摘要
针对白菜种子,以北京小杂55号为研究对象,使用机器视觉技术获取种子10个颜色特征和6个形状特征,再通过单粒种子萌发试验确定种子活力,并使用曼-惠特尼U检验分析种子活力与图像特征的相关性。将显著相关图像特征与种子发芽实验结果组成数据集,结合偏最小二乘判别分析法建立分类模型,并通过MatLab软件进行了仿真分析。结果表明:白菜种子的R分量均值、R分量标准差、G分量均值、G分量标准差、B分量标准差、H分量均值、H分量标准差、S分量均值、S分量标准差和圆形度P与白菜种子活力显著相关。结合这些特征,使用偏最小二乘判别分析法建立分类模型,进行种子精选,可以将该批白菜种子发芽率由原始50.67%提升至69.43%。由此表明,可通过机器视觉技术对白菜种子进行精选,从而提高种子的活力。
Taking Beijing Xiaoza No. 55 as the research object, 10 color features and 6 shape features were obtained by machine vision technology. The seed vigor was determined by single seed germination test, and the correlation between seed vigor and image characteristics was analyzed by Mann Whitney U test. The data set was composed of significant correlation image features and seed germination experiment results, and the classification model was established by combining partial least squares discriminant analysis, and the simulation analysis was carried out by MATLAB software. The results showed that: R component mean value, R component standard deviation, G component mean value, G component standard deviation, B component standard deviation, H component mean value, H component standard deviation, s component mean value, s component standard deviation and roundness P were significantly correlated with Chinese cabbage seed vigor The results showed that the seed germination rate increased from 50.67% to 69.43%. The results showed that the seed vigor could be improved by machine vision technology.
作者
张晗
王成
董宏图
吴旭东
闫宁
宋鹏
罗斌
Zhang Han;Wang Cheng;Dong Hongtu;Wu Xudong;Yan Ning;Song Peng;Luo Bin(Beijing Agricultural Information Technology Research Center,Beijing 100094,China;College of Plant Science&Technology,Huazhong Agricultural University,Wuhan 430070,China;Beijing Research Center for Intelligent Agricultural Equipment,Beijing 100094,China;School of Mechanical Engineering,North University of China,Taiyuan 030051,China)
出处
《农机化研究》
北大核心
2021年第12期31-36,共6页
Journal of Agricultural Mechanization Research
基金
国家重点研发计划项目(2017YFD0701205)
广东省科技创新战略专项(201909020001)。
关键词
白菜种子
精选
种子活力
机器视觉
cabbage seed
selection
seeds vigor
machine vision
作者简介
张晗(1991-),男,安徽淮北人,硕士,(E-mail)zhangha@n ercita.org.cn;通讯作者:罗斌(1981-),男,山东淄博人,高级工程师,博士,(Email)luob@nercita.org.cn。
