biological Engineers, 2017:1-9.
[10]AMARA J, BOUAZIZ B, ALGERGAWY A, et al. A deep learning-based approach for banana leaf diseases classification[C]. B. Mitschang, Bonn: Lecture Notes in Informatics, 2017:79-88.
[11]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.
[12]BRAHIMI M, BOUKHALFA K, MOUSSAOUI A. Deep learning for tomato diseases: classification and dymptoms visualization[J]. Applied Artificial Intelligence, 2017,31 (4):299-315.
[13]LIU S, DENG W. Very deep convolutional neural network based image classification using small training sample size[C].Kuala Lumpur, Malaysia: Asian Conference on Pattern Recognition (ACPR), 2016:730-734.
[14]孙俊,谭文军,毛罕平,等. 基于改进卷积神经网络的多种植物叶片病害识别[J]. 农业工程学报, 2017, 33(19):209-215.
[15]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(6):1-11.
[16]吴翔. 基于机器视觉的害虫识别方法研究[D]. 杭州:浙江大学, 2016.
[17]LAI W S, HUANG J B, AHUJA N, et al. Fast and accurate image super-resolution with deep laplacian pyramid networks [J] Computer Vision and Pattern Recognition, 2017, 99:1-14.
[18]YI Y, XI C, DI Z, et al. Deep recursive super resolution network with laplacian pyramid for better agricultural pest surveillance and detection [J]. Computers & Electronics in Agriculture, 2018, 150:26-32.
[19]杨国国,鲍一丹,刘子毅. 基于图像显著性分析与卷积神经网络的茶园害虫定位与识别[J]. 农业工程学报, 2017, 33(6):156-162.
[20]WU Z, HU Z, FAN Q. Superpixel-Based unsupervised change detection using multi-dimensional change vector analysis and svm-based classification[J]. Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012, 1(7):257-262.
[21]HOOCHANG S, ROTH H R, GAO M, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1285.
[22]ZHAO B, WANG M, LIU M. An energy-efficient coarse grained spatial architecture for convolutional neural networks AlexNet[J]. Ieice Electronics Express, 2017, 14(15):1-12.
[23]TANG J L, WANG D, ZHANG Z G, et al. Weed identification based on K-means feature learning combined with convolutional neural network [J]. Computers & Electronics in Agriculture, 2017, 135:63-70.
[24]TANG J L, WANG D, ZHANG Z G, et al. Weed identification based on K-means feature learning combined with convolutional neural network [J]. Computers & Electronics in Agriculture, 2017, 135:63-70.
[25]KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C].Long Beach, CA, USA: International Conference on Neural Information Processing Systems, MIT Press, 2012:1097-1105.
[26]卢蓉,范勇,陈念年,等. 一种提取目标图像最小外接矩形的快速算法[J]. 计算机工程, 2010, 36(21):178-180.
[27]HARRIS J L. Diffraction and resolving power [J]. J Opt Soc Am, 1964, 54(7):931-933.
[28]ANBARJAFARI G, DEMIREL H. Image super resolution based on interpolation of wavelet domain high frequency subbands and the spatial domain input image[J]. ETRI Journal, 2010, 32(3):390-394.
[29]王会鹏,周利莉,张杰. 一种基于区域的双三次图像插值算法[J]. 计算机工程, 2010, 36(19):216-218.

相似文献/References:

[1]邱洪涛,孙裴,侯金波,等.基于Caffe的猪肉新鲜度分级的设计与实现[J].江苏农业学报,2019,(02):461.[doi:doi:10.3969/j.issn.1000-4440.2019.02.029]
　QIU Hong-tao,SUN Pei,HOU Jin-bo,et al.Design and implementation of pork freshness grading based on Caffe[J].,2019,(01):461.[doi:doi:10.3969/j.issn.1000-4440.2019.02.029]
[2]牛学德,高丙朋,南新元,等.基于改进DenseNet卷积神经网络的番茄叶片病害检测[J].江苏农业学报,2022,38(01):129.[doi:doi:10.3969/j.issn.1000-4440.2022.01.015]
　NIU Xue-de,GAO Bing-peng,NAN Xin-yuan,et al.Detection of tomato leaf disease based on improved DenseNet convolutional neural network[J].,2022,38(01):129.[doi:doi:10.3969/j.issn.1000-4440.2022.01.015]

备注/Memo

备注/Memo:
收稿日期：2018-06-08 基金项目：农业部农业物联网技术集成与应用重点实验室开放基金项目（2016KL01）；国际先进农业科技计划的引进与创新项目（No.2016-X34）；安徽农业大学2018年度研究生创新基金项目(2018yjs-63) 作者简介：孙云云（1992-），女，安徽界首人，硕士研究生，研究方向为作物信息处理，(E-mail)sunyunyun0910@sina.com 通讯作者：江朝晖，(E-mail)jiangzh@ahau.edu.cn
更新日期/Last Update: 2019-02-27