摘要
为构建高识别准确率且适用于手机端应用的玉米籽粒品种识别模型,提出利用手机获取玉米粒籽双面(胚面和非胚面)图像,基于轻量级卷积神经网络MobileNetV2和迁移学习构建玉米籽粒图像品种识别模型,针对已有研究中多以玉米籽粒单面识别为主,分析对比玉米籽粒单、双面特征建模及识别性能。结果表明,玉米籽粒双面特征建模的双面识别准确率达99.83%,优于单面特征建模识别以及胚面和非胚面图像分别建模后双面识别,适用于手机端玉米籽粒品种识别应用需求。
In order to construct a maize kernel variety recognition model with high recognition accuracy and suitable for mobile phone application, a mobile phone is used to obtain maize kernel double-sided(embryonic and non-embryonic) images. Based on the lightweight convolutional neural network MobileNetV2 and transfer learning, a maize kernel image variety recognition model is constructed. In view of the existing research methods are mainly for single-sided recognition of maize kernel variety, the performance of single-sided and double-sided characteristics modeling and recognition is compared. The results show that the double-sided recognition accuracy of maize kernel double-sided characteristics modeling is 99.83%, which is better than single-sided characteristics modeling and recognition. It is also better than double-sided recognition after modeling embryonic side and non-embryonic side images respectively. It is suitable for the application demand of maize kernel variety recognition on mobile phone.
作者
冯晓
张辉
周蕊
乔璐
魏东
李丹丹
张玉尧
郑国清
Feng Xiao;Zhang Hui;Zhou Rui;Qiao Lu;Wei Dong;Li Dandan;Zhang Yuyao;Zheng Guoqing(Institute of Agricultural Economics and Information,Henan Academy of Agricultural Sciences,Zhengzhou 450002,China;Henan Engineering and Technology Research Center for Intelligent Agriculture,Zhengzhou 450002,China;Institute of Agricultural Science and Technology Information,Chongqing Academy of Agricultural Sciences,Chongqing 401329,China)
出处
《系统仿真学报》
CAS
CSCD
北大核心
2021年第12期2983-2991,共9页
Journal of System Simulation
基金
河南省科技攻关计划(212102110220)
河南省农业科学院创新团队(2021TD11)。
