面向移动端的植物病害图像识别方法及其应用-《江苏农业科学》

文章信息/Info

Title:: Mobile-oriented plant disease image recognition method and its application

作者:: 杨祥; 段军明; 董明刚; 桂林理工大学信息科学与工程学院，广西桂林 541000

Author(s):: Yang Xiang; et al

关键词:: 卷积神经网络; 植物病害; ShuffleNet V2; 图像识别; CSPNet; ECA

Keywords:: -

分类号:: TP183；TP391.41

DOI:: -

文献标志码:: A

摘要:: 针对传统卷积神经网络(CNN)在病害图像识别时需要较高的存储空间和计算资源问题，提出一种基于轻量级CNN植物病害图像识别网络CSP-ShuffleNet V2来降低识别成本。CSP-ShuffleNet V2模型基于ShuffleNet V2网络，首先，将卷积核大小由3×3改为5×5扩大病斑图像全局感受野；其次，采用CSPNet结构来改进网络特征层；最后，再引入通道注意力(ECA)模块用于增强图像病斑通道特征信息。采用AI Challenger平台提供的公共植物病害数据集进行训练和测试。试验结果表明，CSP-ShuffleNet V2网络模型识别准确率为90.34%，比原始ShuffleNet V2网络模型提高2.23%，参数量也减少29.6%，权重大小仅为13.5 MB。与ResNet50、MobileNet V2、GoogleNet、DenseNet121网络相比，CSP-ShuffleNet V2网络不仅降低了网络计算量和参数量，而且收敛速度更快、分类效果更好。最终将模型离线部署在Android平台实现了植物病害移动端智能检测，为植物病害防治和诊断提供参考依据。

Abstract:: -

参考文献/References:

［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，2019，35(1)：48-55.
［2］许景辉，邵明烨，王一琛，等. 基于迁移学习的卷积神经网络玉米病害图像识别［J］. 农业机械学报，2020，51(2)：230-236，253.
［3］宋晨勇，白皓然，孙伟浩，等. 基于GoogLeNet改进模型的苹果叶病诊断系统设计［J］. 中国农机化学报，2021，42(7)：148-155.
［4］刘翱宇，吴云志，朱小宁，等. 基于深度残差网络的玉米病害识别［J］. 江苏农业学报，2021，37(1)：67-74.
［5］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(1/2)：49-59.
［6］Simonyan K，Zisserman A. Very deep convolutional networks for large-scale image recognition［C］//ICLR. San Diego，2015.
［7］Szegedy C，Liu W，Jia Y Q，et al. Going deeper with convolutions［C］//Computer Vision and Pattern Recognition.Boston，2015：1-9.
［8］He K M，Zhang X Y，Ren S Q，et al. Deep residual learning for image recognition［C］//Computer Vision and Pattern Recognition.Las Vegas，2016：770-778.
［9］Wang C Y，Liao H Y M，Wu Y H，et al. CSPNet：A new backbone that can enhance learning capability of CNN［C］//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2020：390-391.
［10］Wang Q L，Wu B G，Zhu P F，et al. ECA-net：efficient channel attention for deep convolutional neural networks［C］//Computer Vision and Pattern Recognition. Seattle，2020：11531-11539.
［11］Howard A G，Zhu M L，Chen B，et al. MobileNets：efficient convolutional neural networks for mobile vision applications［Z/OL］. (2017-04-17)［2022-01-01］. https：//arxiv.org/abs/1704.04861.
［12］Hu J，Shen L，Albanie S，et al. Squeeze-and-excitation networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42(8)：2011-2023.
［13］韩兴，张红英，张媛媛. 基于高效通道注意力网络的人脸表情识别［J］. 传感器与微系统，2021，40(1)：118-121.
［14］韩林洁，石春鹏，张建超. 基于一维卷积神经网络的轴承剩余寿命预测［J］. 制造业自动化，2020，42(3)：10-13.
［15］Akiba T，Suzuki S，Fukuda K. Extremely large minibatch SGD：training ResNet-50 on ImageNet in 15 minutes［Z/OL］. (2017-11-17)［2022-01-01］. https：//arxiv.org/abs/1711.04325.
［16］Ma N，Zhang X，Zheng H T，et al. ShuffleNet V2：practical guidelines for efficient cnn architecture design［C］//Proceedings of the European Conference on Computer Vision (ECCV). 2018：116-131.
［17］Ioffe S，Szegedy C. Batch normalization：accelerating deep network training by reducing internal covariate shift［C］//International Conference on Machine Learning. 2015：448-456.
［18］Hinton G E，Srivastava N，Krizhevsky A，et al. Improving neural networks by preventing co-adaptation of feature detectors［J］. Computer Science，2012，3(4)：212-223.

相似文献/References:

[1]马国胜,陈娟,薛毅.苏南地区绿篱病害发生规律与生态控制技术[J].江苏农业科学,2013,41(11):131.
　Ma Guosheng,et al.Occurrence and eco-control technology of hedgerow diseases in Southern Jiangsu[J].Jiangsu Agricultural Sciences,2013,41(4):131.
[2]易龙,张亚,廖晓兰,等.链霉菌防治植物病害的研究进展[J].江苏农业科学,2014,42(03):91.
　Yi Long,et al.Research progress of streptomyces controlling plant diseases[J].Jiangsu Agricultural Sciences,2014,42(4):91.
[3]王超,郭坚华,席运官,等.拮抗细菌在植物病害生物防治中应用的研究进展[J].江苏农业科学,2017,45(18):1.
　Wang Chao,et al.Research progress on application of antagonistic bacteria in biological control of plant diseases[J].Jiangsu Agricultural Sciences,2017,45(4):1.
[4]梁万杰,曹宏鑫.基于卷积神经网络的水稻虫害识别[J].江苏农业科学,2017,45(20):241.
　Liang Wanjie,et al.Identification of rice insect pests based on CNN model[J].Jiangsu Agricultural Sciences,2017,45(4):241.
[5]宋薇薇,朱辉,余凤玉,等.植物内生菌及其对植物病害的防治作用综述[J].江苏农业科学,2018,46(06):12.
　Song Weiwei,et al.Plant endophytes and their control effects on plant diseases：a review[J].Jiangsu Agricultural Sciences,2018,46(4):12.
[6]赵建敏,李艳,李琦,等.基于卷积神经网络的马铃薯叶片病害识别系统[J].江苏农业科学,2018,46(24):251.
　Zhao Jianmin,et al.Potato leaf disease identification system based on convolutional neural network[J].Jiangsu Agricultural Sciences,2018,46(4):251.
[7]魏青迪,范昊,张承明.基于ECLDeeplab模型提取华北地区耕地的方法[J].江苏农业科学,2020,48(04):209.
　Wei Qingdi,et al.A method for extracting cultivated land in North China based on ECLDeeplab model[J].Jiangsu Agricultural Sciences,2020,48(4):209.
[8]陈峰,谷俊涛,李玉磊,等.基于机器视觉和卷积神经网络的东北寒地玉米害虫识别方法[J].江苏农业科学,2020,48(18):237.
　Chen Feng,et al.Recognition method of corn pests in northeast cold region based on machine vision and convolutional neural network[J].Jiangsu Agricultural Sciences,2020,48(4):237.
[9]陈旭君,王承祥,孙福,等.基于改进Faster R-CNN的田间植株幼苗检测方法[J].江苏农业科学,2021,49(4):159.
　Chen Xujun,et al.Detection method for plant seedlings in fields based on improved Faster R-CNN[J].Jiangsu Agricultural Sciences,2021,49(4):159.
[10]黎振,陆玲,熊方康.基于k-means分割和迁移学习的番茄病理识别[J].江苏农业科学,2021,49(12):156.
　Li Zhen,et al.Tomato pathological recognition based on k-means segmentation and transfer learning[J].Jiangsu Agricultural Sciences,2021,49(4):156.

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

文章信息/Info

参考文献/References:

相似文献/References:

备注/Memo

常用功能

导航/Navigate

工具/Tools

统计/Statistics