基于卷积神经网络的柑橘病害叶片分类算法  

Convolutional Neural Network Based Classification Algorithm for Citrus Disease Leaves

作　　者：施宇 李敏 SHI Yu;LI Min(School of Computer and Information Engineering,Nanning Normal University,Nanning Guangxi 530299,China;Agricultural Science and Technology Information Research Institute,Guangxi Academy Agricultural Sciences,Nanning Guangxi 530007,China)

机构地区：[1]南宁师范大学计算机与信息工程学院,广西南宁530299 [2]广西壮族自治区农业科学院农业科技信息研究所,广西南宁530007

出　　处：《信息与电脑》2022年第3期47-51,共5页Information & Computer

基　　金：广西创新驱动发展专项资金项目“广西智慧柑橘产业关键技术研发与集成示范”(项目编号:桂科AA20108003);广西农业科学院科技发展基金项目“基于卷积神经网络的柑橘黄龙病叶片识别关键技术研究”(项目编号:桂农科2021JM73)。

摘　　要：卷积神经网络在根据图像中的隐藏特征信息来学习样本数据的内在规律,在图像分类应用上有着很好的效果。因此,本文基于卷积神经网络提出了应用于柑橘植物叶片病害图像分类的算法模型。本文提出的E-Res2Net模型在柑橘植物叶片病害8分类真实图像上的识别准确率达到了86.04%,该方法的性能较优于常见的卷积神经网络模型。Convolutional neural networks are effective in learning the intrinsic laws of sample data based on the hidden feature information in images for image classification applications.In this paper,an algorithmic model based on convolutional neural network is proposed for application to image classification of citrus plant leaf diseases.The E-Res2Net model proposed in this paper achieves a recognition accuracy of 86.04%on its own real images of citrus plant leaf disease8 classification,and the performance of this method is better than that of common convolutional neural network models.

关 键 词：卷积神经网络 图像分类 柑橘病害 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]