A study on the recognition of maize leaf disease based on deep learning with small sample size

Li Tingting; Wang Qingqing; Tang Qi; Zhang Hao; Hui Xianghui

您当前的位置：

首页 >

文章列表页 >

A study on the recognition of maize leaf disease based on deep learning with small sample size

更新时间：2024-06-19

- A study on the recognition of maize leaf disease based on deep learning with small sample size
- New Generation of Information Technology Pages: 1-5(2024)
- 作者机构：
  
  河南农业大学信息与管理科学学院，河南郑州，450046
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.41;TP18
- Published Online：19 June 2024，
扫描看全文
李婷婷,王晴晴,唐琦等.深度学习下的小样本玉米叶片病害识别研究[J].新一代信息技术,

Li Tingting,Wang Qingqing,Tang Qi,et al.A study on the recognition of maize leaf disease based on deep learning with small sample size[J].New Generation of Information Technology,
李婷婷,王晴晴,唐琦等.深度学习下的小样本玉米叶片病害识别研究[J].新一代信息技术, DOI：10.3969/j.issn.2096-6091.XXXX.XX.001.

Li Tingting,Wang Qingqing,Tang Qi,et al.A study on the recognition of maize leaf disease based on deep learning with small sample size[J].New Generation of Information Technology, DOI：10.3969/j.issn.2096-6091.XXXX.XX.001.

摘要

通过深度学习网络模型来实现玉米叶片病害识别分类已成为主流，但深度学习的模型需要拥有较多的数据集，然实际是人工获得的样本种类和数据是有限的，且小样本数据集下的模型易出现过度拟合丧失泛化能力的情况。基于该背景下，本文提出一种迁移学习下的小样本玉米叶片病害识别方法，一方面从迁移学习角度出发，解决因少样本而导致模型泛化差的问题；另一方面从深度学习方向出发，采用并训练AlexNet、ResNet50和MobileNetV2模型，对比三种模型在基于迁移学习下的病害识别准确率。研究结果表明，迁移学习有助于提高小样本泛化能力，MobileNetV2模型更适合小样本玉米叶片病害的识别。

Abstract

It is the main method to recognize maize leaf disease by deep learning network model

but the deep learning model needs more data sets

but in fact

the sample types and data obtained artificially are limited

moreover

the model with small sample data set is prone to over-fitting and loss of generalization ability. Based on this background

this paper proposes a method of identifying maize leaf disease with small samples by migration learning. On the one hand

it solves the problem of poor generalization caused by small samples from the perspective of migration learning

On the other hand

Alexnet

resnet 50 and mobilenet V2 models were adopted and trained from the direction of deep learning to compare the accuracy of disease recognition based on the three models. The results showed that the mobility learning could improve the generalization ability of small samples

and the mobilenet V2 model was more suitable for the identification of leaf diseases in small samples .

关键词

小样本病害识别迁移学习深度学习

Keywords

small sample sizedisease identificationtransfer learningdeep learning

references

赵秀梅,刘悦,郑旭,等. 我国玉米害虫防控现状与对策建议[J]. 现代农药, 2022, 21(06): 6-14.

赵秀梅,刘悦,郑旭,等. 我国玉米害虫防控现状与对策建议[J]. 现代农药, 2022, 21(06): 6-14

何雨霜,王琢,王湘平,等. 深度学习在农作物病害图像识别中的研究进展[J].中国农机化学报, 2023, 44(02): 148-155

李娇娇. 玉米叶部病斑图像智能处理算法的研究与实现[D]. 北京: 北京邮电大学, 2010.

王国伟,刘嘉欣. 基于卷积神经网络的玉米病害识别方法研究[J]. 中国农机化学报, 2021, 42(2): 139- 145. DOI: 10. 13733/ j. jcam. issn. 2095-5553. 2021. 02. 021http://dx.doi.org/10.13733/j.jcam.issn.2095-5553.2021.02.021.

王大庆,禄琳,于兴龙,等. 基于深度迁移学习的EfficientNet玉米叶部病害识别[J]. 东北农业大学学报, 2023, 54(5): 66- 76. DOI: 10. 3969/ j. issn. 1005- 9369. 2023. 05. 008http://dx.doi.org/10.3969/j.issn.1005-9369.2023.05.008.

B. SAI REDDY, S. NEERAJA. Plant leaf disease classification and damage detection system using deep learning models[J]. Multimedia tools and applications, 2022, 81(17): 24021- 24040. DOI: 10. 1007/ s11042- 022- 12147- 0http://dx.doi.org/10.1007/s11042-022-12147-0.

Afifi A,Alhumam A,Abdelwahab A. Convolutional neural net-work for automatic work for identification of plant diseases with limited limited data[J]. Plants, 2020,10(1): 28.

Xu Y,Zhao B, Zhai Y, et al. Maize diseases identification method based on multi-scale Convolutional global pooling neural net-work[J]. IEEE Access,2021, 9: 27959-27970.

HESHENG LIU. A leaf disease deep learning classification method using EfficientNet [C]. //5th International Conference on Computer Information Science and Application Technology (CISAT 2022), Part Two of Two Parts: Chongqing, China.29-31 July 2022.: Society of Photo-Optical Instrumentation Engineers, 2022: 1245154- 1-1245154-5.

郑铖,董伟,高海涛. 一种基于深度学习的玉米病害识别方法[J]. 安徽科技学院学报,2023,37(2):87-94. DOI:10.19608/j.cnki.1673-8772.2023.0016http://dx.doi.org/10.19608/j.cnki.1673-8772.2023.0016.

叶名炀,张杰强. 基于轻量化网络MobileNetV2的玉米病害识别研究[J]. 现代计算机, 2022, 28(11): 46-50. DOI: 10. 3969/j. issn. 1007-1423. 2022. 11. 008http://dx.doi.org/10.3969/j.issn.1007-1423.2022.11.008.

张正超,方文博,郭永刚. 基于Resnet50的西藏高原地区玉米病害识别系统[J]. 高原农业, 2022, 6(2): 164- 172, 212. DOI: 10.19707/j. cnki. jpa. 2022. 02. 010http://dx.doi.org/10.19707/j.cnki.jpa.2022.02.010.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Bone Age Prediction Based on Lightweight VGG16 and Attention Mechanism

Person Re-Identification Based on Text-Assisted Image Information

Microscopic Displacement Image Classification Based on Deep Learning

Research on Classification of Medicinal Plant Leaves Based on Improved CNN

Related Author

HAN Xue-shan

CHEN Guang-xin

GUO Jin-xing

GUO Wei

GUO Jinxing

Chen Guangxin

HAN Xueshan

HE Xiao-hai

Related Institution

School of Medical Imaging， Mudanjiang Medical University

Hongqi Hospital Affliated to Mudanjiang Medical University

College of Life Science， Mudanjiang Medical University

College of Electronics and Information Engineering， Sichuan University

Chengdu Xitu Technology Co. Ltd

⁰