基于改进ResNet34的玉米病害分类研究  

Research on corn disease classification based on improved ResNet34

作　　者：李涵 唐友 辛鹏[1] 杨牧 Li Han;Tang You;Xin Peng;Yang Mu(Jilin Institute of Chemical Technology,Jilin 132022,China;Jilin College of Agricultural Science and Technology,Jilin 132101,China;FAW-Tokico Shock Absorber Co.,Ltd.,Changchun 130001,China)

机构地区：[1]吉林化工学院,吉林吉林132022 [2]吉林农业科技学院,吉林吉林132101 [3]一汽东机工减振器有限公司,吉林长春130001

出　　处：《无线互联科技》2023年第13期127-130,共4页Wireless Internet Technology

基　　金：吉林省科技发展计划项目,项目名称:基于数据挖掘技术的全基因组选择方法研发及云计算平台体系构建,项目编号:YDZJ202201ZYTS692。

摘　　要：玉米病害分类是一个具有挑战性的问题,因为病害的形态和颜色等特征相似,使得分类难度较大。文章基于深度学习技术,对玉米病害进行分类研究,提出了一种名为CBAM_ResNet34的卷积神经网络模型。该模型在ResNet34基础上加入了CBAM注意力模块,可以更好地提取玉米病害特征,以提高模型的分类性能。本文使用公开玉米病害数据集,共包含8种类别,通过数据增强技术进行数据扩充得到17 670张图片,可以有效提高模型的泛化能力。将改进后的模型与ResNet34模型进行实验对比,实验结果表明,CBAM_ResNet34模型的分类准确率为88.1%,相比ResNet34提高了1.1%。该模型能够有效地对玉米病害进行分类识别,为玉米产业的发展和可持续利用提供了一种新的方法和思路。Corn disease classification is a challenging problem as the diseases have similar morphological and color features,making classification difficult.In this paper,a convolutional neural network model named CBAM_ResNet34 is proposed for corn disease classification using deep learning techniques.The model enhances ResNet34 by adding CBAM attention modules to better extract corn disease features and improve classification performance.A publicly available corn disease dataset containing 8 categories was used,and data augmentation techniques were applied to generate 17670 images for improved model generalization.Experimental comparison between the improved model and ResNet34 showed that CBAM_ResNet34 achieved a classification accuracy of 88.1%,which is a 1.1%improvement over ResNet34.The proposed model effectively recognizes and classifies corn diseases,providing new methods and ideas for the development and sustainable utilization of the corn industry.

关 键 词：ResNet34模型 卷积神经网络 数据增强 CBAM注意力模块 玉米病害分类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]