面向用户视觉心理的实木板材压缩感知聚类分选

李超; 苏耀文; 涂文俊; 张怡卓

doi:10.13332/j.1000-1522.20150315

面向用户视觉心理的实木板材压缩感知聚类分选

东北林业大学机电工程学院,东北林业大学机械工程流动站

基金项目:

林业公益性行业科研专项(201304510)、黑龙江省自然科学基金项目(C2015054、C201405)、中央高校基本科研业务费专项(2572016BB05)。

详细信息

作者简介:
李超,博士,讲师。主要研究方向:信号处理与图像处理。Email:lchao820225@163.com地址:150040黑龙江省哈尔滨市和兴路26号东北林业大学机电工程学院。责任作者:张怡卓,博士,副教授。主要研究方向:图像处理与模式识别。Email:nefuzyz@163.com地址:同上。

李超,博士,讲师。主要研究方向:信号处理与图像处理。Email:lchao820225@163.com地址:150040黑龙江省哈尔滨市和兴路26号东北林业大学机电工程学院。责任作者:张怡卓,博士,副教授。主要研究方向:图像处理与模式识别。Email:nefuzyz@163.com地址:同上。

计量
- 文章访问数: 1710
- HTML全文浏览量: 104
- PDF下载量: 29
出版历程
- 收稿日期: 2015-08-26
- 发布日期: 2016-07-29

User-oriented visual psychological sorting method for wood plate.

College of Mechanical and Electrical Engineering, Northeast Forestry University,Harbin,Heilongjiang,150040,P. R. China.

摘要

摘要: 实木板材外观特性影响着消费者对产品的喜好,在一定程度上决定着产品的价格和销量。实木板材表面的颜色与纹理存在随机性与相异性,因此采用统计特征进行分选具有一定的局限性。针对板材表面特点,本文提出了面向用户视觉特征的板材分选方法。该方法将用户的视觉喜好转化为对颜色和纹理的量化分析,然后挖掘样本数据所表达的特征及状态信息完成样本优选,最后利用压缩感知分类器进行信息整合及板材分选。颜色方面,提取L*a*b*颜色空间下的9个特征,通过区间整合得出颜色分选范围;纹理方面,提取基于人类视觉心理的Tamura纹理特征6个参量和基本统计特征。由于Tamura特征的6个参量对应于心理学角度上纹理的6种属性,这些特征可以将用户视觉心理和基本统计信息相融合,更为准确、完整地表达板材表面的视觉特性。此外,通过遗传非线性映射算法对两类纹理的训练样本进行优选,提高了后期的分选精度。最后,针对用户视觉需求,设计了板材表面压缩感知分类器,构建由L*a*b*颜色特征、Tamura纹理特征和基本统计特征组成的过完备字典,通过求解最小l1范数的方法,找出测试样本的特征数据与过完备字典中相匹配的类别向量,完成分类。实验结果表明该方法的识别精度为90.56%,方法具有实用性。
- 实木板材 /
- 压缩感知 /
- L*a*b*颜色特征 /
- Tamura纹理识别
Abstract: Wood appearance affects consumers’ preference of products, and determines the price of products and sales to a certain extent. Colors and texture on the wood board are random and diverse, so using statistical methods to classify them has limitations. According to the characteristics of board surface, we propose a board classification method based on user’s visual characteristics of. This method converts user’s visual preferences into a quantitative analysis of the color and texture, then optimizes samples through mining features demonstrated by the sample data and status information, and finally designs a compression perception classifier for information integration and wood classification. For colors, Tamura texture features and the basic statistical features were used as feature vector, which include six parameters corresponding to six kinds of psychology properties. These features can fuse user’s visual psychology with the basic statistics, and give a more accurate and complete expression of visual features on the board surface. What’s more, the genetic algorithm was implemented to optimize training sample by its nonlinear mapping. For classifier design, compressed sensing was employed as classifier, an over-complete dictionary was built by L*a*b* color feature, Tamura feature and the basic statistical characteristics, and the classification result was obtained by solving the minimum of l1 norm to find out the characteristic data of the test sample and the class vector in the over complete dictionary. Experiments show that the accuracy is 90.56% and the sorting method is practical.
- wood plate /
- compressed sensing /
- L*a*b* color feature /
- Tamura texture feature

HTML全文

参考文献(27)

[1]	常湛源, 曹军, 张怡卓. 板材心理感知颜色在线模糊分类器设计[J]. 电机与控制学报, 2014, 18(9):93-98.
[1]	CHANG Z Y, CAO J, ZHANG Y Z. Design of on-line timber plate fuzzy classification fused with psychological perceptions of color[J]. Electric Machines and Control, 2014, 18(9):93-98.
[2]	白雪冰, 王克奇, 王辉. 基于灰度共生矩阵的木材纹理分类方法的研究[J]. 哈尔滨工业大学学报, 2005, 37(12):1667-1670.
[2]	BAI X B, WANG K Q, WANG H. Research on the classification of wood texture based on gray level cooccurrence matrix[J]. Journal of Harbin Institute of Technology, 2005, 37(12):1667-1670.
[3]	WANG K Q, WANG Y Q, BAI X B, et al. Acquisition of color feature parameters of wood image identification[J]. Journal of Northeast Forestry University, 2006, 34(3): 104-105.
[3]	王克奇, 王业琴, 白雪冰, 等. 板材图像识别中颜色特征参数的提取[J]. 东北林业大学学报, 2006, 34(3): 104-105.
[4]	杨少春, 王克奇, 戴天虹, 等. 基于直方图的木材表面颜色分类研究[J]. 森林工程, 2008, 24(1): 34-36.
[4]	YANG S C, WANG K Q, DAI T H, et al. A study of color classification on wood surface based on histogram[J]. Forest Engineering, 2008, 24(1): 34-36.
[5]	WANG K Q, YANG S C, DAI T H, et al. Research on wood classification using uniform color space[J].Computer Engineering and Design, 2008, 29(7): 1780-1784.
[5]	SCHMITT E, MAZAUD C, BOMBARDIER V, et al. A fuzzy reasoning classification method for pattern recognition[J]. IEEE International Conference on Fuzzy Systems, 2006, 24(2):1078-1085.
[6]	王克奇, 杨少春, 戴天虹, 等. 基于均匀颜色空间的木材分类研究[J]. 计算机工程与设计, 2008, 29(7): 1780-1784.
[6]	YIN S C. Wood science[M]. Beijing: China Forestry Publishing House, 1996: 33-34.
[7]	尹思慈. 木材学[M]. 北京:中国林业出版社, 1996: 33-34.
[7]	ZHANG Y Z, MA L, XU L,et al. Wood board texture classification based on genetic fusion of wavelet and curvelet features[J]. Journal of Beijing Forestry University, 2014,36(2):119-124.
[8]	张怡卓, 马琳, 许雷, 等. 基于小波与曲波遗传融合的木材纹理分类[J]. 北京林业大学学报, 2014, 36(2): 119-124.
[8]	WANG K Q, BAI X B, WANG H. Classification of wood surface texture based on wavelets transform[J]. Journal of Harbin Institute of Technology, 2009,41(9):232-234.
[9]	REN N,YU H P,LIU Y X,et al. Fractal character and calculation of wood texture[J]. Journal of Northeast Forestry University,2007, 35(2): 9-11.
[9]	王克奇, 白雪冰, 王辉. 基于小波变换的木材表面纹理分类[J]. 哈尔滨工业大学学报, 2009,41(9):232-234.
[10]	LIU Z H, WANG H J. Wood identification based on feature fusion of PCA and fishertrees[J]. Scientia Silvae Sinicae, 2013, 49(6):122-128.
[10]	任宁, 于海鹏, 刘一星, 等. 木材纹理的分形特征与计算[J]. 东北林业大学学报, 2007, 35(2): 9-11.
[11]	XIAO S P,CHEN Y D,YANG J X. Color texture recognition based on wavelet transform and support vector machine[J]. Microelectronics and Computer, 2010,27(7):117-120.
[11]	AVCI E, SENGUR A, HANBAY D. An optimum feature extraction method for texture classification[J]. Expert Systems with Applications, 2009, 36(3): 6036-6043.
[12]	JING J, ZHANG H, WANG J, et al. Fabric defect detection using Gabor filters and defect classification based on LBP and Tamura method[J]. Journal of the Textile Institute, 2013, 104(1): 18-27.
[12]	CHEN L J,WANG K Q,WANG H, et al. The confirmation of wavelet base and decomposition progression in wood texture analysis[J]. Forestry Machinery Woodworking Equipment, 2007, 35(5):25-27.
[13]	刘子豪, 汪杭军. 基于PCA＋FisherTrees特征融合的木材识别[J]. 林业科学, 2013, 49(6):122-128.
[14]	肖淑苹, 陈一栋, 杨建雄. 基于小波变换和支持向量机的彩色纹理识别[J]. 微电子学与计算机,2010,27(7):117-120.
[15]	陈立君, 王克奇, 王辉, 等. 木材纹理分析中小波基的选择和分解级数的确定[J]. 林业机械与木工设备, 2007, 35(5):25-27.