[1]李康,张毛毛,杨忠*,等.基于神经网络的人造板装饰纸表面色泽特征分类研究[J].林业工程学报,2018,3(01):16-20.
 LI Kang,ZHANG Maomao,YANG Zhong*,et al.Classification for decorative papers of wood-based panels using color and glossiness parameters in combination with neural network method[J].Journal of Forestry Engineering,2018,3(01):16-20.
点击复制

基于神经网络的人造板装饰纸表面色泽特征分类研究()
分享到:

《林业工程学报》[ISSN:1001-8081/CN:32-1160/S]

卷:
3
期数:
2018年01期
页码:
16-20
栏目:
木材科学与技术
出版日期:
2018-01-15

文章信息/Info

Title:
Classification for decorative papers of wood-based panels using color and glossiness parameters in combination with neural network method
文章编号:
2096-1359(2018)01-0016-05
作者:
李康张毛毛杨忠*吕斌
中国林业科学研究院木材工业研究所,北京 100091
Author(s):
LI Kang ZHANG Maomao YANG Zhong* LYU Bin
Research Institute of Wood Industry, Chinese Academy of Forestry, Beijing 100091, China
关键词:
人造板装饰纸 表面色泽特征分类 色度学参数 光泽度 主成分分析 误差反向传播神经网络
Keywords:
wood-based panels decorative papers classification of color and glossiness parameters chroma parameters glossiness principal component analysis(PCA) back-propagation(BP)network
分类号:
TS67
文献标志码:
A
摘要:
通过测定人造板专用装饰纸表面的色泽参数(色度学参数和光泽度),对装饰纸表面色泽特征进行量化分析,并利用色泽参数的特征信息结合误差反向传播神经网络(BP神经网络)对装饰纸进行建模分类,探讨利用装饰纸表面的色泽参数进行装饰纸表面色泽特征分类。以色泽参数数据作为神经网络的输入变量,装饰纸类型作为神经网络的输出变量,建立三层BP神经网络模型,其中,隐含层的最佳节点数为9。结果表明:通过对色泽度参数的主成分分析,增加了光泽度参数后,各类装饰纸之间的独特性增强,更利于对装饰纸进行分类。利用色度学参数(明度指数L*,红绿轴色品指数a*和黄蓝轴色品指数b*)对装饰纸进行建模分类时,判别的总正确率为80.9%,引入光泽度参数之后判别的总正确率提高至92.9%,说明利用色度学与光泽度参数结合BP神经网络可以用于装饰纸表面视觉特征的量化分析以及快速识别分类。
Abstract:
As a main decorative material applied to wood-based panel, there is a great demand for decorative paper. However, the quality problem of decorative paper, such as chromatic aberration, has been of a concern in the decorative paper industry. The traditional color difference evaluation method, such as artificial visual assessment, was prone to be affected by subjective factors and the efficiency of this method was relatively low. To explore the possibility of using visual parameters, which included lightness(L*), index of(red-green opponent)axis(a*), index of(yellow-blue opponent)axis(b*), and glossiness(G)to quantitatively analyze the surface characteristics of decorative papers and to classify the different types of decorative papers, and the feature information of visual parameters was extracted to establish classification model. The models of the principal component analysis(PCA)and back-propagation(BP)network were developed to distinguish different types of decorative papers in this study. To avoid overfitting, full-cross validation was applied for PCA modeling of samples. Based on BP network, levenberg-marquardt(L-M)algorithm was selected for the adjustment of weights and thresholds in order to reduce goal error of parameter vector. The results showed that the classification of different types of decorative papers worked well and the total accuracy reached 80.9% when the parameters of L*, a* and b* were employed. The classification accuracy increased to 92.9% when the parameter of glossiness was added, indicating that the model is accurate and practical for the quantitative analysis and rapid classification of decorative papers using the parameters of L*, a*, b* and G coupled with BP network.

参考文献/References:

[1] 张勤丽. 装饰纸在人造板表面装饰中的应用[J]. 中国人造板, 2006, 13(11):1-4, 28.
ZHANG Q L. The application of decorative paper in wood-based panel surface decoration[J]. China Wood-Based Panels, 2006, 13(11):1-4, 28.
[2] 李正木. 浸渍胶膜纸饰面人造板产业现状与创新方向[J]. 木材工业, 2016, 30(2):22-24.
LI Z M. Status and innovations of wood-based panels overlaid with impregnated paper[J]. China Wood Industry, 2016, 30(2):22-24.
[3] 刘瑞诺, 田卫国, 丁武斌. 我国印刷装饰纸发展现状[J]. 中国人造板, 2011, 18(1):4-5, 9.
LIU R N, TIAN W G, DING W B. Current situation of the decor paper industry and its domestic market[J]. China Wood-Based Panels, 2011, 18(1):4-5, 9.
[4] KANDELBAUER A, PETEK P, MEDVED S, et al. On the performance of a melamine-urea-formaldehyde resin for decorative paper coatings[J]. European Journal of Wood and Wood Products, 2010, 68(1):63-75.
[5] 中国林产工业协会. 2016我国地板行业及装饰纸行业销量统计[J]. 木材工业, 2017, 31(2): 61.
[6] AMOR A B, CLOUTIER A, BEAUREGARD R. Determination of physical and mechanical properties of finishing papers used for wood-based composite products[J]. Wood and Fiber Science, 2009, 41(2): 117-126.
[7] KANDELBAUER A, TEISCHINGER A. Dynamic mechanical properties of decorative papers impregnated with melamine formaldehyde resin[J]. European Journal of Wood and Wood Products, 2010, 68(2): 179-187.
[8] 沈春彦. 高耐磨浸渍纸及其生产工艺的研究[J]. 林业科技开发, 2001, 15(4):33-34.
SHEN C Y. Discussion on development of strong impregnated antifriction paper[J]. China Forestry Science and Technology, 2001, 15(4):33-34.
[9] 顾忠基, 姜彬, 朱萍, 等. Mg/Al-LDHs纳米阻燃剂的制备及其在饰面人造板中的应用[J]. 林业科技开发, 2016, 1(4):39-44.
GU Z J, JIANG B, ZHU P, et al. Preparation and application of Mg/Al-LDHs nano flame retardant in veneer wood-based panel[J]. China Forestry Science and Technology, 2016, 1(4):39-44.
[10] 董政, 宁长征, 陈蕾. 减少装饰板色差的主要对策[J]. 木材加工机械, 2002, 13(4):21-22.
DONG Z, NING C Z, CHEN L. How to decrese chromatism of decorative laminates[J]. Wood Processing Machinery, 2002, 13(4):21-22.
[11] 唐正宁, 朱嵬. 基于装饰纸特点的印刷色差及其评价[J]. 包装工程, 2007, 28(11):62-64.
TANG Z N, ZHU W. Color difference and its evaluation based on decorative paper characteristics[J]. Packaging Engineering, 2007, 28(11):62-64.
[12] 杨忠, 张毛毛, 吕斌, 等. 装饰纸表面视觉特征分类的可见光光谱分析[J]. 木材工业, 2014, 28(5):32-35.
YANG Z, ZHANG M M, LYU B, et al. Visible spectroscopy analysis on surface visual characteristics of decorative paper[J]. China Wood Industry, 2014, 28(5):32-35.
[13] 张毛毛, 杨忠, 吕斌, 等. 基于可见光光谱的装饰纸表面视觉特征的模式识别研究[J]. 光谱学与光谱分析, 2015, 35(2):443-446.
ZHANG M M, YANG Z, LYU B, et al. Pattern recognition of decorative papers with different visual characteristics using visible spectroscopy coupled with principal component analysis(PCA)[J]. Spectroscopy and Spectral Analysis, 2015, 35(2):443-446.
[14] YANG Z, ZHANG M, PANG X, et al. Classifications of decorative paper using differential reflection spectrophotometry coupled with soft independent modeling of class analogy[J]. BioResources, 2014, 9(2): 2521-2528.
[15] 彭帮柱, 岳田利, 袁亚宏, 等. 苹果酒发酵过程中糖度近红外光谱检测模型的建立[J]. 光谱学与光谱分析, 2009, 29(3):652-655.
PENG B Z, YUE T L, YUAN Y H, et al. Modeling of sugar content based on NIRS during Cider-Making fermentation[J]. Spectroscopy and Spectral Analysis, 2009, 29(3):652-655.

备注/Memo

备注/Memo:
收稿日期:2017-07-12 修回日期:2017-09-28
基金项目:国家自然科学基金(31370711); 国家重点研发计划项目(2016YFD0600706)。
作者简介:李康,男,研究方向为木材质量与标准化。通信作者:杨忠,男,研究员。E-mail: zyang@caf.ac.cn
更新日期/Last Update: 2018-01-10