您好，欢迎访问北京市农林科学院 机构知识库！
北京市农林科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

MELON SEED VARIETY IDENTIFICATION BASED ON HYPERSPECTRAL TECHNOLOGY COMBINED WITH DISCRIMINANT ANALYSIS

文献类型： 外文期刊

作者： Li, Cuiling 1 ; Fan, Pengfei 1 ; Jiang, Kai 1 ; Wang, Xiu 1 ; Feng, Qingchun 1 ; Zhang, Chunfeng 1 ;

作者机构： 1.Beijing Res Ctr Intelligent Equipment Agr, Beijing 100097, Peoples R China

2.Natl Res Ctr Intelligent Equipment Agr, Beijing 100097, Peoples R China

关键词： Melon seed;Variety identification;Hyperspectral technology;Discriminant analysis

期刊名称：BANGLADESH JOURNAL OF BOTANY （ 影响因子：0.308； 五年影响因子：0.348 ）

ISSN： 0253-5416

年卷期： 2017 年 46 卷 3 期

页码：

收录情况： SCI

摘要： Impurity of melon seed variety causes harm to melon production. Hyperspectral technology combined with discriminant analysis was used to identify melon seed varieties at a non-destructive faster rate. A simple hyperspectral imaging system was developed to collect hyperspectral information of melon seeds. It included a light source unit, a hyperspectral image acquisition unit and a data processing unit. Hyperspectral images of melon seeds were calibrated and reflective spectral information was extracted from images. Multiple scattering correction (MSC), standard normal variable (SNV) transform, first derivative (FD) and Savitzky-Golay (SG) convolution smoothing were carried out. Effects of pre-treatment method were obvious, they mainly eliminated the impacts of surface scattering and optical path change, removed baseline drift and fine white noise. Carrying out SG, MSC, SNV and FD pre-treatments at the same time contributed greatly to discriminant effect. Principal component analysis (PCA) reduced the dimensions of spectral data and extract principal components. Fisher discriminant analysis and distance discriminant analysis generated good and similar discriminant effects, their discriminant accuracies were both higher than 90.0% for validation set. Research results showed that using hyperspectral technology combined with discriminant analysis could realize fast and non-destructive identification of melon seed variety

  • 相关文献

[1]Spectral identification of melon seeds variety based on k-nearest neighbor and Fisher discriminant analysis. Li, Cuiling,Jiang, Kai,Zhao, Xueguan,Fan, Pengfei,Wang, Xiu,Liu, Chuan,Li, Cuiling,Jiang, Kai,Zhao, Xueguan,Fan, Pengfei,Wang, Xiu,Liu, Chuan. 2017

[2]Tomato Leaf Liriomyza Sativae Blanchard Pest Detection Based on Hyperspectral Technology. Li Cui-ling,Jiang Kai,Ma Wei,Wang Xiu,Meng Zhi-jun,Zhao Xue-guan,Song Jian,Li Cui-ling,Jiang Kai,Ma Wei,Wang Xiu,Meng Zhi-jun,Zhao Xue-guan,Song Jian. 2018

[3]Validation of a set of informative simple sequence repeats markers for variety identification in Pak-choi (Brassica rapa L. ssp chinensis var. communis). Su, Tongbing,Zhao, Xiuyun,Sui, Guanglei,Yu, Shuancang,Zhang, Fenglan,Wang, Weihong,Zhang, Deshuang,Yu, Yangjun,Su, Tongbing,Zhao, Xiuyun,Sui, Guanglei,Yu, Shuancang,Zhang, Fenglan,Wang, Weihong,Zhang, Deshuang,Yu, Yangjun,Su, Tongbing,Zhao, Xiuyun,Sui, Guanglei,Yu, Shuancang,Zhang, Fenglan,Wang, Weihong,Zhang, Deshuang,Yu, Yangjun.

[4]Melon Seeds Variety Identification Based on Chlorophyll Fluorescence Spectrum and Reflectance Spectrum. Li Cui-ling,Jiang Kai,Feng Qing-chu,Wang Xin,Meng Zhi-jun,Wang Song-lin,Gao Yuan-yuan,Li Cui-ling,Jiang Kai,Feng Qing-chu,Wang Xin,Wang Song-lin,Gao Yuan-yuan. 2018

[5]Development of maizeSNP3072, a high-throughput compatible SNP array, for DNA fingerprinting identification of Chinese maize varieties. Tian, Hong-Li,Wang, Feng-Ge,Zhao, Jiu-Ran,Yi, Hong-Mei,Wang, Lu,Wang, Rui,Yang, Yang,Song, Wei.

[6]Research on Rapid and Non-Destructive Identification of Aging Wheat Based on ATR-Terahertz Spectroscopy Combined with PLS-DA. Wang Dong,Pan Li-gang,Li An,Jin Xin-xin,Ma Zhi-hong,Wang Ji-hua,Wang Dong,Pan Li-gang,Li An,Jin Xin-xin,Ma Zhi-hong,Wang Ji-hua,Liu Long-hai,Jiang, Justin. 2016

作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：北京市农林科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台