深度学习在基于叶片的油茶品种识别中的研究  

Research on recognition of Camellia oleifera leaf varieties based on deep learning

作　　者：尹显明 棘玉 张日清[1] 莫登奎[1] 彭邵锋[2] 韦维[3] YIN Xianming;JI Yu;ZHANG Riqing;MO Dengkui;PENG Shaofeng;WEI Wei(College of Forestry,Central South University of Forestry and Technology,Changsha 410004,China;Hunan Academy of Forestry,Changsha 410004,China;Guangxi Forestry Research Institute,Nanning 530002,China)

机构地区：[1]中南林业科技大学林学院,湖南长沙410004 [2]湖南省林业科学院,湖南长沙410004 [3]广西壮族自治区林业科学研究院,广西南宁530002

出　　处：《南京林业大学学报（自然科学版）》2023年第3期29-36,共8页Journal of Nanjing Forestry University：Natural Sciences Edition

基　　金：广西壮族自治区林业科学研究院横向课题(GXLKY-15126083);湖南省林业科技创新专项基金项目(XLK201939)。

摘　　要：【目的】采用深度学习方法开展基于叶片的油茶品种识别研究,开发油茶品系图像识别技术,为油茶品种鉴别提供科学依据。【方法】选择自然光照条件下生长的11个油茶品种叶片作为研究对象,采集完整、无明显病虫害的叶片,以白色硬纸板为背景,利用智能手机对叶片的正、背面进行图像采集,通过可用性筛选去除无效图像,构建图像数量为2 791张的油茶叶片品种数据集,采用深度学习网络(GoogLeNet、ResNet)对11个油茶品种的叶片图像进行识别研究。【结果】GoogLeNet和ResNet网络均能满足基于叶片的油茶品种识别要求,总体识别准确率、召回率的调和平均值(F_(1))分别达94.0%和80.7%;其中GoogLeNet网络识别效果更好,平均准确率、召回率、多分类模型指标宏观F_(1)(Macro F_(1))和微观F_(1)(Micro F_(1))分别为94.1%、94.0%、94.0%和96.9%,其对油茶品种编号1和编号8的识别召回率高达100%。【结论】深度学习网络(GoogLeNet、ResNet)能够实现基于叶片的油茶品种识别,可为基于其他作物的品种识别提供参考。【Objective】Deep learning methods are used to carry out research on Camellia oleifera based variety recognition on leaves,this study developed C.oleifera strain image recognition technology to provide scientific basis for C.oleifera variety identification.【Method】Eleven leaves of C.oleifera varieties grown under natural lighting conditions and free from pests and diseases were collected for a study.Images of the front and back of the leaves with a white cardboard background were captured using a smartphone.Invalid images were removed by usability screening,and a dataset of camellia leaf varieties with 2791 images was constructed.Deep learning networks(GoogLeNet and ResNet)were used to identify and study the leaf images of 11 C.oleifera varieties.【Result】Both GoogLeNet and ResNet networks can meet the requirements of C.oleifera variety recognition based on leaves,with overall F_(1) scores of 94􀆰0%and 80􀆰7%.Among them,the GoogLeNet network was more effective in recognition,with average accuracy,recall,Macro F_(1) and Micro F_(1) value of 94.1%,94.0%,94.0%and 96.9%,respectively,and its recognition recall for two varieties,NO.1 and 8,reached 100%.【Conclution】Deep learning networks(GoogLeNet and ResNet)can achieve C.oleifera variety recognition based on leaves,which can provide a reference for rapid leaf⁃based C.oleifera variety recognition.

关 键 词：深度学习 油茶叶片 品种识别 GoogLeNet ResNet 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]