|本期目录/Table of Contents|

[1]马晓,邢雪,武青海.基于改进ConvNext的复杂背景下玉米叶片病害分类[J].江苏农业科学,2023,51(19):190-197.
 Ma Xiao,et al.Maize leaf disease classification under complex background based on improved ConvNext[J].Jiangsu Agricultural Sciences,2023,51(19):190-197.
点击复制

基于改进ConvNext的复杂背景下玉米叶片病害分类(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19期
页码:
190-197
栏目:
农业工程与信息技术
出版日期:
2023-10-05

文章信息/Info

Title:
Maize leaf disease classification under complex background based on improved ConvNext
作者:
马晓1邢雪1武青海12
1.吉林化工学院信息与控制工程学院,吉林吉林 132022; 2.吉林农业科技学院电气与信息工程学院,吉林吉林 132101
Author(s):
Ma Xiaoet al
关键词:
图像分类ConvNeXt注意力机制数据增强玉米叶片病害
Keywords:
-
分类号:
S126;TP181
DOI:
-
文献标志码:
A
摘要:
针对玉米叶片病害分类过程中存在叶片背景复杂且背景与被识别叶片具有较高相似度的问题,提出一种改进的ConvNeXt算法。首先通过随机遮挡等数据增强操作多样化病害数据集,增强网络的抗干扰能力,从而提高了模型的鲁棒性。其次,为了提高网络的分类准确度,在ConvNeXt网络的基础上融合多个注意力模块,使网络更加关注具有判别性的特征,以减少背景的干扰,并在注意力模块中使用LeakyReLu激活函数从而避免网络在输入为负值时神经元不学习的情况。最后,以具有3种玉米常见叶片病害的图像和健康叶片作为分类样本,采用改进后的ConvNeXt模型与相同样本数量和条件下的原ConvNeXt、ResNet50以及Swin Transformer进行试验和对比分析,试验表明,改进后的网络模型在测试集的平均分类准确率为91.77%,优于ResNet50(85.64%)、ConvNeXt-T(79.91%)和Swin Transformer(89.09%)3个对比模型,证明了通过改进后的ConvNeXt进行叶片病害的特征提取,提高了在复杂背景下玉米叶片病害的分类精度。
Abstract:
-

参考文献/References:

[1]傅俊范,景殿玺,刘震,等. 玉米叶部病害流行动态及预测预警研究进展[J]. 吉林农业大学学报,2016,38(6):651-655.
[2]曲维莉. 玉米常见病害防治措施[J]. 农民致富之友,2018(13):139.
[3]李颖. 玉米主要病虫害综合防治技术探究[J]. 农家参谋,2022(16):60-62.
[4]Dhakal A,Shakya S. Image-based plant disease detection with deep learning[J]. International Journal Computer Trends Technology,2018,61(1):26-29.
[5]Ngugi L,Abelwahab M,Abo-Zahhad M. Recent advances in image processing techniques for automated leaf pest and disease recognition-a review[J]. Information Processing in Agriculture,2021,8(1):27-51.
[6]赵春江,李瑾,冯献. 面向2035年智慧农业发展战略研究[J]. 中国工程科学,2021,23(4):1-9.
[7]Panigrah K P,Das H,Sahoo A K,et al. Maize leaf disease detection and classification using machine learning algorithms[J]. Advances in Intelligent Systems and Computing,2020,1119:659-669.
[8]吕洁,卖雄发,谢妙. 基于二维Gabor小波和孪生支持向量机的图像识别算法[J]. 南京理工大学学报,2022,46(1):113-118.
[9]Wagle S A,Harikrishna R. Comparison of plant leaf classification using modified AlexNet and support vector machine[J]. Traitement du Signal:Signal Image Parole,2021,38(1):79-87.
[10]Lecun Y,Bengio Y,Hinton G. Deep learning[J]. Nature,2015,521(1):436-444.
[11]Priyandarshini R A,Arivazhagan S,Arun M,et al. Maize leaf disease classification using deep convolutional neural networks[J]. Neural Computer & Application,2019,31(1):8887-8895.
[12]黄英来,艾昕. 改进残差网络在玉米叶片病害图像的分类研究[J]. 计算机工程与应用,2021,54(23):178-184.
[13]刘合兵,鲁笛,席磊. 基于MobileNetV2和迁移学习的玉米病害识别研究[J]. 河南农业大学学报,2022,56(6):1041-1051.
[14]Singh R K,Tiwari A,Gupta R K. Deep transfer modeling for classification of maize plant leaf disease[J]. Multimedia Tools and Application,2022,81(5):6051-6067.
[15]Lin Z,Mu S,Shi A,et al. A novel method of maize leaf disease image identification based on a multichannel convolutional neural network[J]. Transaction of the ASABE,2018,61 (5):1461-1474.
[16]Xu Y L,Zhao B,Zhai Y T,et al. Maize diseases identification method based on multi-scale convolutional global pooling neural network[J]. IEEE Access,2021,9:27959-27970.
[17]Fujita E,Kawaski Y,Uga H,et al. Basic investigation on a robust and practical plant diagnostic system[J]. IEEE International Conference Machine Learning Applications,2016,15:989-992.
[18]管正雄. 基于深度生成模型的数据增强方法研究[D]. 南京:南京信息工程大学,2019.
[19]Hughes D P ,Salathe M . An open access repository of images on plant health to enable the development of mobile disease diagnostics[J]. Computer Science,2015,1:1-13.
[20]张宸嘉,朱磊,俞璐. 卷积神经网络中的注意力机制综述[J]. 计算机工程与应用,2021,57(20):64-72.
[21]Guo W J,Feng Q,Li X Z,et al. Grape leaf disease detection based on attention mechanisms[J]. International Journal of Agricultural and Biological Engineering,2022,15(5):205-212.
[22]Wang Y Y,Tao J,Gao H. Corn disease recognition based on attention mechanism network[J]. Axioms,2022,11(9):480.
[23]Zhang M,Su H,Wen J.Classification of flower image based on attention mechanism and multi-loss attention network[J]. Computer Communications,2021,179(1):307-317.
[24]Qian Z Z,Mu J,Tian F,et al. Facial expression recognition based on strong attention mechanism and residual network[J]. Multimedia Tools and Applications,2022,81(30):44109-44121.
[25]Hu J,Shen L,Albanie S,et al. Squeeze-and-excitation networks[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2018:7132-7141.
[26]Wang Q,Wu B,Zhu P,et al. ECA-Net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2020:1-12.
[27]Li X,Wang W,Hu X,et al. Selective kernel networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2019:1-12.
[28]Woo S,Park J,Lee J Y,et al. CBAM:convolutional block attention module[C]//Proceeding of the European Conference on Computer Vision(ECCV),2018:3-19.
[29]Liu Z,Mao H,Wu C Y,et al. A ConvNet for the 2020s[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR),2022:11976-11986.
[30]He K,Zhang X,Ren S,et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2016:770-778.
[31]Liu Z,Lin Y,Cao Y,et al. Swin transformer:hierarchical vision transformer using shifted windows[C]//IEEE/CVF International Conference on Computer Vision,2021:10012-10022.
[32]Xu B,Li M,Wang N,et al. Empirical evaluation of rectified activations in convolutional network[J]. arXiv,2015,27:1-5.
[33]肖经纬,田军委,王沁,等. 基于改进残差网络的果实病害分类方法[J]. 计算机工程,2020,46(9):221-225.
[34]宋亚飞,王晓丹,雷蕾. 基于混淆矩阵的证据可靠性评估[J]. 系统工程与电子技术,2015,37(4):974-978.

相似文献/References:

[1]余骥远,高尚兵,李洁,等.基于MS-PLNet和高光谱图像的绿豆叶斑病病级分类[J].江苏农业科学,2023,51(6):178.
 Yu Jiyuan,et al.Classification of mung bean leaf spot based on MS-PLNet and hyperspectral images[J].Jiangsu Agricultural Sciences,2023,51(19):178.
[2]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(19):155.
[3]谭彬,蔡健荣,许骞,等.基于注意力机制改进卷积神经网络的柑橘病虫害识别[J].江苏农业科学,2024,52(8):176.
 Tan Bin,et al.Recognition of citrus pests and diseases based on attention mechanism improved convolutional neural networks[J].Jiangsu Agricultural Sciences,2024,52(19):176.
[4]王晶,崔艳荣.基于改进MobileNet v3-Small模型的草莓病害识别方法[J].江苏农业科学,2024,52(10):225.
 Wang Jing,et al.Strawberry disease identification method based on improved MobileNet v3-Small model[J].Jiangsu Agricultural Sciences,2024,52(19):225.
[5]张澳雪,崔艳荣,李素若,等.基于改进RegNet网络的玉米叶片病害识别研究[J].江苏农业科学,2024,52(11):216.
 Zhang Aoxue,et al.Identification of maize leaf diseases based on improved RegNet network[J].Jiangsu Agricultural Sciences,2024,52(19):216.
[6]李豫晋,沈陆明,何少芳,等.基于改进MobileNet v3的苹果叶片病害识别研究[J].江苏农业科学,2024,52(12):224.
 Li Yujin,et al.Identification of apple leaf diseases based on improved MobileNet v3[J].Jiangsu Agricultural Sciences,2024,52(19):224.
[7]王浩宇,崔艳荣.基于改进ShuffleNet v2模型的苹果叶片病害识别方法[J].江苏农业科学,2024,52(13):214.
 Wang Haoyu,et al.Apple leaf disease identification method based on improved ShuffleNet v2 model[J].Jiangsu Agricultural Sciences,2024,52(19):214.
[8]杨德龙,李婧.基于注意力与小平方核的ConvNeXt农业杂草识别方法[J].江苏农业科学,2024,52(14):207.
 Yang Delong,et al.ConvNeXt agricultural weed recognition method based on attention and small square kernel[J].Jiangsu Agricultural Sciences,2024,52(19):207.
[9]梁倩倩,陈勇,崔艳荣.基于改进轻量化网络MobileViT的苹果叶片病虫害识别方法[J].江苏农业科学,2024,52(14):222.
 Liang Qianqian,et al.An apple leaf pest identification method based on improved lightweight network MobileViT[J].Jiangsu Agricultural Sciences,2024,52(19):222.
[10]戴硕,白涛,李东亚,等.基于知识蒸馏及改进ShuffleNet v2的棉花病虫害识别方法[J].江苏农业科学,2024,52(15):222.
 Dai Shuo,et al.Recognition of cotton pests and diseases based on knowledge distillation and improved ShuffleNet v2[J].Jiangsu Agricultural Sciences,2024,52(19):222.

备注/Memo

备注/Memo:
收稿日期:2023-02-10
基金项目:吉林省智慧农业工程研究中心项目(编号:JLNKU2015);吉林省特色高水平学科新兴交叉学科“数字农业”(编号:JLXK20180319);吉林省高等教育教学改革研究课题(编号:JLJY202338594176)。
作者简介:马晓(1999—),女,山东临沂人,硕士研究生,研究方向为人工智能图像分类。E-mail:1925709084@qq.com。
通信作者:武青海,硕士,副教授,主要从事图形图像处理及农业信息化研究。E-mail:57922126@qq.com。
更新日期/Last Update: 2023-10-05