基于计算机截面图像的棉/苎麻自动分析系统
|
摘要
目前，商检系统确定棉和苎麻纤维混纺品的成份百分比主要采用人工分析的方法，这种检测方法依赖于检测人员的主观判断，检测人员的经验、技术等因素会影响结果的客观性和准确性。人工检测方法费时、费力，并且效率低。因此，商检系统需要一种高速、客观、准确的苎麻和棉纤维分析方法。本论文研究如何采用计算机图像处理和模式识别相关技术，实现基于纤维截面图像的苎麻和棉纤维种类识别和成份分析，为建立棉和苎麻纤维种类识别以及成份分析的全自动系统奠定基础，从而实现纤维种类无人工干预、客观、准确地识别。主要研究工作有显微放大纤维截面图像光照不均现象的校正处理、纤维截面图像的预处理（边缘检测、纤维掩码、截面分离、骨架提取等等）、纤维截面特征参数的定义和提取以及基于SVM的纤维自动分类。具体如下：
论文首先提出用离均差线性迭代算法进行纤维图像点光源光照不均的校正处理。通过计算图像的离均差，寻找需要进行迭代运算的特征点集合；对每个特征点用其局部强度平均值代替灰度值，以得到的新图像作为新的处理对象，反复迭代运算直至图像的标准偏差收敛。在逐次迭代的过程中，光照不均的影响被消除，同时保留了纤维的边缘信息。算法能有效去除显微放大纤维截面图像中由点光源引起的光斑效应，为后续图像处理消除不利影响。
其次对传统Canny边缘算子提出改进，提出基于纤维截面图像内容的Canny高、低阈值的自适应算法，在Canny边缘检测算法的边缘跟踪部分提出了两个概念：“边缘长度”和“边缘分叉间平均间隔”，并以它们作为区分纤维边缘和噪声伪边缘的重要标识。改进后的Canny边缘算子延续了传统Canny边缘算子高效的特征，进一步提高了Canny边缘检测算子的输出信噪比，尤其对分布密度、分布数量各不相同的纤维截面图像具有满意的输出信噪比。对于低分辨率纤维截面图像和细微边缘的边缘检测，本文采用了基于B-Spline插值边缘检测算子，插值边缘算子对输入图像先进行插值而非高斯平滑，能有效克服Canny边缘检测算子在低分辨率图像检测方面的缺陷，改善边缘输出的信噪比和光滑度。
为了解决部分纤维截面相互粘连的问题、克服纤维截面图像边缘检测的双边缘效应，论文接着提出纤维掩码的概念。首先提出的背景填充法纤维掩码能有效克服双边缘效应，亦能较好地分离相互粘连的纤维截面。但背景填充法去掉了截面外轮廓像素点，改变了截面的周长、面积等特征参数，给纤维分类的正确性带来不确定因素。为了进一步提高纤维掩码的可应用性，本文进一步提出了二分法纤维边缘掩码算法。考虑到边缘上像素点的离均差值一般较小，算法设定了两个离均差阈值，其中低阈值用于确定纤维的存在性，高阈值用于连通低阈值检测得到的边缘像素点，以得到完整的纤维边缘掩码。
在纤维边缘掩码的基础上，本文提出了基于欧氏距离变换的纤维截面分离算法。首先以“纤维边缘掩码”为特征点集合，计算输入图像各像素点的最短欧氏距离，并设定阈值以区分“图像背景”和“纤维内腔”，然后以“纤维内腔”为特征点集合，计算“纤维边缘掩码”各像素点的最短欧氏距离。对于那些仅仅距离某个内腔子集合最近、且与其连通的边缘掩码点，被认为与该子集合属于同一个纤维截面，那些与多个内腔子集合距离相等的边缘掩码点则放在一个公共集合中，这个公共集合中的像素点与哪个纤维截面相邻，则认为该像素点属于这个纤维截面。得到独立的纤维截面以后，论文研究了纤维截面的骨架线提取。
然后论文研究并分析了已有的棉/苎麻截面特征参数，根据纤维截面特征，提出用5链码和与5链码差曲线对纤维截面骨架线进行描述，对角点、凹陷等特征进行了新的定义和定量分析。利用链码对纤维截面骨架进行描述，可以将二维的形状概念简化成一维的函数，以利用信号分析技术提取纤维截面特征。
最后对核主元分析法（Kernel Principal Component Analysis，KPCA）与支持向量机（Support Vector Machine，SVM）进行了研究。KPCA能够在高维空间提取纤维截面的一些非线性特征。SVM具有较强的推广能力、能改善由于样本缺少及样本数据残缺带来的性能降低，且SVM在理论上可以得到全局最优的解析解、不存在局部最优化问题等优势，因此本文选用SVM对棉/苎麻纤维截面进行分类。先采用100对棉/苎麻纤维截面作为样本进行训练，然后用训练所得的分类模型对棉/苎麻混纺纤维截面进行分类，并对结果进行分析。
Up to now, the blending ratio of ramie with cotton for the textile import andexport inspection in our country is determined manually. The precision is usuallyaffected by the personal experience and other factors. Furthermore, it istime-consuming and costumers have to wait several days for the result. Therefore, afast automatic system is needed for ramie and cotton test. This dissertation studieshow to use computer image processing and pattern recognition technology to analyzethe blending ratio of the ramie with cotton fibers based on a cross-sectional image. Itis aimed to provide fundamentals for the automatic fiber blending ratio inspectionsystem, which can perform fiber classifying impersonally and precisionally. In thedissertation, studies are the correction algorithm for fiber cross-sectional image withuneven illumination, the improvement for edge operator, fiber mask and overlappedfiber separation, fiber skeleton and fiber feature parameters. The inspection is realizedvia the SVM (Support Vector Machine) calculation. The detailed content is asfollows.
Firstly, linear iterative correction algorithm is presented for fiber image withuneven illumination. For those pixels with obvious deviations, their gray values arereplaced by the neighboring mean gray values, and the operation is iterated tillstandard deviations are converging. After the iterative calculations, the light spot onfiber image caused by point light source can be wiped off and the influence of unevenillumination is removed, while the fibers’ edges are well preserved. Such image isprepared for the succeeding processes.
Secondly, modifications to conventional Canny edge detection algorithm areproposed. A highly threshold and a low threshold for edge decision are self-adaptivelycalculated according to the distribution of fiber cross-sections. Edge length andaverage edge phase are added to distinguish fiber edges from noise during edgetracing. In addition to high efficiency, the output SNR (signal to noise ratio) of themodified Canny operator is higher than that of the conventional Canny operator.Furthermore, continuous edge output with satisfying noise performance can beachieved for different images with different fiber distribution. For low-resolution fiberimage or fine edge, Canny edge operator is unable to produce satisfying edge output.In order to resolve the problem, B-spline interpolatory edge operator is applied. Theinput image interpolation rather than Gaussian function smoothing is employed in the interpolatory edge operator, which is helpful to improve the output edges with goodcontinuity and output SNR.
Thirdly, fiber mask is calculated for separating touching fiber cross-sections andavoiding double edges effect. Painting background algorithm is put forward at first.By the algorithm, double edges during edge detection are avoided effectively andtouching fiber cross-sections are well separated. But outer pixels of edges arediscarded in the algorithm, which results in change of fiber’s characteristicparameters, such as perimeter and area. It will influence the correctness of fiberclassifying. In order to improve the practical applicability, bisection algorithm isproposed to calculate mask of fiber edge. Considering that the pixels on fiber edgesusually have smaller deviations, two thresholds are set for the deviation. Lowthreshold is used to look for pixels on fiber edges and high threshold is applied toconnect these pixels and get full fiber edge masks.
After that, fiber cross-section segmenting algorithm is presented based on themap of the shortest Euclidean distance according to the masks of fiber edges. Thedistance transform is executed with the target of the fiber edge mask set, and athreshold is set up to distinguish the lumen set from the background set. Then thedistance transform is executed with the target of lumen set for fiber edge mask set.When one fiber’s lumen is nearest for an edge pixel, and the edge pixel is connectiveto the lumen, the edge pixel is classified to the fiber. If two or more lumens areneareast for an edge pixel, it is classified to a common set. In which, when a pixel isneighboring to some fiber cross-sections, it is classified to them each. Then theskeletonization algorithm is studied for single fiber cross-section.
Afterwards, the characteristic parameters of ramie and cotton are analyzed.5chain code sum and5chain code difference are proposed to describe fibercross-sectional skeleton. Corner and concave are defined and calculated. By usingchain code to describe fiber cross-sectional skeleton,2D problem is simplified into1Dproblem and it is convenient to find fiber cross-sectional characteristics.
Finally, Kernel Principal Component Analysis (KPCA) and Support VectorMachine (SVM) are studied. By the use of KPCA, some nonlinear features ofcross-sections of fibers are quantified. Because SVM can be generalized better, theoptimal result can be achieved in theory and performance will not be reduced in caseof lacking samples or deformity of data, SVM is applied to fiber classifying. SVM istrained by100cotton cross-sections and100ramie cross-sections in advance, then it is applied to fiber classifying, and the results are analyzed.
论文首先提出用离均差线性迭代算法进行纤维图像点光源光照不均的校正处理。通过计算图像的离均差，寻找需要进行迭代运算的特征点集合；对每个特征点用其局部强度平均值代替灰度值，以得到的新图像作为新的处理对象，反复迭代运算直至图像的标准偏差收敛。在逐次迭代的过程中，光照不均的影响被消除，同时保留了纤维的边缘信息。算法能有效去除显微放大纤维截面图像中由点光源引起的光斑效应，为后续图像处理消除不利影响。
其次对传统Canny边缘算子提出改进，提出基于纤维截面图像内容的Canny高、低阈值的自适应算法，在Canny边缘检测算法的边缘跟踪部分提出了两个概念：“边缘长度”和“边缘分叉间平均间隔”，并以它们作为区分纤维边缘和噪声伪边缘的重要标识。改进后的Canny边缘算子延续了传统Canny边缘算子高效的特征，进一步提高了Canny边缘检测算子的输出信噪比，尤其对分布密度、分布数量各不相同的纤维截面图像具有满意的输出信噪比。对于低分辨率纤维截面图像和细微边缘的边缘检测，本文采用了基于B-Spline插值边缘检测算子，插值边缘算子对输入图像先进行插值而非高斯平滑，能有效克服Canny边缘检测算子在低分辨率图像检测方面的缺陷，改善边缘输出的信噪比和光滑度。
为了解决部分纤维截面相互粘连的问题、克服纤维截面图像边缘检测的双边缘效应，论文接着提出纤维掩码的概念。首先提出的背景填充法纤维掩码能有效克服双边缘效应，亦能较好地分离相互粘连的纤维截面。但背景填充法去掉了截面外轮廓像素点，改变了截面的周长、面积等特征参数，给纤维分类的正确性带来不确定因素。为了进一步提高纤维掩码的可应用性，本文进一步提出了二分法纤维边缘掩码算法。考虑到边缘上像素点的离均差值一般较小，算法设定了两个离均差阈值，其中低阈值用于确定纤维的存在性，高阈值用于连通低阈值检测得到的边缘像素点，以得到完整的纤维边缘掩码。
在纤维边缘掩码的基础上，本文提出了基于欧氏距离变换的纤维截面分离算法。首先以“纤维边缘掩码”为特征点集合，计算输入图像各像素点的最短欧氏距离，并设定阈值以区分“图像背景”和“纤维内腔”，然后以“纤维内腔”为特征点集合，计算“纤维边缘掩码”各像素点的最短欧氏距离。对于那些仅仅距离某个内腔子集合最近、且与其连通的边缘掩码点，被认为与该子集合属于同一个纤维截面，那些与多个内腔子集合距离相等的边缘掩码点则放在一个公共集合中，这个公共集合中的像素点与哪个纤维截面相邻，则认为该像素点属于这个纤维截面。得到独立的纤维截面以后，论文研究了纤维截面的骨架线提取。
然后论文研究并分析了已有的棉/苎麻截面特征参数，根据纤维截面特征，提出用5链码和与5链码差曲线对纤维截面骨架线进行描述，对角点、凹陷等特征进行了新的定义和定量分析。利用链码对纤维截面骨架进行描述，可以将二维的形状概念简化成一维的函数，以利用信号分析技术提取纤维截面特征。
最后对核主元分析法（Kernel Principal Component Analysis，KPCA）与支持向量机（Support Vector Machine，SVM）进行了研究。KPCA能够在高维空间提取纤维截面的一些非线性特征。SVM具有较强的推广能力、能改善由于样本缺少及样本数据残缺带来的性能降低，且SVM在理论上可以得到全局最优的解析解、不存在局部最优化问题等优势，因此本文选用SVM对棉/苎麻纤维截面进行分类。先采用100对棉/苎麻纤维截面作为样本进行训练，然后用训练所得的分类模型对棉/苎麻混纺纤维截面进行分类，并对结果进行分析。
Up to now, the blending ratio of ramie with cotton for the textile import andexport inspection in our country is determined manually. The precision is usuallyaffected by the personal experience and other factors. Furthermore, it istime-consuming and costumers have to wait several days for the result. Therefore, afast automatic system is needed for ramie and cotton test. This dissertation studieshow to use computer image processing and pattern recognition technology to analyzethe blending ratio of the ramie with cotton fibers based on a cross-sectional image. Itis aimed to provide fundamentals for the automatic fiber blending ratio inspectionsystem, which can perform fiber classifying impersonally and precisionally. In thedissertation, studies are the correction algorithm for fiber cross-sectional image withuneven illumination, the improvement for edge operator, fiber mask and overlappedfiber separation, fiber skeleton and fiber feature parameters. The inspection is realizedvia the SVM (Support Vector Machine) calculation. The detailed content is asfollows.
Firstly, linear iterative correction algorithm is presented for fiber image withuneven illumination. For those pixels with obvious deviations, their gray values arereplaced by the neighboring mean gray values, and the operation is iterated tillstandard deviations are converging. After the iterative calculations, the light spot onfiber image caused by point light source can be wiped off and the influence of unevenillumination is removed, while the fibers’ edges are well preserved. Such image isprepared for the succeeding processes.
Secondly, modifications to conventional Canny edge detection algorithm areproposed. A highly threshold and a low threshold for edge decision are self-adaptivelycalculated according to the distribution of fiber cross-sections. Edge length andaverage edge phase are added to distinguish fiber edges from noise during edgetracing. In addition to high efficiency, the output SNR (signal to noise ratio) of themodified Canny operator is higher than that of the conventional Canny operator.Furthermore, continuous edge output with satisfying noise performance can beachieved for different images with different fiber distribution. For low-resolution fiberimage or fine edge, Canny edge operator is unable to produce satisfying edge output.In order to resolve the problem, B-spline interpolatory edge operator is applied. Theinput image interpolation rather than Gaussian function smoothing is employed in the interpolatory edge operator, which is helpful to improve the output edges with goodcontinuity and output SNR.
Thirdly, fiber mask is calculated for separating touching fiber cross-sections andavoiding double edges effect. Painting background algorithm is put forward at first.By the algorithm, double edges during edge detection are avoided effectively andtouching fiber cross-sections are well separated. But outer pixels of edges arediscarded in the algorithm, which results in change of fiber’s characteristicparameters, such as perimeter and area. It will influence the correctness of fiberclassifying. In order to improve the practical applicability, bisection algorithm isproposed to calculate mask of fiber edge. Considering that the pixels on fiber edgesusually have smaller deviations, two thresholds are set for the deviation. Lowthreshold is used to look for pixels on fiber edges and high threshold is applied toconnect these pixels and get full fiber edge masks.
After that, fiber cross-section segmenting algorithm is presented based on themap of the shortest Euclidean distance according to the masks of fiber edges. Thedistance transform is executed with the target of the fiber edge mask set, and athreshold is set up to distinguish the lumen set from the background set. Then thedistance transform is executed with the target of lumen set for fiber edge mask set.When one fiber’s lumen is nearest for an edge pixel, and the edge pixel is connectiveto the lumen, the edge pixel is classified to the fiber. If two or more lumens areneareast for an edge pixel, it is classified to a common set. In which, when a pixel isneighboring to some fiber cross-sections, it is classified to them each. Then theskeletonization algorithm is studied for single fiber cross-section.
Afterwards, the characteristic parameters of ramie and cotton are analyzed.5chain code sum and5chain code difference are proposed to describe fibercross-sectional skeleton. Corner and concave are defined and calculated. By usingchain code to describe fiber cross-sectional skeleton,2D problem is simplified into1Dproblem and it is convenient to find fiber cross-sectional characteristics.
Finally, Kernel Principal Component Analysis (KPCA) and Support VectorMachine (SVM) are studied. By the use of KPCA, some nonlinear features ofcross-sections of fibers are quantified. Because SVM can be generalized better, theoptimal result can be achieved in theory and performance will not be reduced in caseof lacking samples or deformity of data, SVM is applied to fiber classifying. SVM istrained by100cotton cross-sections and100ramie cross-sections in advance, then it is applied to fiber classifying, and the results are analyzed.
引文
[1]周秋宝,郑今欢,吴俭俭.棉/粘、棉/Tencel混纺纱的混合比定量分析.纺织学报,2002,23（5）：50-52.
[2]邰文峰,杨伟忠,石红等.毛/粘混纺产品定量分析方法的研究.印染助剂,2006,23（5）：44-46
[3] R. L. Barker. Determination of Fiber Cross-sectional Circularity from Measurement Made in A Longitudinal View.Transactions ASME, Journal for Industry,1979,101(1):59~64
[4] J. D. Berlin. Measuring the Cross-sectional Area of Cotton Fibers with An Image Analyzer. Textile Res.J.,1981,51:109~113
[5] D. D. Thilbodeaux. Cotton Fiber Maturity by Image Analysis. Textile Res.J.,1986,56:130~139
[6] D.Robson. Cuticuar Scale Measurement Using Image Analysis Techniques. Textile Res.J.,1989,12:713~717
[7] D.Robson. Animal Fiber Analysis Using Imaging Techniques Part I:Scale Pattern Data. Textile Res.J.,1997,8:747~752
[8] D.Robson. Animal Fiber Analysis Using Imaging Techniques Part II: Addition of Scale Height Data. Textile Res.J.,2000,70(2):116~120
[9] F.H. She, X. L. Kong,, S. Nahavandi, et al. Intelligent Animal Fiber Classification with Artifical Neural Networks. TextileRes.J.,2002,61(7):371~374
[10] D. L. Kenneth, E. Coskuntuna. Distinguishing Between New and Recycled Cashmere with Fisher’s DiscriminationAnalysis. Textile Research Journal,2000,70(2):181-184
[11]李静,汪剑鸣,冷宁.织物纤维种类自动识别算法的初步研究.天津工业大学学报,2006,25(5):38-40.
[12]谢莉青,于伟东.麻/涤混纺比图像测试方法的应用研究.上海纺织科技,2002,30(6):62-64
[13]谢莉青,于伟东.混纺麻纱特征的实用图像表征技——II.麻/涤纱混合比的计算.中国麻业,2004,26(4):177-182.
[14]曾志明.用计算机快速检测山羊绒与羊毛混纺比.毛纺科技,2005(10):44-46.
[15]余序芬,吴兆平.棉麻混纺比图像处理测试系统的开发研究.中国纺织大学学报,1998,24(1):41-45
[16]徐回祥,洪安凡,王建民等.关于混纺织物中棉、苎麻纤维识别的图像处理研究.苏州丝绸工学院学报,2000,20(4):14-20.
[17] Y. Huang, B. Xu. Image Analysis for cotton fibers, Part I: Longitudinal Measurement. Textile Res.J.,2002,72(8):713-720.
[18] B.Xu. Characterizing Fiber Crimp by Image Analysis: Definitions、Algorithms and Techniques. Textile Res.J.,1992,62(2):73~80
[19] B. Xu, Y. Huang. Image Analysis for cotton fibers, Part II: Cross-Sectional Measurements. Textile Res.J.,2004,74(5):409-416
[20] Clemex Technologies Inc.. Morphology Characterization of Cotton Fibers. Clemex Image Analysis Report#135,2001.
[21] E. Hequet, B. Wyatt. Relationship Among Image Analysis on Cotton Fiber Cross Sections. AFIS Measurements and YarnQuality, the Proceedings of the Beltwide Cotton Conference,2001,2:1294-1298.
[22] B.Xu. Fiber Cross~sectional Shape Analysis Using Image Processing Techniques. Textile Res.J,1993,63(12):717~730
[23] B.Xu. Fiber Image Analysis, Part I: Fiber Image Enhancement. J.Textile Inst.,1996,87(2):274~283
[24] B. Xu, S. Wang, J. Su. Fiber Image Analysis, Part III: Autonomous Separation of Fiber Cross Sections. Journal of TextileInstitute,1999,90:288-297
[25]许鹤群,黄健.棉纤维成熟度的图像分析.中国纺织大学学报,1992,18(1):78-82
[26]进出口麻/棉混纺产品定量分析方法显微投影仪法.中华人民共和国国家出入境检验检疫局, SN/T0756-1999.
[27] Boylston EK, Hinojosa O, Hebert JJ. A quick embedding method for light and electron microscopy of textile fibers.TheBiotechnical and Histochemical Journal,1991,66(3):122-124
[28]王华辉,陈永林,胡春圃等.基于计算机图像识别的纺织纤维树脂快速包埋技术研究.中国纤检,2006,(3):16-18
[29]严晓燕,吴雄英.纤维包埋技术对单中空纤维截面特征参数的影响.西安工程科技学院学报,2005,19(3):261-264.
[30]施楣梧,裴豫明．纺织材料连续切片方法及其应用．西北纺织工学院学报,1991,20(4):101-104．
[31]严晓燕.纤维的包埋切片技术与异形纤维特征参数研究.东华大学硕士论文,2006年.
[32]宗亚宁,严晓燕,吴雄英等.树脂包埋技术在纤维截面切片中的应用.纺织学报,2007,28(2):8-10,16
[1] Nicolas A. Roddier. Atmospheric wavefront simulation using Zernike polynomials[J]. Optical Engineering,1990,29(10):1174-1180.
[2] Edwin H. Land, John J. McCann. Lightness and Retnix Theory. Journal of the Optical Society of America,1971,61(1):1-11.
[3] Edwin H. Land. The Retinex Theory of Color Vision[J].Scientific American,1977,237(6):108-128.
[4] Zia-ur Rahma, Daniel J.Jobson, Gienn A. Woodell, Retinex Processing for automatic image enhancement. Jouranl ofElectronic Imaging,2004,13(1):100-110.
[5] Steven A Coverr. Another look at Land’s Retinex algorithm. IEEE Proceednigs of Southeasteon’91, Apri1991:.351-355.
[6] John J. McCann.. Retinex at40[J]. Journal of Electronic Imaging,2004,13(1):6-7.
[7]周旋,周树道,黄峰等.基于小波变换的图像增强新算法.计算机应用,2005，25(3):606-608
[8]郝广涛,胡步发.基于DDGVFSnake和Gamma方法处理人脸光照不均.计算机应用,2007,27(4):925-928.
[9]彭国福，林正浩.图像处理中GAMMA校正的研究和实现.电子工程师,2006,32(2):30-32,36.
[10]张毓晋.图像工程（上册）——图像处理和分析（第二版）.清华大学出版社,2006年.
[11] S. N. Sharma, R. Saxena, A. Jain. FIR digital filter design with parzen and cos6(Πt) combinational window family.IEEE International Conference on Signal Processing[C]. Santorini, Greece,2002.
[12] Roark R M, Escabi M. Design of FIR filters with exceptional passband and stopband smoothness using a newtransitional window[J]. IEEE Proceedings on Circuits and Systems,2000,1:96-99.
[13]孙振球主编.医学统计学（第2版）.人民卫生出版社.2006年.
[14]杜全忠.采用不确定度评定和分析实验验差初探.大学物理实验,2006,19(4):45-51
[15] D. P. Bertsekas and J. N. Tsitsiklis. Some aspects of parallel and distributed iterative algorithms—a survey[J],Automatica (Journal of IFAC),1991,27(1):3-21.
[16]谢筱华,汪蕙.一个新的边界检测熵算子[J].信号处理,1995，11(3)：218-221.
[17] Kapur J N, Kesavan H K. Entropy optimization principle with application[M]. Academic Press, Inc,1992.
[18] Martn N F G, England J W. Mathematical theory of entropy[M]. London: Addison-Wesley Publishing company,1981.
[19]丁文锐,佟雨兵,张其善.一种无人机侦察图像质量评价模型.信号与信息处理,2007,37(3):19-21
[1]段瑞玲,李庆祥,李玉和.图像边缘检测方法研究综述.光学技术,2005，31(3):415-419.
[2]王郑耀.数字图像的边缘检测.西安交通大学学位论文,2003年
[3] J. Canny. A Computational Approach to Edge Detection. IEEE Transactions on PAMI, November1986,8(6):679-698.
[4] J. Canny. Finding edges and lines in images. MIT Master's Thesis,1983.
[5]周晓明,马秋禾,肖蓉等.一种改进的Canny算子边缘检测算法.测绘工程,2008,17(1):28-31
[6]张斌,贺赛先.基于Canny算子的边缘提取改善方法.红外技术,2006,28(3):165-169.
[7]张小红,杨丹,刘亚威.基于Canny算子的改进型边缘检测算法.计算机工程与应用,2003,39(29):113-115.
[8]万力,易昂,傅明.一种基于Canny算法的边缘提取改善方法.计算技术与自动化,2003,22(1):24-26.
[9]余洪山,王耀南.一种改进型Canny边缘检测算法.计算机工程与应用,2004,40(20):27-29.
[10]杨振亚,白治江,王成道.自适应Canny边缘检测算法.上海海运学院学报,2003,24(4):373-377.
[11] P.F. Zeng, and T. Hirata. Interpolatory Edge Detection. Machine Graphics&Vision,2001,10(2):175-184.
[12] M. Unser, A. Aldroubi, and M. Eden. Fast B-spline transforms for continuous image representation and interpolation.IEEE Transactions on PAMI, March1991,13:277-285.
[13] M. Unser, A. Aldroubi, and M. Eden. B-Spline signal processing: Part II-Efficient design and applications. IEEETransactions on Signal Processing, February1993,41:834-848.
[14] P. Thevenaz, T. Blu, M. Unser. Interpolation Revisited. IEEE Transactions on Medical Imaging,2000,19(7):739-758.
[15]李开宇,张焕春,经亚枝.基于数字滤波的B-样条插值法在图像旋转中的应用.南京航空航天大学学报,2004,36(5):633-638
[16] M. Unser, A. Aldroubi, and M. Eden. B-Spline signal processing: Part I–Theory. IEEE Transactions on SignalProcessing, February1993,41:821-833.
[17]宗亚宁,严晓燕,吴雄英等.树脂包埋技术在纤维截面切片中的应用.纺织学报,2007,28(2):8-10,16
[18]王华辉,陈永林,胡苗圃等.基于计算机图像识别的纺织纤维树脂快速包埋技术研究.中国纤检,2006,(3):16-18
[19]严晓燕,吴雄英.纤维包埋技术对单中空纤维截面特征参数的影响.西安工程科技学院院报,2005,19(3):261-264
[20] E. K. Boylston, J. P. Evans, D. P. Thibodeaux. A Quick Embedding Method for Light Microscopy and Image Analysis ofCotton Fibers. Biotechnic&Histochemistry,1995,70(1):24-27
[21]严晓燕.纤维的包埋切片技术与异形纤维特征参数研究.东华大学硕士论文,2006年.
[22]刘雁雁,高春鹏,高铭等.纤维横截面切片技术改进.纺织科技进展,2006,(5):84-86
[23] The Textile Institute Manchester. Identification of Textile Materials. London: Manara Printing Services,1985
[24]刘常威,李青山.显微镜法鉴别纤维的评述．上海纺织科技,2004,30(2):61-62
[25] Geoff R Newman, Jan A Hobot．Resins for Combined Light and Electron microscopy: A Half Century of Development.The Histochemical Journal,1999,(31):495-505
[26]李克友,张菊华,向福如.高分子合成原理及工艺学.北京:科学出版社,1999年
[27]沈伟,杨海贤,管云林等.非生物标本的电镜样品制备及超切技术的探讨.天津医科大学学报,2002,8(4):411-412,415
[28]李正理.植物制片技术.北京:科学出版社,1987年
[29]宗亚宁.棉麻纤维图像分析及自动检测技术的研究.东华大学博士论文,2006年.
[30] E. Davies. Machine Vision. Academic Press,1990:91-96.
[31] R. Gonzales and R. Woods. Digital Image Processing. New York: Addison-Wesley Publishing Company,1992:443-452.
[32] A. Jain. Fundamentals of Digital Image Processing. Prentice-Hall,1986:408.
[33] Gonzalez Rafael C., Woods Richard E.. Digital Image Processing Second Edition.北京:电子工业出版社,2005年.
[34] Gonzalez Rafael C., Woods Richard E., Eddins Steven L.. Digital Image Processing Using MATLAB.北京:电子工业出版社,2006年.
[35]刘万春,刘建君,朱玉文等.一种实时高速的八连通区域填充算法.计算机应用研究,2006,(6):177-179
[36] Haralick R. M., Shapiro L. G.. SURVEY: Image Segmentation Techniques. Computer Vision, Graphics, and ImageProcessing,1985,29(1):100-132.
[37] Pal N. R., Pal S. K.. A Review on Image Segmentation Techniques. Pattern Recognition,1993,26(9):1277-1294.
[38] Zhang Y. J.. A Survey on Evaluation Methods for Image Segmentation. Pattern Recognition,1996,29(8):1335-1346.
[39]罗希平,田捷.图像分割方法综述.模式识别与人工智,1999,12(3):300-312.
[40]魏弘博,吕振肃,蒋田仔等.图像分割技术纵览.甘肃科学学报,2004,16(2):19-24.
[41]张新峰,沈兰荪.图像分割技术研究.电路与系统学报,2004,9(2):92-99.
[42]王爱民,沈兰荪.图像分割研究综述.测控技术,2000,19(5):1-5.
[43] B. Xu, Wang, S. and Su, J.. Fiber Image Analysis, Part III: Autonomous Separation of Fiber Cross Sections. Journal ofTextile Institute,1999,90(3):288-297.
[44] G. Borgefors. Distance transformations in digital images. Comput. Vision, Graphics, Image Processing,1986,34:334-371.
[45] Cecilia Di Ruberto, Andrew Dempster, Shahid Khan, et al. Analysis of infected blood cell images using morphologicaloperators. Image and Vision Computing,2002,20:133-146.
[46]游迎荣,范影乐,庞全.基于距离变换的粘连细胞分割方法.计算机工程与应用,2005，41(20)：206-208.
[47] Luc Vincent, Pierre Soille. Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations. IEEETransactions on Pattern Analysis and Machine Intelligence,1991,13:583-595.
[48]魏瑾,韩斌,张其亮.粘连蚕卵图像分离算法研究.江苏科技大学学报（自然科学版）,2006,20(1)：46-50.
[49]冯林,管慧娟,孙焘等.基于分水岭变换和核聚类算法的图像分割.大连理工大学学报,2006,46(6):851-856
[50] A. Rosenfeld, J.L. Pfalz. Sequential operations in digital picture processing. Journal of the Association for ComputingMachinery,1966,13:471-494.
[51] A. Rosenfeld, J.L. Pfalz. Distance functions on digital pictures. Pattern Recognition,1968,1:33-61.
[52] F. de Assis Zampirolli, R. De Alencar Lotufo. Classification of the Distance Transformation Algorithms under theMathematical Morphology Approach. XIII Brizilian Symposium on Computer Graphics and Image Processing(SIBGRAPI'00),17October2000to20October2000.
[53] Gonzalez Rafael C., Woods Richard E.. Digital Image Processing Second Edition.北京:电子工业出版社,2005年.
[54] Gonzalez Rafael C., Woods Richard E.. Eddins Steven L. Digital Image Processing Using MATLAB.北京:电子工业出版社,2006年.
[55]陈晓飞,王润生.基于非脊点下降算子的多尺度骨架算法.软件学报,2003，21(14)：89-93
[56] Blum H.. A transformation for extracting new descriptors of shape. Models for the Perception of Speech and Visual Form,l967,45(18):67-70
[57] Kimmel R., Shaked D., Kiryati D., et al. Skeletonization via distance maps and level sets. Computer Vision and ImageUnderstanding,1995,62(3):382-391
[58] Ivanov D., Kuzmin E. and Burtsev S.. An Efficient Integer-based skeletonization Algorithm. Computers&Graphics,2000,24(1):41-51
[59] Alexa M., Cohen D. and Levin D.. As-rigid-as-possible shape morphing. In Computer Graphics Proceedings AnnualConference Series, ACM SIGGRAPH, New Orleans,2000,3(12):157-164
[60] Blum H.. Biological Shape and Visual Science (Part I). Journal of Theoretical Biology,1973,38:205–287.
[61] A. Rosenfeld, J.L. Pfalz. Sequential operations in digital picture processing. Journal of the Association for ComputingMachinery,1966,13:471-494.
[62] P.-E. Danielsson. Euclidean Distance Mapping. Computer Vision, Graphics, and Image Understanding,1980,14:227-248
[63] C. Arcelli and G. Sanniti Di Baja. A Width-Independent Fast Thinning Algorithm. IEEE Trans. Pattern Analysis andMachine Intelligence,1985,7(4):463-474
[64] F. Meyer. Digital Euclidean Skeletons. Proc. SPIE Visual Comm. and Image Processing,1990,1360:251-262
[65] C.W. fiiblack, P. E. Gibbons, and D. W. Capson. Generating Skeletons and Centerlines from the Distance Transform.CVGIP: Graphical Models and Image Processing,1992,54(5):420-437
[66] H. Talbot and L. Vincent. Euclidean Skeletons and Conditional Bisectors. Proc. SPIE Visual Comm. and imageProcessing’92,1992,1818:862-876
[67] C. Arcelli and G. Sanniti Di Baja. Finding Local Maxima in a Pseudo-Euclidean Distance Transform. ComputerVision, Graphics, and Image Processing,1988,43:361-367
[68] C. Arcelli and G. Sanniti Di Baja. Euclidean Skeleton vis Centre-of-Maximal-Disc Extraction. Image and VisionComputing,1993,11(3):163-173
[69]张立科.数字图像处理典型算法及实现.人民邮电出版社,2006年
[70] F. Y. Shih, C.C. PU. A Skeletonization Algorithm By Maxima Tracking On Euclidean Distance Transform. PatternRecognition,1995,28(3):331-341
[71] Yaorong Ge and J. Michael Fitzpatrick. On the Generation of Skeletons from Discrete Euclidean Distance Maps. IEEETransactions On Pattern Analysis And Machine Intelligence,1996,18(11):1055-1066
[1]姚明.基于B/S架构天然纤维识别系统的研究.东华大学硕士学位论文,2005年.
[2]宗亚宁.棉麻纤维图像分析及自动检测技术的研究.东华大学博士论文,2006年.
[3]于伟东,谢莉青.混纺麻纱特征的实用图像表征技术——I.截面图像生成与特征指标.中国麻业,2004，26（3）：127-132
[4] H. Freeman. On the encoding of arbitrary geometric configurations. IRE Trans Electronics and Computers,1961.16:260-268
[5] E. Bribiesca. A geometric structure for two-dimensional shapes and three-dimensional surfaces. Pattern Recognition,1992,25(5):483-496
[6] E. Bribiesca A new chain code. Pattern Recognition,1999,32(2):235-251
[7]陆宗骐,童韬．链码和在边界形状分析中的应用[J]．中国图象图形学报,2002,7(12):1323-1328.
[8]唐振军,张显全．图像边界的链码表示研究[J]．微计算机信息,2005,21(3):105-107.
[9]陆宗骐,张秋萍．工程图纸矢量化中平均链码与线条轮廓跟踪[J]．模式识别与人工智能,1997，10（2）：147-152.
[10]李素敏.基于n链码的纤维特征参数提取算法的实现.东华大学硕士学位论文,2008年.
[11]姚明,曾培峰,禹素萍等．显微图像分辨率对图像保真度的影响[J]．东华大学学报,2007,33(1):101-107.
[12]徐建华.图像处理与分析[M]，北京：科学出版社,1992年
[13] H. Freeman and L. S. Davis. A Corner-Finding Algorithm for Chain-Coded Curves. IEEE Trans. On Computers,1977：297-303
[14]曹亮吉．怎么说它有多弯？科学月刊第十六卷第八期
[15]陆宗骐．C/C++图像处理编程．清华大学出版社,2005年
[16]孙振球主编.医学统计学（第2版）.人民卫生出版社,2006年.
[1] Haykin S.. Neural Networks: A Comprehensive Foundation. Second Edition. New Jersey: Prentice Hall,1999,25-68
[2]赵丽红.人脸检测和识别算法的研究与实现.东北大学博士学位论文,2006年
[3] K.–R. Muller, S. Mika, G. Ratsch, et al. An Introduce to Kernal-Based Learning Algoritnms. IEEE Transactions on NeuralNetworks,2001,12(2):181-201
[4] B. Scholkopf, S. Mika, C.J.C. Burges, et al. Input Space vs. Feature Space in Kernal-Based Mothods. I EEE Transactionson Neural Networks,1999,10(5):1000-1017
[5] B. Scholkopf, A. Smola, K.-R. Muller. Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Technical ReportNo.44. Max-Planck-Institute for Biological Cybernetics, Tubingen, Germany,1996,10(5):1299-1319
[6]吴成东,樊玉泉,张云周等.基于改进KPCA算法的车牌字符识别方法.东北大学学报（自然科学版）,2008,29(5):629-632
[7]肖健华,吴今培.基于核的特征提取技术及应用研究.计算机工程,2002,28(10):36-38
[8]袁立,穆志纯,刘磊明.基于核主元分析法和支持向量机的人耳识别.北京科技大学学报,2006,28(9):890-895
[9] Vapnik V. N.. Estimation of Dependencies Based on Empirical Data. Berlin: Springer-Verlag,1982.
[10] Cherkassky V., Mulier F.. Learning from Data: Concepts Theory and Methods. NY: John Wiley&Sons,1997.
[11] Vapnik V. N.. The Nature of Statistical Learning Theory. NY: Springer-Verlag,1995.
[12] Boser B., Guyon I. and Vapnik V. N.. A training algorithm for optimal margin classifiers. Fifth Annual Workshop onComputational Learning Theory, Pittsburgh: ACM Press,1992.
[13] Cortes C. and Vapnik V. N.. Support vector networks. Machine Learning,1995,20(30):273-297.
[14]张学工.关于统计学习理论与支持向量机.自动化学报,2000,26（1）:32-42.
[15] C.J.C. Burges. A tutorial support vector decision rules. In Intl. Conf. on Machine Learning,1996,71-77.
[16] Cristianini，N.. Support vector and kernel machines. Technical report, Intl. Conf. Machine Learning,2001.
[17] B. Scholkopf，C.J.C. Bruges，and A.J. Smola, et al. Advances in Kernel Methods Support Vector Learning. MIT Press,Cambridge, MA,1997.
[18]边肇祺等.模式识别.北京:清华大学出版社,1988年.
[19]焦李成,张莉,周伟达.支撑矢量预选取的中心距离比值法.电子学报,2001,29(3)：383-386.
[20]焦李成,屈炳云,周伟达.一种基于支撑矢量机的多用户检测算法.电子学报,2002,30(10)：1549-1551.
[21]梁路宏,艾海舟,肖习攀等.基于模板匹配与支持矢量机的人脸检测.计算机学报,2002,25(1)：.22-29.
[22]张艳宁,赵荣椿,梁怡.一种有效的大规模数据的分类方法.电子学报,2002,30(l0)：1533-1535.
[23] Nello Cristianini and John Shawe-Taylor著.李国正,王猛,曾华军译.支持向量机导论.北京:电子工业出版社,2004年.
[24]杜树新,吴铁军.模式识别中的支持向量机方法.浙江大学学报（工学版）,2003,37(5):521-527.
[25] Hsu C. W., Chang C. C. and Lin C. J.. A Practical Guide to Support Vector Classification. http://www.csie.ntu.edu.tw/～cjlin, Last updated: July18,2007.
[26]肖健华,吴今培.基于核的特征提取技术及应用研究.计算机研究,2002,28(10):36-38.
[2]邰文峰,杨伟忠,石红等.毛/粘混纺产品定量分析方法的研究.印染助剂,2006,23（5）：44-46
[3] R. L. Barker. Determination of Fiber Cross-sectional Circularity from Measurement Made in A Longitudinal View.Transactions ASME, Journal for Industry,1979,101(1):59~64
[4] J. D. Berlin. Measuring the Cross-sectional Area of Cotton Fibers with An Image Analyzer. Textile Res.J.,1981,51:109~113
[5] D. D. Thilbodeaux. Cotton Fiber Maturity by Image Analysis. Textile Res.J.,1986,56:130~139
[6] D.Robson. Cuticuar Scale Measurement Using Image Analysis Techniques. Textile Res.J.,1989,12:713~717
[7] D.Robson. Animal Fiber Analysis Using Imaging Techniques Part I:Scale Pattern Data. Textile Res.J.,1997,8:747~752
[8] D.Robson. Animal Fiber Analysis Using Imaging Techniques Part II: Addition of Scale Height Data. Textile Res.J.,2000,70(2):116~120
[9] F.H. She, X. L. Kong,, S. Nahavandi, et al. Intelligent Animal Fiber Classification with Artifical Neural Networks. TextileRes.J.,2002,61(7):371~374
[10] D. L. Kenneth, E. Coskuntuna. Distinguishing Between New and Recycled Cashmere with Fisher’s DiscriminationAnalysis. Textile Research Journal,2000,70(2):181-184
[11]李静,汪剑鸣,冷宁.织物纤维种类自动识别算法的初步研究.天津工业大学学报,2006,25(5):38-40.
[12]谢莉青,于伟东.麻/涤混纺比图像测试方法的应用研究.上海纺织科技,2002,30(6):62-64
[13]谢莉青,于伟东.混纺麻纱特征的实用图像表征技——II.麻/涤纱混合比的计算.中国麻业,2004,26(4):177-182.
[14]曾志明.用计算机快速检测山羊绒与羊毛混纺比.毛纺科技,2005(10):44-46.
[15]余序芬,吴兆平.棉麻混纺比图像处理测试系统的开发研究.中国纺织大学学报,1998,24(1):41-45
[16]徐回祥,洪安凡,王建民等.关于混纺织物中棉、苎麻纤维识别的图像处理研究.苏州丝绸工学院学报,2000,20(4):14-20.
[17] Y. Huang, B. Xu. Image Analysis for cotton fibers, Part I: Longitudinal Measurement. Textile Res.J.,2002,72(8):713-720.
[18] B.Xu. Characterizing Fiber Crimp by Image Analysis: Definitions、Algorithms and Techniques. Textile Res.J.,1992,62(2):73~80
[19] B. Xu, Y. Huang. Image Analysis for cotton fibers, Part II: Cross-Sectional Measurements. Textile Res.J.,2004,74(5):409-416
[20] Clemex Technologies Inc.. Morphology Characterization of Cotton Fibers. Clemex Image Analysis Report#135,2001.
[21] E. Hequet, B. Wyatt. Relationship Among Image Analysis on Cotton Fiber Cross Sections. AFIS Measurements and YarnQuality, the Proceedings of the Beltwide Cotton Conference,2001,2:1294-1298.
[22] B.Xu. Fiber Cross~sectional Shape Analysis Using Image Processing Techniques. Textile Res.J,1993,63(12):717~730
[23] B.Xu. Fiber Image Analysis, Part I: Fiber Image Enhancement. J.Textile Inst.,1996,87(2):274~283
[24] B. Xu, S. Wang, J. Su. Fiber Image Analysis, Part III: Autonomous Separation of Fiber Cross Sections. Journal of TextileInstitute,1999,90:288-297
[25]许鹤群,黄健.棉纤维成熟度的图像分析.中国纺织大学学报,1992,18(1):78-82
[26]进出口麻/棉混纺产品定量分析方法显微投影仪法.中华人民共和国国家出入境检验检疫局, SN/T0756-1999.
[27] Boylston EK, Hinojosa O, Hebert JJ. A quick embedding method for light and electron microscopy of textile fibers.TheBiotechnical and Histochemical Journal,1991,66(3):122-124
[28]王华辉,陈永林,胡春圃等.基于计算机图像识别的纺织纤维树脂快速包埋技术研究.中国纤检,2006,(3):16-18
[29]严晓燕,吴雄英.纤维包埋技术对单中空纤维截面特征参数的影响.西安工程科技学院学报,2005,19(3):261-264.
[30]施楣梧,裴豫明．纺织材料连续切片方法及其应用．西北纺织工学院学报,1991,20(4):101-104．
[31]严晓燕.纤维的包埋切片技术与异形纤维特征参数研究.东华大学硕士论文,2006年.
[32]宗亚宁,严晓燕,吴雄英等.树脂包埋技术在纤维截面切片中的应用.纺织学报,2007,28(2):8-10,16
[1] Nicolas A. Roddier. Atmospheric wavefront simulation using Zernike polynomials[J]. Optical Engineering,1990,29(10):1174-1180.
[2] Edwin H. Land, John J. McCann. Lightness and Retnix Theory. Journal of the Optical Society of America,1971,61(1):1-11.
[3] Edwin H. Land. The Retinex Theory of Color Vision[J].Scientific American,1977,237(6):108-128.
[4] Zia-ur Rahma, Daniel J.Jobson, Gienn A. Woodell, Retinex Processing for automatic image enhancement. Jouranl ofElectronic Imaging,2004,13(1):100-110.
[5] Steven A Coverr. Another look at Land’s Retinex algorithm. IEEE Proceednigs of Southeasteon’91, Apri1991:.351-355.
[6] John J. McCann.. Retinex at40[J]. Journal of Electronic Imaging,2004,13(1):6-7.
[7]周旋,周树道,黄峰等.基于小波变换的图像增强新算法.计算机应用,2005，25(3):606-608
[8]郝广涛,胡步发.基于DDGVFSnake和Gamma方法处理人脸光照不均.计算机应用,2007,27(4):925-928.
[9]彭国福，林正浩.图像处理中GAMMA校正的研究和实现.电子工程师,2006,32(2):30-32,36.
[10]张毓晋.图像工程（上册）——图像处理和分析（第二版）.清华大学出版社,2006年.
[11] S. N. Sharma, R. Saxena, A. Jain. FIR digital filter design with parzen and cos6(Πt) combinational window family.IEEE International Conference on Signal Processing[C]. Santorini, Greece,2002.
[12] Roark R M, Escabi M. Design of FIR filters with exceptional passband and stopband smoothness using a newtransitional window[J]. IEEE Proceedings on Circuits and Systems,2000,1:96-99.
[13]孙振球主编.医学统计学（第2版）.人民卫生出版社.2006年.
[14]杜全忠.采用不确定度评定和分析实验验差初探.大学物理实验,2006,19(4):45-51
[15] D. P. Bertsekas and J. N. Tsitsiklis. Some aspects of parallel and distributed iterative algorithms—a survey[J],Automatica (Journal of IFAC),1991,27(1):3-21.
[16]谢筱华,汪蕙.一个新的边界检测熵算子[J].信号处理,1995，11(3)：218-221.
[17] Kapur J N, Kesavan H K. Entropy optimization principle with application[M]. Academic Press, Inc,1992.
[18] Martn N F G, England J W. Mathematical theory of entropy[M]. London: Addison-Wesley Publishing company,1981.
[19]丁文锐,佟雨兵,张其善.一种无人机侦察图像质量评价模型.信号与信息处理,2007,37(3):19-21
[1]段瑞玲,李庆祥,李玉和.图像边缘检测方法研究综述.光学技术,2005，31(3):415-419.
[2]王郑耀.数字图像的边缘检测.西安交通大学学位论文,2003年
[3] J. Canny. A Computational Approach to Edge Detection. IEEE Transactions on PAMI, November1986,8(6):679-698.
[4] J. Canny. Finding edges and lines in images. MIT Master's Thesis,1983.
[5]周晓明,马秋禾,肖蓉等.一种改进的Canny算子边缘检测算法.测绘工程,2008,17(1):28-31
[6]张斌,贺赛先.基于Canny算子的边缘提取改善方法.红外技术,2006,28(3):165-169.
[7]张小红,杨丹,刘亚威.基于Canny算子的改进型边缘检测算法.计算机工程与应用,2003,39(29):113-115.
[8]万力,易昂,傅明.一种基于Canny算法的边缘提取改善方法.计算技术与自动化,2003,22(1):24-26.
[9]余洪山,王耀南.一种改进型Canny边缘检测算法.计算机工程与应用,2004,40(20):27-29.
[10]杨振亚,白治江,王成道.自适应Canny边缘检测算法.上海海运学院学报,2003,24(4):373-377.
[11] P.F. Zeng, and T. Hirata. Interpolatory Edge Detection. Machine Graphics&Vision,2001,10(2):175-184.
[12] M. Unser, A. Aldroubi, and M. Eden. Fast B-spline transforms for continuous image representation and interpolation.IEEE Transactions on PAMI, March1991,13:277-285.
[13] M. Unser, A. Aldroubi, and M. Eden. B-Spline signal processing: Part II-Efficient design and applications. IEEETransactions on Signal Processing, February1993,41:834-848.
[14] P. Thevenaz, T. Blu, M. Unser. Interpolation Revisited. IEEE Transactions on Medical Imaging,2000,19(7):739-758.
[15]李开宇,张焕春,经亚枝.基于数字滤波的B-样条插值法在图像旋转中的应用.南京航空航天大学学报,2004,36(5):633-638
[16] M. Unser, A. Aldroubi, and M. Eden. B-Spline signal processing: Part I–Theory. IEEE Transactions on SignalProcessing, February1993,41:821-833.
[17]宗亚宁,严晓燕,吴雄英等.树脂包埋技术在纤维截面切片中的应用.纺织学报,2007,28(2):8-10,16
[18]王华辉,陈永林,胡苗圃等.基于计算机图像识别的纺织纤维树脂快速包埋技术研究.中国纤检,2006,(3):16-18
[19]严晓燕,吴雄英.纤维包埋技术对单中空纤维截面特征参数的影响.西安工程科技学院院报,2005,19(3):261-264
[20] E. K. Boylston, J. P. Evans, D. P. Thibodeaux. A Quick Embedding Method for Light Microscopy and Image Analysis ofCotton Fibers. Biotechnic&Histochemistry,1995,70(1):24-27
[21]严晓燕.纤维的包埋切片技术与异形纤维特征参数研究.东华大学硕士论文,2006年.
[22]刘雁雁,高春鹏,高铭等.纤维横截面切片技术改进.纺织科技进展,2006,(5):84-86
[23] The Textile Institute Manchester. Identification of Textile Materials. London: Manara Printing Services,1985
[24]刘常威,李青山.显微镜法鉴别纤维的评述．上海纺织科技,2004,30(2):61-62
[25] Geoff R Newman, Jan A Hobot．Resins for Combined Light and Electron microscopy: A Half Century of Development.The Histochemical Journal,1999,(31):495-505
[26]李克友,张菊华,向福如.高分子合成原理及工艺学.北京:科学出版社,1999年
[27]沈伟,杨海贤,管云林等.非生物标本的电镜样品制备及超切技术的探讨.天津医科大学学报,2002,8(4):411-412,415
[28]李正理.植物制片技术.北京:科学出版社,1987年
[29]宗亚宁.棉麻纤维图像分析及自动检测技术的研究.东华大学博士论文,2006年.
[30] E. Davies. Machine Vision. Academic Press,1990:91-96.
[31] R. Gonzales and R. Woods. Digital Image Processing. New York: Addison-Wesley Publishing Company,1992:443-452.
[32] A. Jain. Fundamentals of Digital Image Processing. Prentice-Hall,1986:408.
[33] Gonzalez Rafael C., Woods Richard E.. Digital Image Processing Second Edition.北京:电子工业出版社,2005年.
[34] Gonzalez Rafael C., Woods Richard E., Eddins Steven L.. Digital Image Processing Using MATLAB.北京:电子工业出版社,2006年.
[35]刘万春,刘建君,朱玉文等.一种实时高速的八连通区域填充算法.计算机应用研究,2006,(6):177-179
[36] Haralick R. M., Shapiro L. G.. SURVEY: Image Segmentation Techniques. Computer Vision, Graphics, and ImageProcessing,1985,29(1):100-132.
[37] Pal N. R., Pal S. K.. A Review on Image Segmentation Techniques. Pattern Recognition,1993,26(9):1277-1294.
[38] Zhang Y. J.. A Survey on Evaluation Methods for Image Segmentation. Pattern Recognition,1996,29(8):1335-1346.
[39]罗希平,田捷.图像分割方法综述.模式识别与人工智,1999,12(3):300-312.
[40]魏弘博,吕振肃,蒋田仔等.图像分割技术纵览.甘肃科学学报,2004,16(2):19-24.
[41]张新峰,沈兰荪.图像分割技术研究.电路与系统学报,2004,9(2):92-99.
[42]王爱民,沈兰荪.图像分割研究综述.测控技术,2000,19(5):1-5.
[43] B. Xu, Wang, S. and Su, J.. Fiber Image Analysis, Part III: Autonomous Separation of Fiber Cross Sections. Journal ofTextile Institute,1999,90(3):288-297.
[44] G. Borgefors. Distance transformations in digital images. Comput. Vision, Graphics, Image Processing,1986,34:334-371.
[45] Cecilia Di Ruberto, Andrew Dempster, Shahid Khan, et al. Analysis of infected blood cell images using morphologicaloperators. Image and Vision Computing,2002,20:133-146.
[46]游迎荣,范影乐,庞全.基于距离变换的粘连细胞分割方法.计算机工程与应用,2005，41(20)：206-208.
[47] Luc Vincent, Pierre Soille. Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations. IEEETransactions on Pattern Analysis and Machine Intelligence,1991,13:583-595.
[48]魏瑾,韩斌,张其亮.粘连蚕卵图像分离算法研究.江苏科技大学学报（自然科学版）,2006,20(1)：46-50.
[49]冯林,管慧娟,孙焘等.基于分水岭变换和核聚类算法的图像分割.大连理工大学学报,2006,46(6):851-856
[50] A. Rosenfeld, J.L. Pfalz. Sequential operations in digital picture processing. Journal of the Association for ComputingMachinery,1966,13:471-494.
[51] A. Rosenfeld, J.L. Pfalz. Distance functions on digital pictures. Pattern Recognition,1968,1:33-61.
[52] F. de Assis Zampirolli, R. De Alencar Lotufo. Classification of the Distance Transformation Algorithms under theMathematical Morphology Approach. XIII Brizilian Symposium on Computer Graphics and Image Processing(SIBGRAPI'00),17October2000to20October2000.
[53] Gonzalez Rafael C., Woods Richard E.. Digital Image Processing Second Edition.北京:电子工业出版社,2005年.
[54] Gonzalez Rafael C., Woods Richard E.. Eddins Steven L. Digital Image Processing Using MATLAB.北京:电子工业出版社,2006年.
[55]陈晓飞,王润生.基于非脊点下降算子的多尺度骨架算法.软件学报,2003，21(14)：89-93
[56] Blum H.. A transformation for extracting new descriptors of shape. Models for the Perception of Speech and Visual Form,l967,45(18):67-70
[57] Kimmel R., Shaked D., Kiryati D., et al. Skeletonization via distance maps and level sets. Computer Vision and ImageUnderstanding,1995,62(3):382-391
[58] Ivanov D., Kuzmin E. and Burtsev S.. An Efficient Integer-based skeletonization Algorithm. Computers&Graphics,2000,24(1):41-51
[59] Alexa M., Cohen D. and Levin D.. As-rigid-as-possible shape morphing. In Computer Graphics Proceedings AnnualConference Series, ACM SIGGRAPH, New Orleans,2000,3(12):157-164
[60] Blum H.. Biological Shape and Visual Science (Part I). Journal of Theoretical Biology,1973,38:205–287.
[61] A. Rosenfeld, J.L. Pfalz. Sequential operations in digital picture processing. Journal of the Association for ComputingMachinery,1966,13:471-494.
[62] P.-E. Danielsson. Euclidean Distance Mapping. Computer Vision, Graphics, and Image Understanding,1980,14:227-248
[63] C. Arcelli and G. Sanniti Di Baja. A Width-Independent Fast Thinning Algorithm. IEEE Trans. Pattern Analysis andMachine Intelligence,1985,7(4):463-474
[64] F. Meyer. Digital Euclidean Skeletons. Proc. SPIE Visual Comm. and Image Processing,1990,1360:251-262
[65] C.W. fiiblack, P. E. Gibbons, and D. W. Capson. Generating Skeletons and Centerlines from the Distance Transform.CVGIP: Graphical Models and Image Processing,1992,54(5):420-437
[66] H. Talbot and L. Vincent. Euclidean Skeletons and Conditional Bisectors. Proc. SPIE Visual Comm. and imageProcessing’92,1992,1818:862-876
[67] C. Arcelli and G. Sanniti Di Baja. Finding Local Maxima in a Pseudo-Euclidean Distance Transform. ComputerVision, Graphics, and Image Processing,1988,43:361-367
[68] C. Arcelli and G. Sanniti Di Baja. Euclidean Skeleton vis Centre-of-Maximal-Disc Extraction. Image and VisionComputing,1993,11(3):163-173
[69]张立科.数字图像处理典型算法及实现.人民邮电出版社,2006年
[70] F. Y. Shih, C.C. PU. A Skeletonization Algorithm By Maxima Tracking On Euclidean Distance Transform. PatternRecognition,1995,28(3):331-341
[71] Yaorong Ge and J. Michael Fitzpatrick. On the Generation of Skeletons from Discrete Euclidean Distance Maps. IEEETransactions On Pattern Analysis And Machine Intelligence,1996,18(11):1055-1066
[1]姚明.基于B/S架构天然纤维识别系统的研究.东华大学硕士学位论文,2005年.
[2]宗亚宁.棉麻纤维图像分析及自动检测技术的研究.东华大学博士论文,2006年.
[3]于伟东,谢莉青.混纺麻纱特征的实用图像表征技术——I.截面图像生成与特征指标.中国麻业,2004，26（3）：127-132
[4] H. Freeman. On the encoding of arbitrary geometric configurations. IRE Trans Electronics and Computers,1961.16:260-268
[5] E. Bribiesca. A geometric structure for two-dimensional shapes and three-dimensional surfaces. Pattern Recognition,1992,25(5):483-496
[6] E. Bribiesca A new chain code. Pattern Recognition,1999,32(2):235-251
[7]陆宗骐,童韬．链码和在边界形状分析中的应用[J]．中国图象图形学报,2002,7(12):1323-1328.
[8]唐振军,张显全．图像边界的链码表示研究[J]．微计算机信息,2005,21(3):105-107.
[9]陆宗骐,张秋萍．工程图纸矢量化中平均链码与线条轮廓跟踪[J]．模式识别与人工智能,1997，10（2）：147-152.
[10]李素敏.基于n链码的纤维特征参数提取算法的实现.东华大学硕士学位论文,2008年.
[11]姚明,曾培峰,禹素萍等．显微图像分辨率对图像保真度的影响[J]．东华大学学报,2007,33(1):101-107.
[12]徐建华.图像处理与分析[M]，北京：科学出版社,1992年
[13] H. Freeman and L. S. Davis. A Corner-Finding Algorithm for Chain-Coded Curves. IEEE Trans. On Computers,1977：297-303
[14]曹亮吉．怎么说它有多弯？科学月刊第十六卷第八期
[15]陆宗骐．C/C++图像处理编程．清华大学出版社,2005年
[16]孙振球主编.医学统计学（第2版）.人民卫生出版社,2006年.
[1] Haykin S.. Neural Networks: A Comprehensive Foundation. Second Edition. New Jersey: Prentice Hall,1999,25-68
[2]赵丽红.人脸检测和识别算法的研究与实现.东北大学博士学位论文,2006年
[3] K.–R. Muller, S. Mika, G. Ratsch, et al. An Introduce to Kernal-Based Learning Algoritnms. IEEE Transactions on NeuralNetworks,2001,12(2):181-201
[4] B. Scholkopf, S. Mika, C.J.C. Burges, et al. Input Space vs. Feature Space in Kernal-Based Mothods. I EEE Transactionson Neural Networks,1999,10(5):1000-1017
[5] B. Scholkopf, A. Smola, K.-R. Muller. Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Technical ReportNo.44. Max-Planck-Institute for Biological Cybernetics, Tubingen, Germany,1996,10(5):1299-1319
[6]吴成东,樊玉泉,张云周等.基于改进KPCA算法的车牌字符识别方法.东北大学学报（自然科学版）,2008,29(5):629-632
[7]肖健华,吴今培.基于核的特征提取技术及应用研究.计算机工程,2002,28(10):36-38
[8]袁立,穆志纯,刘磊明.基于核主元分析法和支持向量机的人耳识别.北京科技大学学报,2006,28(9):890-895
[9] Vapnik V. N.. Estimation of Dependencies Based on Empirical Data. Berlin: Springer-Verlag,1982.
[10] Cherkassky V., Mulier F.. Learning from Data: Concepts Theory and Methods. NY: John Wiley&Sons,1997.
[11] Vapnik V. N.. The Nature of Statistical Learning Theory. NY: Springer-Verlag,1995.
[12] Boser B., Guyon I. and Vapnik V. N.. A training algorithm for optimal margin classifiers. Fifth Annual Workshop onComputational Learning Theory, Pittsburgh: ACM Press,1992.
[13] Cortes C. and Vapnik V. N.. Support vector networks. Machine Learning,1995,20(30):273-297.
[14]张学工.关于统计学习理论与支持向量机.自动化学报,2000,26（1）:32-42.
[15] C.J.C. Burges. A tutorial support vector decision rules. In Intl. Conf. on Machine Learning,1996,71-77.
[16] Cristianini，N.. Support vector and kernel machines. Technical report, Intl. Conf. Machine Learning,2001.
[17] B. Scholkopf，C.J.C. Bruges，and A.J. Smola, et al. Advances in Kernel Methods Support Vector Learning. MIT Press,Cambridge, MA,1997.
[18]边肇祺等.模式识别.北京:清华大学出版社,1988年.
[19]焦李成,张莉,周伟达.支撑矢量预选取的中心距离比值法.电子学报,2001,29(3)：383-386.
[20]焦李成,屈炳云,周伟达.一种基于支撑矢量机的多用户检测算法.电子学报,2002,30(10)：1549-1551.
[21]梁路宏,艾海舟,肖习攀等.基于模板匹配与支持矢量机的人脸检测.计算机学报,2002,25(1)：.22-29.
[22]张艳宁,赵荣椿,梁怡.一种有效的大规模数据的分类方法.电子学报,2002,30(l0)：1533-1535.
[23] Nello Cristianini and John Shawe-Taylor著.李国正,王猛,曾华军译.支持向量机导论.北京:电子工业出版社,2004年.
[24]杜树新,吴铁军.模式识别中的支持向量机方法.浙江大学学报（工学版）,2003,37(5):521-527.
[25] Hsu C. W., Chang C. C. and Lin C. J.. A Practical Guide to Support Vector Classification. http://www.csie.ntu.edu.tw/～cjlin, Last updated: July18,2007.
[26]肖健华,吴今培.基于核的特征提取技术及应用研究.计算机研究,2002,28(10):36-38.