基于波峰波谷特征提取技术的檀香紫檀光谱识别

doi:10.3964/j.issn.1000-0593(2024)12-3463-10

Abstract
References
Related Citation (15)

Download: PDF (16612 KB)
Export: BibTeX | EndNote (RIS)

Abstract With the rapid growth of the economic level, people's demand for mahogany products is increasing day by day. As precious mahogany, criminals replace sandalwood and counterfeit it because of its spiritual pursuit and high price. To maintain the order of the timber market and the interests of consumers and realize the rapid non-destructive detection and identification of sandalwood, it is necessary to establish a fast and reliable intelligent identification method of sandalwood. This paper used near-infrared spectroscopy to extract the spectral information of Pterocarpus santalinus and its similar blood sandalwood. The qualitative analysis method, partial least squares discriminant analysis ( PLS-DA ), and error back propagation artificial neural network ( BPNN ) were used to establish the calibration model of spectral information. Then, Pterocarpus santalinus and its similar wood blood sandalwood were identified. By analyzing and comparing the advantages and disadvantages and recognition accuracy of these three models for these two kinds of wood recognition, the feasibility of this method in the recognition of sandalwood and sandalwood is verified. The experimental results show that the three discriminant models can quickly identify the wood spectral images, and can quickly and non-destructively classify and identify sandalwood and sandalwood. In the case of selecting different image processing methods, the results of the three discriminant models are different, and the recognition results are also different. Further analysis reveals that when the spectral data are modeled using the BPNN model, the peak and trough eigenvalues of the original spectral data within the wavelength range of 866~2 533 nm are utilized as input following preprocessing. It is observed that when the number of input layer nodes is Setto 24 eigenvalues and the hidden layer consists of 13 neurons, the model achieves the smallest root mean square error, with an accuracy rate of 96.43%. Additionally, shortening the spectral range does not result in an improvement in the model's recognition rate. The BPNN model demonstrates the highest recognition rate across the full band range among the three models. The experimental results indicate that the combination of artificial neural network modeling and near-infrared spectral feature extraction technology yields a high recognition accuracy in identifying sandalwood wood, surpassing trevious methodologies. This study contributes to mitigating the subjectivity inherent in manual recognition processes. The utilization of computers can expedite the recognition process, while the enhanced accuracy aids in maintaining order within the wood market and safeguarding consumer rights. Simultaneously, it offers insights into realizing intelligent visual recognition of sandalwood and furnishes technical support for the sustainable development of the mahogany industry.

Key words：Near-Infrared spectroscopy; Wood identification; PLS-DA; BPNN: Qualitative analysis

Received: 2023-09-18 Accepted: 2024-04-21

ZTFLH:

S781.23

Corresponding Authors: SUN Jian-ping, HE Tuo E-mail: jpsun@gxu.edu.cn；tuohe@caf.ac.cn

Cite this article:

ZHUANG Peng-yan,NIU Jia-shun,CHENG Jun, et al. Spectral Recognition of Sandalwood Based on Peak and Valley Feature Extraction Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(12): 3463-3472.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)12-3463-10 OR https://www.gpxygpfx.com/EN/Y2024/V44/I12/3463

[1] ZHANG Jing-han, WANG Ming-hao, LIN Qiao, et al(张静涵, 王明豪, 林巧，等). Journal of Northwest Forestry University(西北林学院学报), 2022, 37(5): 223.
[2] Xue X, Chen Z, Wu H, et al. Forests, 2023，14(6): 1259.
[3] LIU Shou-jia, WANG Jia-jun, LU Yang, et al(刘守佳, 汪嘉君, 陆杨, 等). World Forestry Research(世界林业研究), 2023, 36(5): 70.
[4] ZHU Guang-qian, SHEN Wei(朱光前, 申伟). China Wood-Based Panels(中国人造板), 2022, 29(7): 36.
[5] ZHOU Chun-chang, DU Ya-tian, PENG Feng-zhen(周春长, 杜亚填, 彭凤珍). Journal of Anhui Agricultural Sciences(安徽农业科学), 2020, 48(16): 13.
[6] Ravindran P, Thompson B J, Soares R K, et al. Frontiers in Plant Science, 2020, 11：1015.
[7] FU Li-yan, FENG Guo-hong, LIU Xu-ming(付立岩, 冯国红, 刘旭铭). Forest Engineering(森林工程), 2023, 39(4): 101.
[8] Sun X, Li H, Yi Y, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 250：119346.
[9] Barea-Sepúlveda M, Calle J L P, Ferreiro-González M, et al. Foods，2023，12(18): 3362.
[10] Zhao P, Xing J, Hu C, et al. Agriculture，2022; 12(3): 411.
[11] Squeo G, Amigo J M. Foods, 2023，12(16): 3041.
[12] Tsuchikawa S, Inagaki T, Ma T. Current Forestry Reports, 2023, 9：401.
[13] LIU Tao, LI Bo, XIA Rui, et al(刘涛，李博，夏蕊，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2024, 44(3): 821.
[14] Zhang L, Wang F, Sun T，et al. Neural Comput. & Applic., 2018, 29: 413.
[15] WANG Yu, LI Yan-jie, CHEN Yi-cun, et al(王珏, 李彦杰, 陈益存, 等). Journal of Nanjing Forestry University(Natural Sciences Edition)[南京林业大学学报(自然科学版)], 2023, 47(3): 237.
[16] Xue X，Chen Z，Wu H, et al. Scientific Reports, 2022, 12：11507.
[17] Specht D F. IEEE Transactions on Neural Networks, 1991, 2(6): 568.
[18] Liao L, Zhao Y, Wei S, et al. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(11): 4600.
[19] Cozzolino D, Williams P J, Hoffman L C. Microchemical Journal, 2023, 193: 109129.
[20] Michael Greenacre, Patrick J F Groenen, Trevor Hastie, et al. Nature Reviews Methods Primers, 2022, 2：100.
[21] Stephan Weiss, Ian K Proudler, Fraser K Coutts. IEEE Transactions on Signal Processing, 2021, 69: 722.
[22] Zhang L, Wang F, Sun T, et al. Neural Computing and Applications, 2018, 29: 413.
[23] XU Wang-li, SHI Ting-chun, CHEN Hong-yu, et al(徐旺莉, 史廷春, 陈鸿宇, 等). Computer Integrated Manufacturing Systems(计算机集成制造系统), 2023, 29(8): 2733.