Preprocessing and feature wavelength selection of near-infrared spectrum for plastic material identification

Senlin Zhao; Chaoyi Shi; Zhongma Wang; Xianhe Gao; Xueyou Hu; Sheng Zhang; Zehua Zhou

doi:10.1117/12.3034194

5 July 2024 Preprocessing and feature wavelength selection of near-infrared spectrum for plastic material identification

Senlin Zhao, Chaoyi Shi, Zhongma Wang, Xianhe Gao, Xueyou Hu, Sheng Zhang, Zehua Zhou

Author Affiliations +

Proceedings Volume 13183, International Conference on Optoelectronic Information and Functional Materials (OIFM 2024); 131832A (2024) https://doi.org/10.1117/12.3034194
Event: The 3rd International Conference on Optoelectronic Information and Functional Materials (OIFM 2024), 2024, Wuhan, China

Abstract

The near-infrared spectroscopy technology has been widely used in the identification of plastic materials. In this paper, the analysis of spectra preprocessing methods and wavelength selection methods is carried out for the accurate identification of seven plastic materials, including PET, PE, HDPE, ABS, PP, PS, and PVC. Three spectra preprocessing methods, including Multivariate Scatter Correction, Standard Normal Variate, Savitzky-Golay filtering coupled with Standard Normal Variate and three feature wavelength selection methods, including Successive Projections Algorithm, Genetic Algorithm and Competitive Adaptive Reweighted Sampling were compared and analyzed. The experimental results showed that the identification model built based on Support Vector Machine using the Standard Normal Variate after Savitzky-Golay filtering spectra preprocessing method and the Competitive Adapative Reweighted Sampling wavelength selection method had the highest accuracy, with an accuracy of 99.81% in recognizing the seven plastic materials.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Senlin Zhao, Chaoyi Shi, Zhongma Wang, Xianhe Gao, Xueyou Hu, Sheng Zhang, and Zehua Zhou "Preprocessing and feature wavelength selection of near-infrared spectrum for plastic material identification", Proc. SPIE 13183, International Conference on Optoelectronic Information and Functional Materials (OIFM 2024), 131832A (5 July 2024); https://doi.org/10.1117/12.3034194

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available