Research on the Retention Time of Sweat Latent Fingerprints on Glass by Hyperspectral Combination with Multiple Models

Pengyu Tang; Zhen Wang

doi:10.3788/LOP232622

Laser & Optoelectronics Progress, Volume. 61, Issue 18, 1812005(2024)

Research on the Retention Time of Sweat Latent Fingerprints on Glass by Hyperspectral Combination with Multiple Models

Pengyu Tang¹ and Zhen Wang^1,2、*

Author Affiliations

¹College of Forensic Sciences, Criminal Investigation Police University of China, Shenyang 110035, Liaoning, China

²Key Laboratory of Impression Evidence Examination and Identification Technology, Ministry of Public Security,Criminal Investigation Police University of China, Shenyang 110854, Liaoning, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(8)

Fig. 1. Flow chart of experimental

Download full size

Fig. 2. Fingerprint sample

Download full size

Fig. 3. ROI selected by ENVI

Download full size

Fig. 4. Original spectrogram

Download full size

Fig. 5. Spectrum after SG smoothing and SNV preprocessing. (a) SG; (b) SNV

Download full size

Fig. 6. Error distribution map of different models at 20 bands. (a)(d) SVM; (b)(e) GA-BPNN; (c)(f) PLSR

Download full size

Table 1. Performance evaluation indicators for different model prediction effects (full bands)
View table
Table 1. Performance evaluation indicators for different model prediction effects (full bands)
Prediction model（full bands） Model parameter
I_RMSEC /d I_RMSEP /d R² I_RPD I_P/C
SVM 2.427 3.437 0.607 1.498 1.416
GA-BPNN 2.331 4.043 0.490 1.274 1.734
PLSR 3.558 4.335 0.370 1.188 1.218

Table 2. Performance evaluation indicators for different model prediction effects (20 bands)
View table
Table 2. Performance evaluation indicators for different model prediction effects (20 bands)
Prediction model
（SPA，20 bands）
Model parameter
I_RMSEC/d I_RMSEP/d R² I_RPD I_P/C
SVM 2.925 3.247 0.627 1.583 1.110
GA-BPNN 3.034 3.035 0.659 1.490 1.000
PLSR 3.169 3.060 0.606 1.483 0.966

Tools

Get Citation

Copy Citation Text

Pengyu Tang, Zhen Wang. Research on the Retention Time of Sweat Latent Fingerprints on Glass by Hyperspectral Combination with Multiple Models[J]. Laser & Optoelectronics Progress, 2024, 61(18): 1812005

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Instrumentation, Measurement and Metrology

Received: Dec. 5, 2023

Accepted: Feb. 18, 2024

Published Online: Sep. 14, 2024

The Author Email: Zhen Wang (wangyuchena9@163.com)

DOI:10.3788/LOP232622

CSTR:32186.14.LOP232622

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Performance evaluation indicators for different model prediction effects (full bands)

Table 1. Performance evaluation indicators for different model prediction effects (full bands)

Table 2. Performance evaluation indicators for different model prediction effects (20 bands)

Table 2. Performance evaluation indicators for different model prediction effects (20 bands)