文献类型： 外文期刊

作者： Liu, W. ¹ ; Liu, Ch. ² ; Ma, F. ² ; Lu, X. ³ ; Yang, J. ³ ; Zheng, L. ² ;

作者机构： 1.Hefei Univ, Intelligent Control & Compute Vis Lab, Hefei, Peoples R China

2.Hefei Univ Technol, Sch Biotechnol & Food Engn, Hefei, Peoples R China

3.Anhui Acad Agr Sci, Rice Res Inst, Hefei 230031, Peoples R China

4.Hefei Univ Technol, Sch Med Engn, Hefei, Peoples R China

关键词： multispectral imaging;rice varieties;nondestructive determination;chemometric

期刊名称：JOURNAL OF APPLIED SPECTROSCOPY （ 影响因子：0.741； 五年影响因子：0.718 ）

ISSN：

年卷期：

页码：

收录情况： SCI

摘要： Variety identification plays an important role in ensuring the quality and quantity of yield in rice production. The feasibility of a rapid and nondestructive determination of varieties of rice seeds was examined by using a multispectral imaging system combined with chemometric data analysis. Deethods of the partial least squares discriminant analysis (PLSDA), principal component analysis-back propagation neural network (PCA-BPNN), and least squares-support vector machines (LS-SVM) were applied to classify varieties of rice seeds. The results demonstrate that clear differences among varieties of rice seeds could be easily visualized using the multispectral imaging technique and an excellent classification could be achieved combining data of the spectral and morphological features. The classification accuracy was up to 94% in a validation set with the LS-SVM model, which was better than the PLSDA (62%) and PCA-BPNN (84%) models.