Infrared Spectral Pattern Recognition of Watercolor Pen Ink Based on Artificial Neural Network

Xiaobin Wang; Xiao Ma; Xincheng Wang

doi:10.3788/LOP57.153005

Laser & Optoelectronics Progress, Volume. 57, Issue 15, 153005(2020)

Infrared Spectral Pattern Recognition of Watercolor Pen Ink Based on Artificial Neural Network

Xiaobin Wang¹, Xiao Ma¹, and Xincheng Wang^2、*

Author Affiliations

¹School of Forensic Science, People's Public Security University of China, Beijing 100038, China

²School of Chemical Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(6)

Fig. 1. Compression results of infrared spectrum

Download full size

Fig. 2. Structure of ANN

Download full size

Fig. 3. Classification results and accuracy

Download full size

Fig. 4. ROC curves. (a) Training set; (b) validation set; (c) test set; (d) total ROC curve of overall

Download full size

Table 1. X_RMSE at different compression times
View table
Table 1. X_RMSE at different compression times
Compression time X_RMSE
1 2.0×10^-3
2 2.4×10^-3
3 1.9×10^-1
4 2.1×10^-1
5 4.0×10^-1

Table 2. Characteristic wave numbers of different kinds of samplesunit: cm^-1
View table
Table 2. Characteristic wave numbers of different kinds of samplesunit: cm^-1
Sample category Characteristic wave numbers
1 2 3 4 5 6 7 8 9 10
1 3340 3010 1620 3960 3550 991 2790 1260 2040 1140
2 3430 3140 1080 1170 2260 903 2510 3570 2820 976
3 3360 2300 3030 1330 972 3550 995 918 3170 1430

Tools

Get Citation

Copy Citation Text

Xiaobin Wang, Xiao Ma, Xincheng Wang. Infrared Spectral Pattern Recognition of Watercolor Pen Ink Based on Artificial Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(15): 153005

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites