木材显微图像特征参数提取与树种判别方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
应用先进的计算机彩色图像分析软件对木材横切面的细胞轮廓形态、细胞几何尺寸、组织比量等进行测定与分析;采用空间灰度共生矩阵方法提取木材横切面的显微图像灰度变化与构造特征参数,探讨了基于所提取的多种量化的图像特征参数实现树种判别的可行性,并初步建立基于木材横切面显微图像内容(特征参数)的木材树种判别程序。
     对基于木材横切面显微图像所提取的33项特征进行主成分分析,结果表明前七个主成分因子集中了33个变量的90%左右的信息,它们分别是导管(树脂道)形态与尺寸因子、横切面纹理强弱及周期大小因子、组织比量因子、纹理粗细与复杂程度因子、木纤维(管胞)细胞的几何尺寸因子、木纤维(管胞)细胞形态因子、径向木纤维(管胞)细胞壁大小因子。同时结合变量间的相关分析,从33项特征中选取出了15项对树种判别具有实际意义的特征参数。
     利用所选取出的15项特征参数,以最大相似原理初步建立了基于图像分析的计算机树种判别匹配算法,这种判别匹配算法是通过计算待判别树种与已知树种之间的相似系数来实现的。文中运用了最小差值差数判别法、树种综合特征阈值法、综合加权相似法三种方式进行相似系数的计算。其中最小差值差数判别法与树种综合特征阈值法是将每个特征参数对木材横切面显微图像特征的贡献率视为一致,只是树种综合特征阈值法是以阈值的大小来判断特征的相似性,而综合加权相似法是建立在对木材横切面显微图像特征参数的主成分分析的基础上,根据每个特征参数的贡献率大小计算相似系数。以相似系数计算为基础的计算机树种判别程序对未知树种的判别并不是给出唯一的答案,而是将数据库中的树种按相似系数的大小进行排序,同时能在主界面上显示树种的宏、微观特征和三切面显微图像,以便用户进一步验证待判别树种应为何种树种,提高了判别结果的准确性。
     通过对木材横切面显微图像量化特征参数的提取与分析、基于图像分析的判别匹配算法和判别程序的建立,结果表明,以基于图像分析的方法达到木材判别的目的是基本可行的。此项研究结果将为木材鉴别、树木分类提供一种新的技术参考手段和初步的科学理论依据。
It determined and analyzed the cellular contour, cellular dimension, tissue proportion, etc. of the wood transverse section by the software of multicolor image manipulation. And it determined the gray level and structure parameters of wood transverse section micrograph by spatial gray level cooccurrence matrix (GLCM). Then it researched on the feasibility of wood recognition according to the quantitative characters about micrograph, moreover, it programmed the wood recognition program based on the micrograph content of wood transverse section elementarily.
    It analyzed the 33 parameters about the micrograph of wood transverse section by the principal component and induced seven principal components. The results showed that the contribution of first seven principal components to total parameters was close to 90 percent. The first seven principal components were vessel(resin canal) morphological and dimension factor, texture intensity and period factor, tissue proportion factor, texture thickness and complexity factor, fiber (tracheid) dimension factor, fiber(tracheid) morphological factor, radial cell wall dimension of fiber(tracheid) factor, respectively. At the same time, it analyzed the correction among the parameters, and extracted 15 parameters which have significance for wood recognition from all parameters.
    It founded the computer aided wood recognition algorithm based on image manipulation according to 15 quantitative parameters. The algorithm was founded on the most similar principle. The key of the algorithm was computing the similar coefficient between the unknown sample and the samples in database. The methods of computing for similar coefficient were Discriminance of Minimal Difference of Parameters(DMDP), Discriminance of Limen of Tree Compositive Character(DLTC) and Synthetic Weight Similarity of Parameters(SWSP). The contribution of all parameters were considering as same for DMDP and DLTC, but it estimate s the similarity between parameters according to the limen for DLTC. DMDP was based on the principal component analysis for wood transverse section micrograph characters and computing the similar coefficient according to the contribution of every parameter. The recognition results of wood recognition program is not the only one. The all records in database are sorted by the similar coefficient. At th
    e same time, the micro structural characteristic, the macro structural characteristic and the image of three sections are shown in the main interface. The user can testify which is the unknown sample. Then the veracity was improved.
    
    
    According to determined and analyzed of parameters of the wood transverse section micrograph, established of the recognition algorithm and programmed of wood recognition method, the results showed that the wood recognition method was feasibility based on the image manipulation. It would offer a new technical reference means and elementary theory foundation
引文
1 李坚等.木材波谱学.科学出版社.北京:2002
    2 薛重生,王霞.基于分形几何的遥感图像纹理分析方法及应用.地质科技情报,1997,16(增刊):99-105
    3 张继贤,李德仁.基于纹理质地子特征的影像纹理分形分析.测绘学报,1995,(4):267-274
    4 李小川,程光钺.化学药物对细胞形变作用的计算机识别方法(Ⅰ)——模糊识别法.计算机与应用化学,1996,13(2):114-118
    5 竺子民,余兴龙,金国藩,谭耀麟.中医舌像自动识别系统的研究.华中理工大学学报,1995,23(8):55-59
    6 祁亨年,寿韬,金水虎.基于叶片特征的计算机辅助植物识别模型.浙江林学院学报,2003,20(3):281-284
    7 任王君,陶玲.中国沙拐枣属植物的数值分类研究.西北植物学报,2002,22(5):1073-1085
    8 邬浩,潘云鹤,庄越挺,杨宇艇.基于对象形状的图像查询技术.软件学报,1998,9(5):343-349
    9 Nozomu Takahashi, Masajiro lwasakri, Takayuki Kunieda, et al. Image Retrieval Using Spatial Intensity Features. Signal Processing: Image Communication. 2000, 16:45-47
    10 刘忠伟,章毓晋.综合利用颜色和特征的图像检索.通信学报,1999,20(5):36-40
    11 章毓晋,刘忠伟.基于HIS模型和累积直方图的彩色图像检索.第八届信号处理学组委员会联合会议论文集,1997,256-260
    12 傅德胜,王新芝.云图纹理特征的抽取与云的自动分类.南京气象学院学报,1995,18(4):530-535
    13 夏德深,金盛,王健.基于分数维与灰度梯度共生矩阵的气象云图识别(Ⅰ)——分数维对纹理复杂度和粗糙度的描述.南京理工大学学报,1999,23(3):278-281
    14 Niblack et al. The QBIC project: querying image by content using color, texture, and shape. International Society for Optical Engineering, 1993, 19:173-187
    15 Flicker et al. Query by image and video content, the QBIC system. IEEE Computer, 1995, 28(9): 23-31
    16 杨家驹,程放,卢鸿俊.木材(特征图象)的微机识别.木材工业,2001,15(3):31-32
    17 李坚.木材科学.高等教育出版社.北京:2002
    18 Charles W. McMillin. Application of automatic image analysis to wood science. Wood Science. 1982. 14(3): 97-105
    19 Jordan B D. A simple image analysis procedure for fiber wall thickness. JPPS Journal of Pulp-and-Paper-Science. 1988, 14(2): 44-45
    20 Huang YS. Chen SS. Application of FFT spectrum analysis to the evaluation of roughness of wood sanding surface. Forest Products Industries. 1990, 9(2): 61-70
    21 前川知之,藤田稔,佐伯浩.木材细胞配列解析——极坐标评价.日本木材学会研究发表要旨集,1991,第41回:65
    
    
    22 岩切一树,藤田稔,佐伯浩.积算画象处理细胞壁厚度计划.木材学会研究发表要旨集,1991,第41回:67
    23 藤田稔,前川知之,佐伯浩.木材横断面细胞形状配列白己相关特微抽出.第41回日本木材学会大会研究发表要旨集,1991
    24 Choi D, Thorpe JL, Hanna RB. Image analysis to measure strain in wood and paper. -Wood Science and Technology, 1991. 25(4): 251-262
    25 Ttetford RD. Darrigo RD. Jacoby CC. An image analysis system for determining densitometric and ring-width time series. Canadian Journal of Forest Research, 1991, 21 (10): 1544-1549
    26 Fjjita M. Hata, S. Saiki H. Periodic analysis of non-microscopic wood structure. Ⅳ. characteristics of the power spectral pattern of wood sections and application of non-microscopic wood pictures. Mem. Coll. Agile. KyotoUniv. 1991. 138:11-23
    27 Watanabe U. Fujita M. Norimoto M. Analysis of the shrinkage deformation of wood cells using the replica and Fast Fourier Transform methods. In. - Donaldson LA. Singh AP. Butterfield BG. Whitehouse LJ(eds)Recent Advances in Wood Anatomy. New Zealand Forest Research Institute Ltd. 1996. - 363-365
    28 Fujita M, Ohyama M, Saiki H. Characterization of vessel distribution by Fourier Transform Image Analysis. In: Donaldson LA. Singh AP. Butterfield BG. Whitehouse LJ(eds) Recent Advances in Wood Anatomy. New Zealand Forest Research Institute Lth. 1996:36-44
    29 Diao Xiuming, Takeshi Furuno, Tohru Uehara. Analysis of Cell Arrangement in Softwoods Using two-dimensional Fast Fourier Transforms. Mokuzai Gakkaishi, 42(7):634-641
    30 Diao Xiuming, Takeshi Furuno, Minoru Fujita. Digital image analysis of cross-sectional tracheid shapes in Japanese softwoods using the circularity index and aspect ratio. Journal of Wood Science, 1999, 45(2):98-105
    31 Donaldson L.A.et al.应用图像分析技术测定木材细胞尺寸时常规透射光学显微镜与共焦显微镜的比较.IAWA.,1998,19(3):321-336
    32 刘自强等.木材缺陷图像的伪彩色处理.林业科学,1989,25(2)
    33 赵学增.木质材料表面粗糙度计算机视觉检测技术的研究.东北林业大学学报,1992:20(5)
    34 王金满主编.木质材料计算机视觉分析.东北林业大学出版社.哈尔滨:1998
    35 王金满,曲艳杰,李坚.傅立叶变换图像处理方法在木材解剖特征研究中的应用.四川农业大学学报,1998,16(1):176-180
    36 曲艳杰.木材解剖特征FFT图谱构建及其演化模式的研究.[学位论文].哈尔滨:东北林业大学,2000
    37 孙丽萍,宋文龙,张冬研等.基于数字图像处理技术实现木材横纹压缩过程中构造学形态特征的研究.东北林业大学学报,2000,16(2):15-18
    38 戚大伟.木材无损检测图像处理系统的研究.林业科学,2001,37(6):92-96
    
    
    39 成俊卿主编.木材学.北京:中国林业出版社.北京:1985
    40 程放、王艳君、陆熙娴,木材综合信息数据库查询系统的研究,木材工业,1995,9(4):16-19
    41 徐峰,中国和东南亚1000种木材图像计算机查询系统,四川农业大学学报,1998,16(1):181-183
    42 邵卓平、卫广杨、方林,应用V.Forpro6. 0开发木材标本微机管理系统,林业科技通讯,2000.1:16-17
    43 邵卓平、费本华、卫广杨,木材标本管理系统的研究,木材工业,1998,12(3):37-39
    44 王艳君,程放.拉丁美洲热带木材树种数据库查询系统.木材工业,2000,14(2):31-32
    45 卢官明.基于内容的图像及视频检索.南京邮电学院学报,2002,22(2):33-36
    46 黄学军,杨恒新,王伟.利用图像特征的图像检索.红外与激光工程,2002,31(6):495-498
    47 陈咏梅.前馈网络模式识别预处理方法评价及其在手写体数字识别中的应用.[博士学位论文].北京:中国科学半导体研究所,2001
    48 苏剑波.徐波.应用模式识别技术导论.上海交通大学出版社.上海:2001
    49 Haralick R., Shanmugam K., Dinstein I. Textural Features for Image Classification, IEEE Transactions on Systems. Man and Cybernetics, 1973, 3(6): 610-621
    50 P. Szczypifiski, M. Kociolek, A. Materka, M. Strzelecki. Computer Program for Image Texture Analysis in PhD Students Laboratory. International Conference on Signals and Electronic Systems, Lód-Poland 2001:255-262
    51 徐建华.图像处理与分析.科学出版社.北京:1992
    52 Hawkins, J. K. Textural properties for pattern recognition. Picture Processing and Psychpietorics. New York: Academic Press, 1970, 347-370
    53 洪继光.灰度—梯度共生矩阵纹理分析方法.自动化学报,1984,10(1):22-25
    54 Furht B. et al. Video and Image Processing in Multimedia System. Boston:Lluwer Academic Publishers, 1995, 226-270
    55 于海鹏,刘一星,张斌,李永峰.木材表面纹理的灰度共生矩阵分析.中国林学会木材科学分会第九次学术研究讨会论文集,哈尔滨:2004,314-322
    56 于海鹏,刘一星,刘镇波.木材表面纹理的定量化分析算法与模型.中国林学会木材科学分会第九次学术研究讨会论文集.哈尔滨:2004,323-333
    57 贾永红.计算机图像处理与分析.武汉大学出版社.武汉:2001
    58 袁志发,周静芋.多元统计分析.科学出版社.北京:2002
    59 卢纹岱.SPSS for Windows统计分析.电子工业出版社.北京:2002
    60 梅长林,周家良.实用统计方法.科学出版社.北京:2002
    61 朱进忠.织物识别方法的数学模型.郑州纺织工业学院学报,1997,8(4):9-12
    62 朱进点,唐予远.织物的模式识别方法浅探.天津纺织工学院学报,1998,17(4):53-55
    63 方文彬,徐永吉,罗建举.栽培措施对短周期工业材材性影响规律的研究.中南林学院学报,
    
    1997,17(4):14-23
    64 徐魁梧,徐永吉.不同立地条件对红皮云杉人工林材性影响.林业科技开发,1997,4(2):45-46.
    65 刘盛全,鲍甫成.生长培育措施对人工林木材性质的影响.世界林业研究,1999,12(6):24-27.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700