河南农业大学信息与管理科学学院,河南郑州 450046
李婷婷(1991—),女,助教/工程师。研究方向:信息与通信工程。E-mail: 978321488@qq.com
王晴晴 (2000—),女,河南业大学在校本科生。研究方向:深度学习图像处理。E-mail: yu2521benben@163.com
唐 琦 (1994—),女,助教。研究方向:信息与通信工程,深度学习图像处理。E-mail: 751212224@qq.com
张 浩 (1980—),男,副教授。研究方向:深度学习、知识图谱、多模态计算。E-mail: 27343731@qq.com
惠向晖 (1980—),男,副教授。研究方向:云计算、计算机应用。E-mail: truhui@sina.com
纸质出版日期:2023-12-31,
移动端阅览
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, 2023, 6(24): 01-05
LI Ting-ting, WANG Qing-qing, 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, 2023, 6(24): 01-05
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, 2023, 6(24): 01-05 DOI: 10.3969/j.issn.2096-6091.2023.24.001.
LI Ting-ting, WANG Qing-qing, 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, 2023, 6(24): 01-05 DOI: 10.3969/j.issn.2096-6091.2023.24.001.
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,然而实际情况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容易出现过度拟合从而丧失泛化能力。基于此背景,本文提出了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,解决了因少样本而导致模型泛化差的问题;另一方面从深度学习的方向出发,采用并训练AlexNet、ResNet50和MobileNetV2模型,并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。
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 .
小样本病害识别迁移学习深度学习
small sample sizedisease identificationtransfer learningdeep learning
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(6): 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(6): 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(2): 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.
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.
SAI REDDY B, NEERAJA S. Plant leaf disease classification and damage detection system using deep learning models[J]. Multimedia Tools and Applications, 2022, 81(17): 24021-24040.
AFIFI A, ALHUMAM A, ABDELWAHAB A. Convolutional neural network for automatic identification of plant diseases with limited data[J]. Plants, 2020, 10(1): 28.
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, 1812, 9: 27959-27970.
LIU H S. A leaf disease deep learning classification method using EfficientNet[C]//5th International Conference on Computer Information Science and Application Technology (CISAT 2022). SPIE, 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.
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.
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.
0
浏览量
39
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构