您好，欢迎访问江苏省农业科学院 机构知识库！
江苏省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Classifying maize kernels naturally infected by fungi using near-infrared hyperspectral imaging

文献类型： 外文期刊

作者： Chu, Xuan 1 ; Wang, Wei 2 ; Ni, Xinzhi 3 ; Li, Chunyang 4 ; Li, Yufeng 5 ;

作者机构： 1.Zhongkai Univ Agr & Engn, Coll Mech & Elect Engn, Guangzhou 510225, Peoples R China

2.China Agr Univ, Coll Engn, Beijing Key Lab Optimized Design Modern Agr Equip, Beijing 100083, Peoples R China

3.USDA ARS, Crop Genet & Breeding Res Unit, 2747 Davis Rd, Tifton, GA 31793 USA

4.Jiangsu Acad Agr Sci, Inst Food Sci & Technol, Nanjing 210014, Peoples R China

5.Chinese Acad Sci, Multidisciplinary Initiat Ctr, Inst High Energy Phys, Beijing 100049, Peoples R China

关键词： Near-infrared hyperspectral imaging; Naturally-occurring moldy corn kernels; Sampling strategies; Characteristic wavelengths; Support vector machine

期刊名称：INFRARED PHYSICS & TECHNOLOGY （ 影响因子：2.638； 五年影响因子：2.581 ）

ISSN： 1350-4495

年卷期： 2020 年 105 卷

页码：

收录情况： SCI

摘要： Maize is easily to be infected with fungi in field, and cause a considerable yield reduction and mycotoxin contamination. The objective was to assess, with the use of a near-infrared hyperspectral imaging (900-1700 nm), the difference between healthy and fungi infected maize kernels of three hybrids (i.e., `JingKe968', `JingNuo2000' and 'XianYu335', representing dent, waxy, and semi-flint endosperms, respectively). Two sampling strategies, i.e., pixel-wise (PW) and object-wise (OW), were examined using principal component analysis (PCA), successive projections algorithm (SPA) and support vector machine (SVM) modelling. In objectwise analysis, average spectra of whole individual kernel were analyzed. OW-PCA-SVM models developed using PC1 and PC3 through PC6 achieved accuracies of 99.00%, 97.96% and 97.87% for the three maize hybrids respectively. Eight (1168, 1344, 1414, 1428, 1520, 1269, 1691 and 1205 nm), eight (1161, 1336, 1450, 1638, 1266, 1698, 1189 and 1520 nm), and ten (1168, 1375, 1673, 1602, 1340, 1189, 1245, 1534, 1417 and 1262 nm) optimal wavelengths were respectively selected by SPA, and similar results (100%, 98.98% and 98.94%) were achieved. In pixel-wise analysis, classification accuracies at kernel level for the three varieties were 92.00%, 95.3% and 99.32% for PW-PCA-SVM models, and 100%, 100% and 100% for PW-SPA-SVM models, respectively. The results indicated that both object-wise and pixel-wise methods can be used for classification of fungi infected maize kernels. Pixel-wise classifications was superior in generating visualization maps for presenting the spatial information of infected kernels.

  • 相关文献
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：江苏省农业科学院

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