中红外光谱结合CA-SDP-DenseNet的木材种类识别研究

doi:10.3964/j.issn.1000-0593(2023)03-0814-09

Abstract
References
Related Citation (15)

Download: PDF (16391 KB)
Export: BibTeX | EndNote (RIS)

Abstract Spectral analysis technology has a certain potential in wood species identification, and mid-infrared spectroscopy technology is also widely used in qualitative and quantitative analysis. This research focuses on the identification of wood species by mid-infrared spectroscopy. Based on a deep convolutional neural network, an algorithm that combines cluster analysis (CA), symmetrical lattice image analysis (SDP) and deep learning (DenseNet) is proposed to achieve a high recognition rate with few parameters. With the advantages of DenseNet, the accuracy of wood recognition in mid-infrared spectroscopy is improved. First, 250 sets of mid-infrared spectroscopy data, including guaiacum sanctum, dalbergiabariensis, pterocarpuserinaceus, pterocarpusmacarocarpus, and spiraea, are collected. Through eliminating outliers based on Euclidean distance, the feasibility analysis of the remaining 240 groups as data to be analyzed and classified. The optimal parameters of SDP conversion are determined through the SDP conversion analysis of the original spectral data. The characteristics of original spectral data are filtered out through CA. According to CA, different thresholds determine the characteristics of the three groups of dimensions and related discussions are carried out. The optimal dimensional feature is initially determined by comparing the three sets of feature data, including the intra-class similarity and the inter-class difference between the images after SDP conversion. The determined optimal dimensional feature data is input into the SDP-DenseNet model to obtain model recognition accuracy. Finally, the comparative analysis verifies the validity of the model. On the one hand, the original data and the feature data of the other two sets of contrast dimensions are input into the SDP-DenseNet model to compare recognition accuracy. On the other hand, the optimal dimensional feature data is input into the random forest for recognition to compare the accuracy of traditional machine recognition and SDP-DenseNet algorithm recognition. According to the results, the accuracy of the SDP-DenseNet model filtered by the CA feature is generally higher than that of the SDP-DenseNet model directly input to the original data. The optimal dimension of CA feature selection is 255 dimensions, with the highest recognition rate of 88.67%. In the control group, the recognition rate of 107 dimensions is 77.78%, and the recognition rate of 322 dimensions is 68.89%. In contrast, the SDP-DenseNet model recognition rate of the original data is only 57.78%. The recognition rate of the random forest model corresponding to the optimal dimensionality data screened by clustering features is relatively low, only 66.67%. Therefore, the CA-SDP-DenseNet model proposed in this study can effectively improve the accuracy of mid-infrared spectroscopy in identifying wood species.

Key words：Mid-infrared spectroscopy; Identification of wood species; Cluster analysis; Symmetrical lattice image analysis; Deep learning

Received: 2022-01-13 Accepted: 2022-06-01

ZTFLH:

O657.3

Corresponding Authors: FENG Guo-hong E-mail: fgh_1980@126.com

Cite this article:

LIU Si-qi,FENG Guo-hong,TANG Jie, et al. Research on Identification of Wood Species by Mid-Infrared Spectroscopy Based on CA-SDP-DenseNet[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 814-822.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2023)03-0814-09 OR https://www.gpxygpfx.com/EN/Y2023/V43/I03/814

[1] MENG Qian，LUO Xin-jian，LIU Ying，et al（孟倩，罗信坚，刘颖，等）. World Forestry Research（世界林业研究），2017，30（2）：73.
[2] FU Feng，WANG Xin-jie，WANG Jin，et al（傅锋，王新杰，汪锦，等）. Remote Sensing for Land & Resources （国土资源遥感），2019，31（2）：118.
[3] CHEN Ming-jian，CHEN Zhi-bo，YANG Meng，et al（陈明健，陈志泊，杨猛，等）. Journal of Beijing Forestry University（北京林业大学学报），2017，39（2）：108.
[4] JIANG Yan，WU Pei-yi（江艳, 武培怡）. Progress in Chemistry（化学进展）, 2009，21（4）：705.
[5] FENG Yu，GU Xiao-hong，TANG Jian，et al（冯宇，顾小红，汤坚，等）. Journal of Food Science and Biotechnology（食品与生物技术学报），2007，（2）：7.
[6] WANG Xun-shun，SUN Yi-dan，HUANG Min-gao，et al（王学顺，孙一丹，黄敏高，等）. Journal of Northeast Forestry University（东北林业大学学报），2015，43（12）：82.
[7] LIANG Long，FANG Gui-gan，CUI Hong-hui，et al（梁龙，房桂干，崔宏辉，等）. Chemistry and Industry of Forest Products（林产化学与工业），2016，36（1）：55.
[8] DOU Gang，CHEN Guang-sheng，ZHAO Peng（窦刚，陈广胜，赵鹏）. Journal of Tianjin University（天津大学学报），2015，48（2）：147.
[9] LIU Jia-zheng，WANG Xue-feng，WANG Tian（刘嘉政，王雪峰，王甜）. Journal of Nanjing Forestry University（南京林业大学学报），2020，44（1）：138.
[10] LI Bin, JING Qi-chao（李滨，敬启超）. Forest Engineering（森林工程），2021，37（5）：75.
[11] YE Qiao-lin，XU Deng-ping，ZHANG Dong（业巧林，许等平，张冬）. Journal of Forestry Engineering（林业工程学报），2019，4（2）：119.
[12] Yang Haowen, Hsu Haochun, Yang Chihkai, et al. Computers and Electronics in Agriculture, 2019, 162: 739.
[13] Liu Jiazheng, Wang Xuefeng, Wang Tian. Computers and Electronics in Agriculture, 2019, 166: 105012.
[14] Sun Yongjian, Li Shaohui. Measurement, 2022, 199: 110702.
[15] ZHAO Li-hua，XU Li，LIU Yan，et al（赵莉华，徐立，刘艳，等）. Transactions of China Electrotechnical Society（电工技术学报），2021，36（17）：3614.
[16] Edna C T, Li Y, Sam N K, et al. Computers and Electronics in Agriculture, 2019, 161: 272.
[17] BAI Yan，BAO Hong-juan，WANG Dong，et al（白雁, 鲍红娟, 王东，等）. Journal of Chinese Medicinal Materials（中药材）, 2006（7）：663.
[18] HU Shan-ke，QIN Yu-hua，DUAN Ru-min，et al（胡善科，秦玉华，段如敏，等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析），2020，40（12）：3772.