基于深度学习的大豆豆荚类别识别研究  

Classification of soybean pods using deep learning

作　　者：闫壮壮 闫学慧 石嘉 孙凯 虞江林 张战国[1] 胡振邦 蒋鸿蔚 辛大伟[3] 李杨[1] 齐照明[3] 刘春燕[3] 武小霞[3] 陈庆山[3] 朱荣胜[1] YAN Zhuang-Zhuang;YAN Xue-Hui;SHI Jia;SUN Kai;YU Jiang-Lin;ZHANG Zhan-Guo;HU Zhen-Bang;JIANG Hong-Wei;XIN Da-Wei;LI Yang;QI Zhao-Ming;LIU Chun-Yan;WU Xiao-Xia;CHEN Qing-Shan;ZHU Rong-Sheng(College of Arts and Sciences,Northeast Agricultural University,Harbin 150030,Heilongjiang,China;Engineering College Northeast Agricultural University,Harbin 150030,Heilongjiang,China;Soybean Research Institute,Northeast Agricultural University,Harbin 150030,Heilongjiang,China)

机构地区：[1]东北农业大学文理学院,黑龙江哈尔滨150030 [2]东北农业大学工程学院,黑龙江哈尔滨150030 [3]东北农业大学大豆研究所,黑龙江哈尔滨150030

出　　处：《作物学报》2020年第11期1771-1779,共9页Acta Agronomica Sinica

基　　金：国家自然科学基金项目(31471516);国家自然科学基金青年项目(31400074)资助。

摘　　要：作物表型调查是作物品种选育过程中的一项关键工作。传统表型调查主要依靠人力,使得表型调查的结果难以达到自动化、高精度、高可靠性的要求。在大豆的表型调查中,对豆荚类别的正确识别是豆荚个数、长度和宽度等表型准确提取的关键和前提。本文针对成熟期大豆豆荚的图片,通过利用深度学习迁移5种不同的网络模型[AlexNet、VggNet(Vgg16,Vgg19)、GoogleNet、ResNet-50],对一粒荚、二粒荚、三粒荚、四粒荚进行识别。为提高训练速度和准确率,本试验微调模型,选择不同的优化器(SGD、Adam)对网络模型进行优化。结果表明,在针对豆荚辨识问题中,Adam的性能优于SGD,而Vgg16网络模型搭配Adam优化器,豆荚类别的测试准确率达到了98.41%,在所选的网络模型中体现了最佳的性能。在十折交叉验证试验中也体现了Vgg16网络模型具有良好的稳定性。因此本研究认为Vgg16网络模型可以应用到实际的豆荚识别中,为进一步实现豆荚表型自动提取提供一条重要的解决途径。Crop phenotype investigation is a key task in the selection and breeding of crop varieties.The traditional phenotypic survey mainly relies on human labors,which makes the results of the phenotypic survey difficult to meet the requirements of automation,high precision and high reliability.In the investigation of soybean phenotypes,the correct identification of pod types is the key and premise for the accurate extraction of phenotypes such as the number,length and width of pods.This study focused on the pictures of mature soybean pods by using deep learning to migrate five different network models[AlexNet,VggNet(Vgg16,Vgg19),GoogleNet,ResNet-50],to identify one-pod,two-pod,three-pod,and four-pod.In order to improve training speed and accuracy,this experiment fine-tuning the model and selected different optimizers(SGD,Adam)to optimize the network model.Adam’s performance was better than SGD in the problem of pod identification.With the Vgg16 network model and the Adam optimizer,the test accuracy of the pod category reached 98.41%,which reflected the best performance in the selected network model.In the 10-fold cross-validation test,the Vgg16 network model had good stability.Therefore,this study indicates that the Vgg16 network model can be applied to the actual identification of pods,and provide an important solution for further automatic extraction of pod phenotypes.

关 键 词：大豆育种 豆荚辨别 深度学习 迁移学习 

分 类 号：S565.1[农业科学—作物学]