[1]李云红,张蕾涛,谢蓉蓉,等.基于AT-DenseNet网络的番茄叶片病害识别方法[J].江苏农业科学,2023,51(21):209-217.
 Li Yunhong,et al.An identification method for tomato leaf disease based on AT-DenseNet network[J].Jiangsu Agricultural Sciences,2023,51(21):209-217.
点击复制

基于AT-DenseNet网络的番茄叶片病害识别方法()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第51卷
期数:
2023年第21期
页码:
209-217
栏目:
农业工程与信息技术
出版日期:
2023-11-05

文章信息/Info

Title:
An identification method for tomato leaf disease based on AT-DenseNet network
作者:
李云红张蕾涛谢蓉蓉朱景坤刘杏瑞
西安工程大学电子信息学院,陕西西安 710048
Author(s):
Li Yunhonget al
关键词:
DenseNet注意力机制迁移学习Focal Loss损失函数叶片病害识别
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
针对番茄叶片病害识别方法存在丢失特征信息、易产生过拟合现象和各类样本数据不均匀的问题,提出了基于混合注意力机制的DenseNet的番病叶片病害识别模型AT-DenseNet。该网络模型以DenseNet121为基础,首先,在DenseNet中融入混合注意力机制模块,实现特征复用,并对混合特征赋予不同权重,提高特征提取能力;在分类网络前设计过渡层,匹配特征维度;其次,引入Focal Loss损失函数,专注难分类样本,改善类间样本不均匀问题;然后,采用迁移学习方法,导入预训练权重,重构全连接层,增强模型鲁棒性;最后,在数据增强的辅助作用下,用Plant Village数据集中的6种番茄叶片病害图像进行测试,试验结果表明,本研究提出的AT-DenseNet网络模型在测试集上的准确率可达99.49%,并通过设置消融试验、绘制混淆矩阵等,验证了病害识别模型的有效性,可为番茄叶片的病害识别提供参考。
Abstract:
-

参考文献/References:

[1]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.
[2]Srivastava A,Ma S,Inoue K.Development of a sensor for automatic detection of downey mildew disease[C]//International Conference on Intelligent Mechatronics and Automation,2004:562-567.
[3]Mondal D,Chakraborty A,Kole D K,et al. Detection and classification technique of yellow vein mosaic virus disease in okra leaf images using leaf vein extraction and Naive Bayesian classifier[C]//International Conference on Soft Computing Techniques & Implementations. IEEE,2016.
[4]Chakraborty S,Paul S,Rahat-uz-Zaman M. Prediction of apple leaf diseases using multiclass support vector machine[C]//International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST). IEEE,2021:147-151.
[5]Kurmi Y,Gangwar S,Chaurasia V,et al. Leaf images classification for the crops diseases detection[J]. Multimed Tools Appl,2022,81:8155-8178.
[6]张子昊,王蓉. 基于MobileFaceNet网络改进的人脸识别方法[J]. 北京航空航天大学学报,2020,46(9):1756-1762.
[7]白志程,李擎,陈鹏,等. 自然场景文本检测技术研究综述[J]. 工程科学学报,2020,42(11):1433-1448.
[8]Wang G,Sun Y,Wang J X. Automatic image-based plant disease severity estimation using deep learning[J]. Computational Intelligence and Neuroscience,2017,2017:2917536.
[9]Tan W X,Zhao C J,Wu H R. Intelligent alerting for fruit-melon lesion image based on momentum deep learning[J]. Multimedia Tools and Applications,2016,75(24):16741-16761.
[10]杨红云,万颖,王映龙,等. 基于批归一化与AlexNet网络的水稻病害识别[J]. 激光与光电子学进展,2021,58(6):164-174.
[11]Syarief M,Setiawan W. Convolutional neural network for maize leaf disease image classification[J]. Telecommunication Computing Electronics and Control,2020,18(3):1376-1381.
[12]鲍文霞,黄雪峰,胡根生,等. 基于改进卷积神经网络模型的玉米叶部病害识别[J]. 农业工程学报,2021,37(6):160-167.
[13]王春山,周冀,吴华瑞,等. 改进Multi-scale ResNet的蔬菜叶部病害识别[J]. 农业工程学报,2020,36(20):209-217.
[14]Huang G,Liu Z,van der Maaten L,et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu,HI,USA,2017:2261-2269.
[15]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(1):129-134.
[16]Zhu H Y,Xie C,Fei Y Q,et al. Attention mechanisms in CNN-based single image super-resolution:a brief review and a new perspective[J]. Electronics,2021,10(10):1187.
[17]黄林生,罗耀武,杨小冬,等. 基于注意力机制和多尺度残差网络的农作物病害识别[J]. 农业机械学报,2021,52(10):264-271.
[18]李晓振,徐岩,吴作宏,等. 基于注意力神经网络的番茄叶部病害识别系统[J]. 江苏农业学报,2020,36(3):561-568.
[19]Zeng W,Li M. Crop leaf disease recognition based on self-attention convolutional neural network[J]. Computers and Electronics in Agriculture,2020,172(1):105341.
[20]侯金秀,李然,邓红霞,等. 融合通道信息注意力网络的叶片病害识别[J]. 计算机工程与应用,2020,56(23):124-129.
[21]贾兆红,张袁源,王海涛,等. 基于Res2Net和双线性注意力的番茄病害时期识别方法[J]. 农业机械学报,2022,53(7):259-266.
[22]胡志伟,杨华,黄济民,等. 基于注意力残差机制的细粒度番茄病害识别[J]. 华南农业大学学报,2019,40(6):124-132.

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(21):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(21):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(21):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(21):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(21):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(21):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(21):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(21):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(21):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(21):155.

备注/Memo

备注/Memo:
收稿日期:2023-02-06
基金项目:陕西省自然科学基础研究重点项目(编号:2022JZ-35)。
作者简介:李云红(1974—),女,辽宁锦州人,博士,教授,研究方向为红外热像测温技术、图像处理、人工智能、信号与信息处理技术。E-mail:hitliyunhong@163.com。
更新日期/Last Update: 2023-11-05