|本期目录/Table of Contents|

[1]吴刚正,蔡成岗,朱瑞瑜.基于注意力机制和残差网络的苹果叶片病害分类[J].江苏农业科学,2023,51(18):177-185.
　Wu Gangzheng,et al.Apple leaf disease classification based on attention mechanism and residual network[J].Jiangsu Agricultural Sciences,2023,51(18):177-185.
点击复制

基于注意力机制和残差网络的苹果叶片病害分类(PDF)
分享到：

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第51卷
期数:
2023年第18期
页码:
177-185
栏目:
农业工程与信息技术
出版日期:
2023-09-20

文章信息/Info

Title:
Apple leaf disease classification based on attention mechanism and residual network
作者:
吴刚正; 蔡成岗; 朱瑞瑜
浙江科技学院生物与化学工程学院/浙江省农产品化学与生物加工技术重点实验室，浙江杭州 310023
Author(s):
Wu Gangzheng; et al
关键词:
苹果叶片病害分类; 注意力机制; 特征提取; 残差网络; P-D-ECA-ResNet101
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
苹果叶片病害的高效准确识别有助于合理使用杀虫剂、肥料等农业资源，进而保证苹果的产量与质量。为提高苹果叶片病害识别的准确率，提出一种残差网络与注意力机制结合的苹果叶片病害识别模型：P-D-ECA-ResNet101。首先构建苹果叶片病害数据集，然后使用常见的4种网络模型在构建的数据集上进行训练，选取训练效果最好的ResNet101为骨干网络模型，通过推迟下采样(delayed downsampling)、拆解大卷积层以及引入高效通道(efficient channel attention module，ECA)注意力模块对ResNet101网络模型进行优化，最后通过特征图可视化展示改进后网络模型的识别机制。试验结果表明，推迟下采样可以增强模型特征提取能力，拆解大卷积层可以有效减少模型的复杂度，引入ECA注意力模块可以削弱无效特征信息对模型的干扰。改进后的P-D-ECA-ResNet101模型在构建的苹果叶片病害测试集上的平均识别准确率达到96.20%，相较于原模型ResNet101提升了2.20百分点。特征图可视化分析表明改进后的P-D-ECA-ResNet101模型可以更好地聚焦于病斑区域。本研究提出的P-D-ECA-ResNet101模型较ResNet101模型具有更深的网络结构，更好的特征提取能力，更强的抗干扰能力，可为田间环境下的苹果叶片病害识别提供参考。
Abstract:
-

参考文献/References:

［1］Sethy P K，Barpanda N K，Rath A K，et al. Deep feature based rice leaf disease identification using support vector machine［J］. Computers and Electronics in Agriculture，2020，175(1)：105527.
［2］翟肇裕，曹益飞，徐焕良，等. 农作物病虫害识别关键技术研究综述［J］. 农业机械学报，2021，52(7)，1-18.
［3］Sladojevic S，Arsenovic M，Anderla A，et al. Deep neural networks based recognition of plant diseases by leaf image classification［J］. Computational Intelligence and Neuroscience，2016，2016：3289801.
［4］Patil R，Kumar S. Bibliometric survey on diagnosis of plant leaf diseases using artificial intelligence［J］. International Journal of Modern Agriculture，2020，9(3)：1111-1131.
［5］Kalwad P D，Kanakaraddi S G，Preeti T，et al. Apple leaf disease detection and analysis using deep learning technique［M］//Information And Communication Technology For Competitive Strategies. Berlin：Springer，2022：803-814.
［6］Bin L，Ding Z F，Tian L L，et al. Grape leaf disease identification using improved deep convolutional neural networks［J］. Frontiers in Plant Science，2020，11：1082.
［7］Zeng W H，Li M.Crop leaf disease recognition based on self-attention convolutional neural network［J］. Computers and Electronics in Agriculture，2020，172：105341.
［8］李淼，王敬贤，李华龙，等. 基于CNN和迁移学习的农作物病害识别方法研究［J］. 智慧农业，2019，1(3)：46-55.
［9］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.
［10］Gonzalez-Huitron V，León-Borges J A，Rodriguez-Mata A E，et al. Disease detection in tomato leaves via CNN with lightweight architectures implemented in Raspberry Pi 4［J］. Computers and Electronics in Agriculture，2021，181：105951.
［11］Germano M，Augusto M S，Tatiana P，et al. Benchmark of deep learning and a proposed HSV colour space models for the detection and classification of greenhouse tomato［J］. Agronomy，2022，12(2)：356.
［12］Tang Z，Yang J L，Li Z，et al. Grape disease image classification based on lightweight convolution neural networks and channelwise attention［J］. Computers and Electronics in Agriculture，2020，178：105735.
［13］Zhu X Y，Li J J，Jia R C，et al. LAD-net：a novel light weight model for early apple leaf pests and diseases classification［J］. IEEE/ACM Transactions on Computational Biology and Bioinformatics，2023，20(2)：1156-1169.
［14］Zhao S Y，Liu J Z，Wu S.Multiple disease detection method for greenhouse-cultivated strawberry based on multiscale feature fusion Faster R_CNN［J］. Computers and Electronics in Agriculture，2022，199：107176.
［15］He K M，Zhang X Y，Ren S Q，et al. Deep residual learning for image recognition［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas：IEEE，2016：770-778.
［16］Szegedy C，Vanhoucke V，Ioffe S，et al. Rethinking the inception architecture for computer vision［EB/OL］. (2015-12-11)［2022-11-01］. https：//arxiv.org/abs/1512.00567.
［17］Zhang H，Zu K K，Lu J，et al. EPSANet：an efficient pyramid squeeze attention block on convolutional neural network［EB/OL］. (2021-07-22)［2022-11-01］. https：//arxiv.org/abs/2105.14447.
［18］Krizhevsky A，Sutskever I，Hinton G.ImageNet classification with deep convolutional neural networks［J］. Advances in Neural Information Processing Systems，2012，25(2)：84-90.
［19］Simonyan K，Zisserman A.Very deep convolutional networks for large-scale image recognition［EB/OL］. (2015-04-10)［2022-10-11］. https：//arxiv.org/abs/1409.1556.
［20］Szegedy C，Liu W，Jia Y Q，et al. Going deeper with convolutions［C］//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston：IEEE，2015：1-9.

相似文献/References:

[1]张会敏,谢泽奇,张善文.基于注意力胶囊网络的作物病害识别方法[J].江苏农业科学,2022,50(6):101.
　Zhang Huimin,et al.Study on crop disease recognition method based on attention capsule network[J].Jiangsu Agricultural Sciences,2022,50(18):101.
[2]李萍,邵彧,齐国红,等.基于跨深度学习模型的作物病害检测方法[J].江苏农业科学,2022,50(8):193.
　Li Ping,et al.Crop disease detection method based on cross deep learning model[J].Jiangsu Agricultural Sciences,2022,50(18):193.
[3]荣民希,班彬,王智峥,等.基于Macbm-RCNN的叶片周长和面积测量方法[J].江苏农业科学,2022,50(13):199.
　Rong Minxi,et al.Measurement method of leaf circumference and area based on Macbm-RCNN[J].Jiangsu Agricultural Sciences,2022,50(18):199.
[4]崔艳荣,卞珍怡,高英宁.基于生成对抗网络的花卉识别方法[J].江苏农业科学,2022,50(22):200.
　Cui Yanrong,et al.Flower recognition method based on generative adversarial networks[J].Jiangsu Agricultural Sciences,2022,50(18):200.
[5]马驰,吴华瑞,于会山.基于YOLOX的穴盘甘蓝病害检测方法[J].江苏农业科学,2023,51(8):193.
　Ma Chi,et al.Detection method of cabbage disease based on YOLOX[J].Jiangsu Agricultural Sciences,2023,51(18):193.
[6]温艳兰,陈友鹏,王克强,等.基于迁移学习和改进残差网络的复杂背景下害虫图像识别[J].江苏农业科学,2023,51(8):171.
　Wen Yanlan,et al.Recognition of pest images under complex background based on transfer learning and improved residual network[J].Jiangsu Agricultural Sciences,2023,51(18):171.
[7]赵嘉威,田光兆,邱畅,等.基于改进YOLOv4算法的苹果叶片病害检测方法[J].江苏农业科学,2023,51(9):193.
　Zhao Jiawei,et al.Detection method of apple leaf diseases based on improved YOLOv4 algorithm[J].Jiangsu Agricultural Sciences,2023,51(18):193.
[8]温钊发,蒲智,程曦,等.基于轻量级MIE_Net的田间农作物病害识别[J].江苏农业科学,2023,51(10):176.
　Wen Zhaofa,et al.Field crop disease identification based on lightweight MIE_Net[J].Jiangsu Agricultural Sciences,2023,51(18):176.
[9]沈志豪,刘金江,张建洋.基于改进YOLOX-s的田间麦穗检测及计数[J].江苏农业科学,2023,51(12):164.
　Shen Zhihao,et al.Detection and counting of wheat ears in field based on improved YOLOX-s[J].Jiangsu Agricultural Sciences,2023,51(18):164.
[10]曾晏林,贺壹婷,蔺瑶,等.基于BCE-YOLOv5的苹果叶部病害检测方法[J].江苏农业科学,2023,51(15):155.
　Zeng Yanlin,et al.An apple leaf disease detection method based on BCE-YOLOv5[J].Jiangsu Agricultural Sciences,2023,51(18):155.

备注/Memo

备注/Memo:
收稿日期：2022-11-03
基金项目：浙江省基础公益研究计划(编号：LGN20C200012)；浙江省重点研发计划(编号：2020C02038)。
作者简介：吴刚正(1998—)，男，浙江温州人，硕士研究生，主要从事农业机械研究。E-mail：wgz15990709984@163.com。
通信作者：朱瑞瑜，博士，副教授，研究方向为食品安全控制、功能性食品。E-mail：zhuruiyu7@126.com。
更新日期/Last Update: 2023-09-20