油漆涂层对近红外鉴别两种红木家具种类影响分析

红木家具市场以次充好、以假乱真的现象非常普遍, 导致消费者对其真伪难以鉴别。目前对于近红外识别木材种类的研究已经很多, 但对成品家具而言, 表面涂饰是阻碍近红外光谱检测的最大障碍。因此本文通过对不同种类油漆涂层覆盖下木材近红外光谱特征分析, 提出了一种主成分分析(Principal Component Analysis, PCA)结合BP神经网络(Back Propagation)的红木家具种类鉴别方法。以市面上易混淆的交趾黄檀和微凹黄檀为试验对象, 首先使用近红外光谱仪采集光谱数据, 比较了原木与家具的光谱差异, 然后采用标准正态变量变换(Standard Normal Variate Transformation, SNV)的预处理方法, 再利用主成分分析法以累积贡献率大于95%的主成分作为样品特征, 构建3层BP神经网络模型。结果表明: 基于主成分分析的BP神经网络的方法能较好的鉴别交趾黄檀和微凹黄檀两种红木家具, 预测结果准确率分别为92.59%和94.38%, 给红木家具种类的鉴别提供了一种新的可靠的方法。

Abstract

It’s a common phenomenon that shoddy and deceptive the hongmu furniture is filled with all markets.It’s so hard for consumers to identify the species of the hongmu furniture.There are many studies on the application of near infrared spectroscopy classification of wood species.But for the finished furniture, the surface decoration is the biggest problem to classify the hongmu furniture.So this paper analyzes the spectral characteristics of wood covered by different kinds of paints and proposes a method which is combined with Principal Component Analysis(PCA) and Back Propagation Neural Networks by using near infrared spectroscopy.We firstly collected spectral data from Dalbergia cochinchinensis and Dalbergia retusa which are usuaslly confusing hongmu furniture species in the market, and compered the spectral difference of hongmu and the hongmu furniture.Secondly, reflection spectra were preprocessed by taking SNV to remove irrelevant information and noise.Finally, principal component analysis was used to distill initial feature vectors and asbilish new sample’s feature vectors according to cumulate reliability.Then, we chose the new feature vectors which its cumulate reliability is more than 95%.A three layer probabilistic neural network was designed.Results show that recognition rates of these three species of hongmu furniture are 92.59% and 94.38%.So our approach provides an new and reliable method for the identification of hongmu furniture.

参考文献

[1] 赵荣军, 邢新婷, 吕建雄, 等.粗皮桉木材力学性质的近红外光谱方法预测［J］.林业科学, 2012, 48(06): 106-111.(ZHAO Rongjun, XING Xinting, LV Jianxiong, et al.Estimation of wood mechanical properties of eucalyptus pellita by near infrared spectroscopy［J］.Sinentia Silvae Sinicae, 2012, 48(06): 106-111)

[2] 赵荣军, 张黎, 霍小梅, 等.基于近红外光谱技术预测径/弦切面粗皮桉木材微纤丝角［J］.光谱学与光谱分析, 2010, 30(09): 2355-2359.(ZHAO Rongjun, ZHANG Li, HUO Xiaomei, et al.Microfibril angle prediction of eucalyputs pellita wood samples based on radial and tangential section by near infrared spectroscopy［J］.Spectroscopy and Spectral Analysis, 2010, 30(09): 2355-2359)

[3] 徐浩凯.东北林区主要阔叶材密度近红外定标模型研究［D］.东北林业大学, 2015.(XU Haokai.Nir-based modeling wood denstiy of major hardwood species in northeastern region［D］.Northeast Forestry University, 2015)

[4] 李菲菲, 张晶, 范静涛, 等.基于NIR和SVM算法的巴里黄檀和交趾黄檀鉴别研究［J］.光谱学与光谱分析, 201636(S1): 69-72.(LI Feifei, ZHANG Jing, FAN Jingtao, et al.Study on classifi-cation of Dalber-gia Bariensis and Dalbergia Cochinchinensis by near infrared spectroscopy and SVM［J］.Spectroscopy and Spectral Analysis, 2016, 36(S1): 69-72)

[5] 曲志华.基于近红外技术的木材腐朽理化性质变化及腐朽分级研究［D］.东北林业大学, 2011.(QU Zhihua.Study on wood physcial and chemical decay properties and grading based on near infrared spectroscopy［D］.Northeast Forestry University, 2011)

[6] 杨忠, 江泽慧, 吕斌.红木的近红外光谱分析［J］.光谱学与光谱分析, 2012, 2(9): 2405-2408.(YANG Zhong, JIANG Zehui, LV Bin.Investigation of Near Infrared Spectroscopy of Rose-wood［J］.Spectroscopy and Spectral Analysis, 2012, 32(9): 2405-2408)

[7] 王学顺, 孙一丹, 黄敏高, 等.基于BP神经网络的木材近红外光谱树种识别［J］.东北林业大学学报, 2015, 43(12): 82-85+89.(WAGN Xunshun, SUN Yidan, HUANG Mingao, et al.Back propagation artificial neural network combined with near infrared spectroscopy for timber recognition［J］.Journal of Northeast Forestry University, 2015, 43(12): 82-85+89)

[8] Gu Y Q, Shou G Z, Zhang W Y, et al.Application of near infrared spectroscopy for discrimination of similar rare woods in the Chinese market［J］.Journal of Near Infrared Spectroscopy, 2015, 22(6): 423)

[9] 汪杭军, 张广群, 祁亨年, 等.木材识别方法研究综述［J］.浙江林学院学报, 2009, 26(06): 896-90.(WANG Hangjun, ZHANG Guangqun, QI Hengnian, et al.A review of research on wood recog-nition technology［J］.Journal of Zhejiang Forstry College, 2009, 26(06): 896-90)

[10] 李敏华, 谭必明, 黄志同, 等.古家具木材无损鉴定方法研究［J］.西北林学院学报, 2012, 27(06): 165-167+173.(LI Minghua, TAN Biming, HUANG Zhitong, et al.A study on wood nondestru-ctive identification method of ancient furniture［J］.Journal of Northwest Forestry University, 2012, 27(06): 165-167+173)

[11] 陈全胜, 王名星, 郭志明, 等.鸡肉中假单胞菌的近红外光谱快速识别［J/OL］.农业机械学报, 2017, 48(08): 328-334.(CHEN Quansheng, WANG Mingxing, GUO Zhiming, et al.Rapid identification of pseudomonas spp.in chicken by near-infrared spectroscopy［J/OL］.Transaction of the Chinese Soci-ety for Agricultural Machinery, 2017, 48(08): 328-334)

[12] 吴江, 黄富荣, 黄才欢, 等.近红外光谱结合主成分分析和BP神经网络的转基因大豆无损鉴别研究［J］.光谱学与光谱分析, 2013,(06): 1537-1541.(WU Jiang, HUANG Furong, HUANG Caihuan, et al.Study on near infrared spectroscopy of transgenic soyben indentification based on principal component analysis and neural network［J］.Spectroscopy and Spectral Analysis, 2013,(06): 1537-1541)

[13] 陈争光, 李鑫, 范学佳.基于可见近红外光谱分析技术的马铃薯品种鉴别方法［J］.光谱学与光谱分析, 2016, 36(08): 2474-2478.(CHEN Zhengguang, LI Xing, FAN Xuejia.Method for the discrimi-nation of the variety of potatoes with vis/nir spectroscopy［J］.Spectroscopy and Spectral Analysis, 2016, 36(08): 2474-2478)

[14] 张敏, 范龙, 代祥, 等.基于BP神经网络的变量喷雾供药系统研究［J］.林业工程学报, 2017, 2(2): 133-137.(ZHANG Ming, FAN Long, DAI Xiang, et al.Study on pesticide-delivery system of variable-rate spraying based on BP neural network［J］.Journal of Forestry Engineering, 2017, 2(2): 133-137)

赵晓俊, 顾玉琦, 王佩欣, 寿国忠, 钱孟波. 油漆涂层对近红外鉴别两种红木家具种类影响分析[J]. 光散射学报, 2019, 31(1): 88. ZHAO Xiaojun, GU Yuqi, Wang Peixin, SHOU Guozhong, QIAN Mengbo. Analysis on the Near Infrared Identification of Two Kinds of Hongmu Furniture by the Influence of Paint Coating[J]. The Journal of Light Scattering, 2019, 31(1): 88.

油漆涂层对近红外鉴别两种红木家具种类影响分析

关于本站 Cookie 的使用提示

全站搜索

油漆涂层对近红外鉴别两种红木家具种类影响分析

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索