NIR Spectroscopy Identification of Persimmon Varieties Based on PCA-SVM - Computer and Computing Technologies in Agriculture IV - Part II Access content directly
Conference Papers Year : 2011

NIR Spectroscopy Identification of Persimmon Varieties Based on PCA-SVM

Abstract

In order to achieve non-destructive measurement of varieties in persimmon, a fast discrimination method based on Vis$\diagup$NIRS spectroscopy was put forward. A Field Spec 3 spectroradiometer was used for collecting 22 sample spectra data of the three kinds of persimmon separately. Then principal component analysis (PCA) was used to process the spectral data after pretreatment. The near infrared fingerprint of persimmon was acquired by principal component analysis(PCA), Cand support vector machine (SVM) methods were used to further identify the persimmon separately. The result of PCA indicated that the score map made by the scores of PCI, CPC2 and PC3 was used, and 8 principal components (PCs) were selected as the input of support vector machine (SVM) based on the reliabilities of PCs of 99. 888%.51 persimmon samples were used for calibration and the remaining 15 persimmon samples were used for validation. A one-against- all multi-class SVM model was built, and the result showed that SVM possessing with the RBF kernel function has the best identification capabilities with the accuracy of 100%. This research indicated that the mixed algorithm method of principal component analysis( PCA) and support vector Machine(SVM) has a good identification effect, and can work as a new method for quick, efficient and correct identification of persimmon separately.
Fichier principal
Vignette du fichier
978-3-642-18336-2_14_Chapter.pdf (177.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01562735 , version 1 (17-07-2017)

Licence

Attribution

Identifiers

Cite

Shujuan Zhang, Dengfei Jie, Haihong Zhang. NIR Spectroscopy Identification of Persimmon Varieties Based on PCA-SVM. 4th Conference on Computer and Computing Technologies in Agriculture (CCTA), Oct 2010, Nanchang, China. pp.118-123, ⟨10.1007/978-3-642-18336-2_14⟩. ⟨hal-01562735⟩
89 View
158 Download

Altmetric

Share

Gmail Facebook X LinkedIn More