支持向量机复合核函数的高光谱显微成像木材树种分类

doi:10.3964/j.issn.1000-0593(2019)12-3776-07

Abstract
References
Related Citation (15)

Download: PDF (2622 KB)
Export: BibTeX | EndNote (RIS)

Abstract In this paper, a stereomicroscopic hyper-spectral imaging scheme is used for wood species recognition. The SOC710VP hyper-spectral imaging system is used to pick up the wood images in visible and near-infrared spectral band (i. e., 372.53～1 038.57 nm). First, the ENVI software is used to pick up the mean spectra of wood sample’s Region of Interest (ROI). The Successive Projection Algorithm (SPA) and Competitive Adaptive Reweighted Sampling algorithm (CARS) are used for spectral dimension reduction. Second, a Support Vector Machine (SVM) is used to classify the wood samples in full spectral band and in feature wavelengths. Third, in the spatial dimension the 1^st principal component image (PC1) is used to compute the wood texture features based on Gray Level Co-occurrence Matrix (GLCM). In the 4 directions of 0°, 45°, 90°, 135° the 16 feature parameters such as energy, entropy, inertia moment and so on are calculated and are put into SVM for wood species recognition. Lastly, the 4 composite kernels SVM are used to fuse the spatial-spectral features for wood species recognition. Experiments on 20 wood species classification indicate that CARS is a better choice in view of the feature wavelength selection and running speed and the classification accuracy for testing set reaches to 92.166 7% if the ordinary SVM is used for wood spectral classification. If the wood texture features based on GLCM are used, the classification accuracy for testing set reaches to 60.333 0% if the ordinary SVM is used. When the wood spectral and texture features are fused for classifications, the composite kernel SVM has the best classification accuracy. Especially, the classification accuracy of the 2^nd composite kernel SVM is the highest with 94.1667% for testing set and a processing speed of 0.254 7 s. Moreover, the classification accuracy of the 1^st or 3^rd composite kernel SVM reaches to 93.333 3% or 92.610 0% with a running speed of 0.180 0 or 0.260 2 s. Therefore, wood species classification accuracy can be improved by use of hyper-spectral imaging and composite kernel SVM, which may be applied in the practical wood species classification system.

Key words：Wood species classification; Hyper-spectral imaging; Composite kernel; SVM; Feature fusion

Received: 2019-03-18 Accepted: 2019-07-24

ZTFLH:

TP391

Corresponding Authors: ZHAO Peng E-mail: bit_zhao@aliyun.com

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2019)12-3776-07 OR https://www.gpxygpfx.com/EN/Y2019/V39/I12/3776

[1] Yusof R, Khalid M, Khairuddin A S M. Machine Vision and Applications, 2013, 24：1589.
[2] Ibrahim I, Khairuddin A S M, Talip M S A, et al. Wood Science and Technology, 2017, 51(3)：431.
[3] Piuri V, Scotti F. IEEE Trans SMC-Part C, 2010, 40(3)：358.
[4] Yuan W, Shuai S, Nan Z, et al. Bioresources, 2019, 14(1)：1033.
[5] Yusof R, Khalid M, Khairuddin A S M. Computers and Electronics in Agriculture, 2013, 93：68.
[6] LIU Ping, MA Mei-hu(刘平，马美湖). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2018，38(1)：246.
[7] WANG Bin, XUE Jian-xin, ZHANG Shu-juan(王斌，薛建新，张淑娟). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报)，2013，44(s1)：205.
[8] SUN Jun, JIN Xia-ming, MAO Han-ping, et al(孙俊，金夏明，毛罕平，等). Transactions of the Chinese Society for Agricultural Engineering(农业工程学报)，2014，30(21): 301.
[9] DENG Xiao-qin, ZHU Qi-bing, HUANG Min(邓小琴，朱启兵，黄敏). Laser & Optoelectronics Progress(激光与光电子学进展)，2015，52(2)：122.
[10] Fauvel M, Tarabalka Y, Benediktsson J A, et al. Proceedings of the IEEE, 2013, 101(3)：652.
[11] Dong K X, Tao L S, Benediktsson J A. IEEE Transactions on Geoscience & Remote Sensing, 2014, 52(5)：2666.
[12] Hong L, Song Y, Chen C L P. IEEE Transactions on Geoscience & Remote Sensing, 2017, 55(9)：5302.
[13] Cui X, Wang Q Q, Zhao Y, et al. Applied Physics B: Lasers and Optics, 2019, 125(4): 56.
[14] Dawson A B, Adedipe O E. Wood Science and Technology, 2012, 46(6): 1193.
[15] Cortes C, Vapnik V. Machine Learning, 1995, 20(3)：273.
[16] Valls G C, Chova L G, Mari J M, et al. IEEE Geoscience and Remote Sensing Letters, 2006, 3(1)：93.
[17] Pontes M J C, Galvo R K H, Araujo M C U，et al. Chemometrics and Intelligent Laboratory Systems, 2005, 78(1-2)：11.
[18] Li H, Liang Y, Xu Q, et al. Analytica Chimica Acta, 2009, 648(1)：77.