Rapid Nondestructive Identification of Wood Lacquer Using Raman Spectroscopy Based on Characteristic-Band-Fisher-<i>K</i> Nearest Neighbor

Ya He; Jifen Wang

doi:10.3788/LOP57.013001

Laser & Optoelectronics Progress, Volume. 57, Issue 1, 013001(2020)

Rapid Nondestructive Identification of Wood Lacquer Using Raman Spectroscopy Based on Characteristic-Band-Fisher-K Nearest Neighbor

Ya He and Jifen Wang^*

Author Affiliations

Institute of Forensic Science and Technology, People's Public Security University of China, Beijing, 100038, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(7)

Fig. 1. Preprocessing results of Raman spectra of CY003 samples. (a) BL; (b) nine-point smoothing; (c) first derivative; (d) second derivative

Download full size

Fig. 2. Classification of three brands of woodlacquer samples obtained by characteristic-band ratio method

Download full size

Fig. 3. Discriminant distribution of three brands of woodlacquer samples obtained by functions 1 and 2

Download full size

Table 1. Basic information of six samples of wood lacquer

View table

Table 1. Basic information of six samples of wood lacquer

Number	Brand	Category	Manufacturer
CY003	CYSO	Water-basedmultifunctional paint	CYSO
CY008	CYSO	Water-basedmultifunctional paint	CYSO
HC004	HUACAI	Water-basedpaint	Chaomeiyaqi
HC013	HUACAI	Water-basedpaint	Chaomeiyaqi
QS001	TRYKON	Waterbornefurniture finish	Changfeng
QS010	TRYKON	Waterbornefurniture finish	Changfeng

Table 2. Discriminant results of different preprocessing methods
View table
Table 2. Discriminant results of different preprocessing methods
Index Original spectrum BL+Smoothing BL+Smoothing+1^st derivative BL+Smoothing+2^nd derivative
Overall accuracy /% 68.0 79.8 96.0 100
Number of errors 55 35 7 0
Cross validation rate /% 65.1 69.4 94.1 100

Table 3. Summary of Fisher-function discriminant
View table
Table 3. Summary of Fisher-function discriminant
Function Eigen value Cumulative variance Regular correlation Test function Wilks’ Lambda Significance
1 113.871 90.1 0.996 1 and 2 0.001 0
2 12.455 100 0.962 1 0.074 0.041

Table 4. Classification results of samples for two models
View table
Table 4. Classification results of samples for two models
Spectral type Overall accuracy /% Cross validationrate /%
Fisher KNN
BL+Smoothing+1^st derivative 96 79.2 100
BL+Smoothing+2^ndderivative 100 88.5 100

Tools

Get Citation

Copy Citation Text

Ya He, Jifen Wang. Rapid Nondestructive Identification of Wood Lacquer Using Raman Spectroscopy Based on Characteristic-Band-Fisher-K Nearest Neighbor[J]. Laser & Optoelectronics Progress, 2020, 57(1): 013001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites