Acta Photonica Sinica, Volume. 49, Issue 3, 0330001(2020)
Multi-channel Raman Spectral Reconstruction Based on Gaussian Kernel Principal Component Analysis
Figures & Tables(11)
Fig. 1. Process of Raman spectral reconstruction algorithm based on KPCA
Fig. 2. The calibration Raman spectra of PMMA measured by different integration times and sample preparation methods
Fig. 3. The Raman spectrum of PMMA with random fluorescence background and noise and the Raman spectrum of PMMA without fluorescence background and noise
Fig. 4. Full reconstructed Raman spectra based on PINV, Wiener estimation, PCA and KPCA, respectively
Fig. 6. The Raman images reconstructed by PINV, Wiener estimation and KPCA, respectively
Fig. 7. Full Raman spectra based on pixel 1 and 2 reconstructed by PINV, Wiener estimation and KPCA, respectively
Table 1. The calibration Raman spectra of PMMA measured by different integration times and sample preparation methods
View tableView in ArticleTable 1. The calibration Raman spectra of PMMA measured by different integration times and sample preparation methods
Raman spectra r r r r r Integration times 10 s 3 s 10 s 10 s 10 s Preparation methods Original package Original package Valve bag Quartz tube Glass tube
Table 2. RMSEs offull reconstructed Raman spectra based on PINV, wiener estimation, PCA and KPCA
View tableView in ArticleTable 2. RMSEs offull reconstructed Raman spectra based on PINV, wiener estimation, PCA and KPCA
Method r r r r r Mean PINV 0.015 9 0.015 8 0.017 8 0.008 5 0.018 6 0.015 3 Wiener estimation 0.014 2 0.013 9 0.010 3 0.012 9 0.019 0 0.014 1 PCA 0.009 9 0.010 9 0.011 0 0.010 8 0.009 1 0.010 4 KPCA 0.005 0 0.004 2 0.006 9 0.006 7 0.015 7 0.007 7
Table 3. RMSEs of full reconstructed Raman spectra based on PINV, wiener estimation, PCA and KPCA under conditions of different noise
View tableView in ArticleTable 3. RMSEs of full reconstructed Raman spectra based on PINV, wiener estimation, PCA and KPCA under conditions of different noise
Method SNR PINV Wiener estimation PCA KPCA Test 1 13.072 6 0.015 3 0.014 1 0.010 4 0.007 7 Test 2 10.614 0 0.021 8 0.016 4 0.010 1 0.007 8 Test 3 9.637 3 0.029 7 0.018 6 0.011 0 0.007 6 Test 4 8.236 5 0.037 1 0.021 3 0.012 0 0.008 0 Test 5 7.770 5 0.042 7 0.024 7 0.014 7 0.009 7 Test 6 7.457 4 0.048 6 0.028 8 0.018 7 0.013 5 Test 7 6.702 9 0.055 5 0.033 4 0.026 4 0.016 3 Test 8 5.921 4 0.064 2 0.039 3 0.032 5 0.021 3 Test 9 5.506 3 0.075 1 0.046 9 0.041 5 0.029 7 Test 10 5.121 0 0.088 1 0.058 6 0.055 5 0.044 3
Table 4. RMSEs of full Raman spectra based on pixel 1 and pixel 2 reconstructed by PINV, Wiener estimation and KPCA, respectively
View tableView in ArticleTable 4. RMSEs of full Raman spectra based on pixel 1 and pixel 2 reconstructed by PINV, Wiener estimation and KPCA, respectively
Method PINV Wiener estimation KPCA Pixel 1 0.032 9 0.018 2 0.008 4 Pixel 2 0.042 8 0.022 5 0.011 1
Tools
Get Citation
Copy Citation Text
Xin WANG, Zhe-ming KANG, Long LIU, Xian-guang FAN. Multi-channel Raman Spectral Reconstruction Based on Gaussian Kernel Principal Component Analysis[J]. Acta Photonica Sinica, 2020, 49(3): 0330001
Paper Information
Category: Spectroscopy
Received: Nov. 4, 2019
Accepted: Dec. 27, 2019
Published Online: Apr. 24, 2020
The Author Email: FAN Xian-guang (fanxg@xmu.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20