棉麻纤维图像分析及自动检测技术的研究
|
摘要
本文以棉麻纤维图像特征提取和识别为研究对象，系统研究纺织纤维自动检测的技术，主要包括纤维切片技术、图像自动摄取技术、图像轮廓描述技术、图像分割技术、图像特征提取和纤维识别技术。
纤维成分的测定在纺织加工业、商品交易和国际贸易中有极其重要的地位。对由化学结构相似纤维制成的混纺产品，无法用化学溶解法测定其成分比例，通常只能使用显微镜鉴别方法，棉／麻纤维的鉴别是其中的典型代表。
长期以来，人工检测为基础的检验方法，检验时间较长，检验成本较高，检验结果会受主观情绪和长时间工作的视觉疲劳影响产生测试误差。本文研究棉／麻自动检测的相关技术，从而达到缩短检验周期，提高检验效率，减轻检验人员的劳动强度，排除人为因素的干扰，保证结果的一致性和客观性。
纤维切片技术关系到纤维自动检测的难易和检测结果的准确性。本文首先简单介绍制备纵向形态测试样品的过程，利用煮沸法形成分布均匀、密度适当的纤维悬浊液，然后在载玻片上形成分布均匀的纤维层，并且尽可能减少载玻片上纤维之间重叠和交叉。根据纤维图像自动检测和分析的需要，采用预聚技术的丙稀酸类树脂快速包埋技术制作纤维截面切片，改进重点在于降低该类包埋剂聚合时收缩率，避免不均匀聚合，同时提高包埋速度，以适应常规研究和快速检测的要求。通过对木棉纤维和涤纶单中空纤维中空率、圆整度进行测试，证明本技术具有良好的保形性能。采用树脂切片技术获得的纤维截面切片，切片薄，截面变形小，截面之间的粘连少，为图像自动检测系统的研制打下良好的基础。
图像自动摄取技术保证图像数字化的自动进行，该技术主要由三部分组成——自动聚焦、多焦面图像融合和图像拼接技术，核心是聚焦算法。在聚焦算法研究上，对灰度差分算子、灰度方差算子、Tengrad算子、Lapal算子和灰度熵算子在纤维显微图像聚焦效果进行研究，在无偏性、单值性、单义性、抗干扰性和简单性五个方面进行性能比较，依据聚焦曲线选定灰度差分算子作为纤维图像粗聚焦算子；通过对纤维图像的特点进行分析，提出自适应局部区域和基于轮廓边缘灰度变化精确聚焦方法，分别应用于纵向片段和截面聚焦。通过对实际摄取过程的分析，充分利用不同视野聚焦平面位置之间的相关性，预置起始聚焦位置，缩短聚焦距离，和改进的调焦策略相结合，提高聚焦速度。
利用自动聚焦过程提供的多焦面图像聚焦信息，在粗聚焦图像的基础上，根据纤维轮廓，将多焦面图像组中每幅图像分割为背景区域(无目标)、清晰区域(目标聚焦区域)、模糊区域(目标离焦区域)。融合图像背景由系列聚焦图像背景区域平均获得，目标区域通过清晰区域直接替代模糊区域获得，并结合边界处理。
在显微图像处理分析中，受显微镜视野的限制，常常需要将多幅图像拼成一幅较完整的图像。本文提出的拼接算法基于模板匹配原则，根据图像的相邻关系确定拼接模板和拼接区域，利用中值滤波和梯度算子处理拼接模板和拼接区域，避免噪声干扰和图像灰度差异影响，保证定位精确和拼接正确。
目标轮廓的特点是纤维图像识别研究的重点，利用链码对目标轮廓描述，可以将轮廓的2-D边界形状描述问题，转化成对1-D波形进行分析的问题，为随后进行的目标形状特征的描述和判别提供便利。为解决图像噪声干扰问题，采用轮廓边缘平滑方法；为提高链码表征角度的能力，扩大计算轮廓切线方向的支撑区间，提高抗噪声能力和减少线性采样的影响，对Freeman链码进行改进，引入方向链码概念，即累加差分链码和；通过对人工轮廓方向链码曲线的分析，进行轮廓角点提取技术研究。针对纤维纵向形态图像，利用方向链码确定轮廓跟踪起始点和判断纤维交叉部位及纤维头端；根据纤维纵向轮廓的特点，提出快速生成纤维中轴线的算法。将纤维截面粘连形式分为串联、并联两种基本形式，给出判断截面粘连的算法，针对不同的截面粘连形式提出不同的分割策略。最后对典型棉麻截面的中腔胞壁轮廓进行方向链码描述，并归纳了它们的链码曲线特点。
将轮廓采用链码表示就意味着将二维的图像分析问题转化为一维信号处理，就可以利用信号分析技术来提取纤维截面特征。从信号分析角度，轮廓信号可视为由轮廓包络信号和轮廓特征信号组成。小波变换通过伸缩和平移等运算功能对函数或信号进行多尺度分析，具有多分辨率分析的特点，很适合探测正常信号中夹带的瞬态反常现象并展示其成分。文中首先对小波变换原理、多分辨率分析原理及一维Mallat快速算法进行简单介绍；对纤维截面轮廓的方向链码曲线振荡原因进行分析，依据小波降噪的原理，利用多层小波变换进行信号降噪；利用小波变换多尺度分析能力，先获得截面轮廓的包络信号，然后获得轮廓特征信号，并在裂缝、凹陷和角点的模型上验证本算法的可行性；最后对中腔胞壁的突变特征信号进行相关性分析，利用相关性系数区分棉麻纤维截面。
在棉麻纤维纵向形态识别方面，首先简单回顾已有的棉麻纤维纵向形态特征参数；根据纤维纵向轮廓的特点，提出快速准确计算纤维纵向形态投影直径的算法；根据纤维纵向形态图像灰度变化的特点，提出利用纤维断面灰度变化特征表征棉转曲和判断棉中腔的方法；针对纤维横节和裂纹提取的困难，采用灰度投影方法提取纤维横节和裂纹特征，将二维纹理特征的提取转化为对一维灰度曲线波形分析；引入图像样式转换技术解决弯曲纤维横节和裂纹提取困难，并在此基础上提出基于纤维中轴线的快速判断方法；最后建立棉麻纤维纵向形态识别流程。
针对天然纤维特征参数不稳定的特点，利用神经网络进行纤维识别。首先对棉麻纤维截面特征参数的分布进行统计，初步得到它们的分布规律；然后在介绍神经网络原理和特点的基础上，构建用于纤维识别的三层BP神经网络；采用固定测试法和交叉检验法对特征参数在识别中的作用进行了研究，筛选出用于识别的截面特征集合；并在此基础上，对网络隐层节点数目和激活函数类型进行优选。
针对天然纤维特征参数不稳定的特点，利用神经网络进行纤维识别。首先对棉麻纤维截面特征参数的分布进行统计，初步得到它们的分布规律；然后在介绍神经网络原理和特点的基础上，构建用于纤维识别的三层BP神经网络；采用固定测试法和交叉检验法对特征参数在识别中的作用进行了研究，筛选出用于识别的截面特征集合；并在此基础上，对网络隐层节点数目和激活函数类型进行优选。
本文以棉麻纤维为研究对象，系统研究纺织纤维自动检测的相关技术，获得了一系列成果。首先改进树脂包埋技术，缩短包埋时间，为纤维截面分析提供低变形、高分离度的光学显微镜半薄切片，保证截面图像质量，基本满足实际检测工作的需要；根据纺织纤维光学显微图像的自身特点，确定自动聚焦算法，为自动显微镜的研制和应用奠定基础；对Freeman链码进行改进，引入方向链码概念，可以更精确地描述纤维截面的轮廓特征，而且将二维图像特征提取转化为一维信号分析，方便随后的截面特征分析工作；利用小波变换具有多尺度分析的特点，对轮廓细节特征进行提取，准确反映截面轮廓特征变化；充分利用纤维图像中的灰度信息，增加分析信息来源，提高纤维识别率；最后将神经网络技术应用到纤维判别，利用其自学习、自组织的特性应对天然纤维截面特征参数分布波动的问题。上述技术不仅仅只适用于纤维成分分析工作，还可以推广到纤维品质检测、纤维成形技术、纺纱工艺过程质量控制以及纺织材料结构检测等领域，具有广阔的应用前景。
The feature extraction and determination of cotton and bast fiber is researched in this thesis. A series of automated determining technology in textile fibers is studied, which include microscopical sample preparing technology, image automatic photographing technology, the object contour describing technology, the image segmented technology, feature extraction technology and fiber identification technology.
The determination of fiber contents is very important in textile industry, national and international trade. The chemical dissolving analysis is no use for these textiles containing two or more fiber types of similar chemical structure. The only way is microscopical analysis, and the determination of fiber content in cotton/blast fiber blends is typical in this identification type.
Microscopical analysis is based on manual determining, which results in much time-consuming, high testing-cost. The identification result can be easily influenced by subjective emotion and eye strain for long time work. The automatic determination of fiber contents can shorten inspection period, heighten testing efficiency, lighten technical labor intension, eliminate artificial disturb, ensure results consistency and objectivity.
The slicing technology of fiber directly influences the difficulty and correctness of automatic identification. The procedure of preparing the longitudinal slices is simply introduced. A uniform and fairly fiber suspension is obtained through quick boiling, the noticing part of which is to avoid the fiber overlapping and crossing. The improved methacrylate resin embedding is used in fiber cross-section slices. This method reduces the polymerized shrinkage, uneven polymerization and embedding time. The embedding method is fit for research and fast testing. The hollowness and circularity measuring from the slices of hollow polyester fiber and kapok proved this method has best form-keeping. The slice from resin embedding has little deformation, low touching and thin thickness. These will facilitate the automated image testing system.
The automatic photograph ensures the automated image-digitalizing. This technology is made up of auto-focus technology, multi-focus image fusion and image stitching, the core of which is auto focusing algorithm. In the part of auto-focusing, several focusing algorithms are discussed: the sum of the absolute of value of gray difference(SMD), the gray scale variance, the Tengrad operator, the Lapal operator and the gray scale entropy. The unbiased ness, uniqueness, single meanings, anti-noise performance and simplicity of these algorithms is compared, and the SMD is selected for coarse focusing algorithm based on the focusing curve. The adaptive local sub-area algorithm is applied in the fiber longitudinal section image, and the gray variation around the contour is applied in the cross sectional focusing. The practical focusing procedure is analyzed, and the relativity between locations of focal planes of different visual fields is used to decide the pre-location of focusing procedure. The pre-location method which shortens the focus distance and the improved focusing tactic increase focusing speed.
At the use of the info of multi-focus image from auto-focusing procedure and coarse focusing image, the images from the image series are segmented into background(no object), sharp area(the object focusing) and blur area(the object defocusing). The background of the fusion image is obtained from the average of backgrounds of series images, and the object area of the fusion image is obtained through the sharp area substituting blur area and combining with border processing.
In microscopically image analysis, several images is stitched together to form an entirely image for the limitation of visual field. The algorithm is based on template matching principle. The stitched template and area is defined from the relationship between neighboring images. The two areas are processed by median filter and gradient operator in order to escape from the influence of noise and image gray level difference, which ensures the correctness of location and join.
The character of object contour is the focus of fiber image recognizing. The feature extraction of 2-D image is converted into the analysis of 1-D signal by the use of chain code describing method for the contour, which facilitates the following feature analysis of shape. The border smoothing is used to decrease the influence of image noise. The concept of direction chain code is introduced, which is the sum of differential chain code cumulativeness to increase the ability of direction expression, anti-noise and anti-rectilinear-sampling. Depended on the direction chain code curve from artificial contour, the method of detecting corner is studied. Aiming at longitudinal image, the start point of border-tracing, the ends and cross part of fibers is decided on the directional chain code. The middle axis can be quickly decided on the character of longitudinal shape. The touching cross-section can be divided into two basic touching type, serial touching and shunt touching. The algorithm to judge touching cross-section and the different separating algorithm for different touching types is brought forward. The lumen and cross-section border of the typical fiber/ramie fiber is described by the direction chain code, and the character of these curves is concluded.
If the contour is described by the chain code, this means that the 2-D image analysis can be converted into 1-D signal proceeding, so the signal analyzing technique can be used to extract features of fiber contour. The contour signal can be taken for the buildup of envelop signal and detail signal. The wavelet transform have multi-scale analysis on signal through dilation and translation transform, which is suitable for detecting the transient abnormal phenomena and its component. The principle of wavelet transform, multi-resolution analysis and 1 -D Mallat fast method is simply introduced. The reason for the surge of directional chain code curve is analyzed, and the curve is denoised by the multi-level wavelet transform. The envelop signal is obtained from the contour curve by the multi-scale analysis, and then the detail signal is gotten. This method is validated on the crack model, concavity model and corner model. The correlativity between lumen and cross-sectional border is calculated, and the coefficient is used to discriminated cotton/bast fibers.
In the part of distinguishment of longitudinal modality, the distinguishing algorithms which have been studied are simply introduced. A fast algorithm of measuring fiber widths is put forward based on the fiber longitudinal character. The gray level variation is used to decide natural convolution and lumen of cotton. The gray projecting method is used to extract the cross markings and cracks, which converts 2-D feature extraction into the 1-D gray curve analysis. The difficulty of extraction of the cross markings and cracks on curly fiber is solved by the image transform, and a fast improved deciding method based on fiber middle axis is put forward. The flow of deciding fiber type on the longitudinal feature is built up.
The neutral network is used to determine the fiber types to answer for the unsteadiness of natural fibers feature. The distributing of cross-sectional character parameter is investigated, and the elementary statistics rule is obtained. After the principle and trait of neutral network is introduced, the three-level BP neutral network is formed for fiber determining. The effect of feature in fiber determining is researched on steady testing method and cross testing method, from which the determine set of cross-sectional feature is screened out. Based on these work, the hide-layer nodes number and activating function is choose.
This thesis focuses on the determination of cotton/blast fiber. The determining technologies are systemically researched. First the embedding resin is improved, and the embedding time is shortened. The little deforming and high separating half-thin microscopy slide is provided, which ensures the cross-sectional image quality and satisfies the practical testing task. The auto-focusing algorithm is decided by the character of microscopical image of textile fiber, which is the foundation of auto-microscope. The Freeman chain code is improved and the concept of direction chain code is introduced. The new code describes the contour of fiber cross-sectional more precisely. The feature extraction of 2-D image is converted into the analysis of 1-D signal, which facilitate the following feature analysis of shape. The detail feature is extracted from the multi-resolution analysis of wavelet transform, which indicated the character more truly. The gray level info is fully made use of to increase the analysis source and the determining correctness. The cross-sectional image is differentiated by the artificial neutral network, of which the self-study and self-organize is fit for the unsteadiness of the natural fiber cross-sectional feature. All above technology is not just fit for fiber content analyzing, but also can be used in fiber quality inspect, fiber forming technology, the quality control of spinning procedure and the testing of textile material structure, which has extensively applied fields.
纤维成分的测定在纺织加工业、商品交易和国际贸易中有极其重要的地位。对由化学结构相似纤维制成的混纺产品，无法用化学溶解法测定其成分比例，通常只能使用显微镜鉴别方法，棉／麻纤维的鉴别是其中的典型代表。
长期以来，人工检测为基础的检验方法，检验时间较长，检验成本较高，检验结果会受主观情绪和长时间工作的视觉疲劳影响产生测试误差。本文研究棉／麻自动检测的相关技术，从而达到缩短检验周期，提高检验效率，减轻检验人员的劳动强度，排除人为因素的干扰，保证结果的一致性和客观性。
纤维切片技术关系到纤维自动检测的难易和检测结果的准确性。本文首先简单介绍制备纵向形态测试样品的过程，利用煮沸法形成分布均匀、密度适当的纤维悬浊液，然后在载玻片上形成分布均匀的纤维层，并且尽可能减少载玻片上纤维之间重叠和交叉。根据纤维图像自动检测和分析的需要，采用预聚技术的丙稀酸类树脂快速包埋技术制作纤维截面切片，改进重点在于降低该类包埋剂聚合时收缩率，避免不均匀聚合，同时提高包埋速度，以适应常规研究和快速检测的要求。通过对木棉纤维和涤纶单中空纤维中空率、圆整度进行测试，证明本技术具有良好的保形性能。采用树脂切片技术获得的纤维截面切片，切片薄，截面变形小，截面之间的粘连少，为图像自动检测系统的研制打下良好的基础。
图像自动摄取技术保证图像数字化的自动进行，该技术主要由三部分组成——自动聚焦、多焦面图像融合和图像拼接技术，核心是聚焦算法。在聚焦算法研究上，对灰度差分算子、灰度方差算子、Tengrad算子、Lapal算子和灰度熵算子在纤维显微图像聚焦效果进行研究，在无偏性、单值性、单义性、抗干扰性和简单性五个方面进行性能比较，依据聚焦曲线选定灰度差分算子作为纤维图像粗聚焦算子；通过对纤维图像的特点进行分析，提出自适应局部区域和基于轮廓边缘灰度变化精确聚焦方法，分别应用于纵向片段和截面聚焦。通过对实际摄取过程的分析，充分利用不同视野聚焦平面位置之间的相关性，预置起始聚焦位置，缩短聚焦距离，和改进的调焦策略相结合，提高聚焦速度。
利用自动聚焦过程提供的多焦面图像聚焦信息，在粗聚焦图像的基础上，根据纤维轮廓，将多焦面图像组中每幅图像分割为背景区域(无目标)、清晰区域(目标聚焦区域)、模糊区域(目标离焦区域)。融合图像背景由系列聚焦图像背景区域平均获得，目标区域通过清晰区域直接替代模糊区域获得，并结合边界处理。
在显微图像处理分析中，受显微镜视野的限制，常常需要将多幅图像拼成一幅较完整的图像。本文提出的拼接算法基于模板匹配原则，根据图像的相邻关系确定拼接模板和拼接区域，利用中值滤波和梯度算子处理拼接模板和拼接区域，避免噪声干扰和图像灰度差异影响，保证定位精确和拼接正确。
目标轮廓的特点是纤维图像识别研究的重点，利用链码对目标轮廓描述，可以将轮廓的2-D边界形状描述问题，转化成对1-D波形进行分析的问题，为随后进行的目标形状特征的描述和判别提供便利。为解决图像噪声干扰问题，采用轮廓边缘平滑方法；为提高链码表征角度的能力，扩大计算轮廓切线方向的支撑区间，提高抗噪声能力和减少线性采样的影响，对Freeman链码进行改进，引入方向链码概念，即累加差分链码和；通过对人工轮廓方向链码曲线的分析，进行轮廓角点提取技术研究。针对纤维纵向形态图像，利用方向链码确定轮廓跟踪起始点和判断纤维交叉部位及纤维头端；根据纤维纵向轮廓的特点，提出快速生成纤维中轴线的算法。将纤维截面粘连形式分为串联、并联两种基本形式，给出判断截面粘连的算法，针对不同的截面粘连形式提出不同的分割策略。最后对典型棉麻截面的中腔胞壁轮廓进行方向链码描述，并归纳了它们的链码曲线特点。
将轮廓采用链码表示就意味着将二维的图像分析问题转化为一维信号处理，就可以利用信号分析技术来提取纤维截面特征。从信号分析角度，轮廓信号可视为由轮廓包络信号和轮廓特征信号组成。小波变换通过伸缩和平移等运算功能对函数或信号进行多尺度分析，具有多分辨率分析的特点，很适合探测正常信号中夹带的瞬态反常现象并展示其成分。文中首先对小波变换原理、多分辨率分析原理及一维Mallat快速算法进行简单介绍；对纤维截面轮廓的方向链码曲线振荡原因进行分析，依据小波降噪的原理，利用多层小波变换进行信号降噪；利用小波变换多尺度分析能力，先获得截面轮廓的包络信号，然后获得轮廓特征信号，并在裂缝、凹陷和角点的模型上验证本算法的可行性；最后对中腔胞壁的突变特征信号进行相关性分析，利用相关性系数区分棉麻纤维截面。
在棉麻纤维纵向形态识别方面，首先简单回顾已有的棉麻纤维纵向形态特征参数；根据纤维纵向轮廓的特点，提出快速准确计算纤维纵向形态投影直径的算法；根据纤维纵向形态图像灰度变化的特点，提出利用纤维断面灰度变化特征表征棉转曲和判断棉中腔的方法；针对纤维横节和裂纹提取的困难，采用灰度投影方法提取纤维横节和裂纹特征，将二维纹理特征的提取转化为对一维灰度曲线波形分析；引入图像样式转换技术解决弯曲纤维横节和裂纹提取困难，并在此基础上提出基于纤维中轴线的快速判断方法；最后建立棉麻纤维纵向形态识别流程。
针对天然纤维特征参数不稳定的特点，利用神经网络进行纤维识别。首先对棉麻纤维截面特征参数的分布进行统计，初步得到它们的分布规律；然后在介绍神经网络原理和特点的基础上，构建用于纤维识别的三层BP神经网络；采用固定测试法和交叉检验法对特征参数在识别中的作用进行了研究，筛选出用于识别的截面特征集合；并在此基础上，对网络隐层节点数目和激活函数类型进行优选。
针对天然纤维特征参数不稳定的特点，利用神经网络进行纤维识别。首先对棉麻纤维截面特征参数的分布进行统计，初步得到它们的分布规律；然后在介绍神经网络原理和特点的基础上，构建用于纤维识别的三层BP神经网络；采用固定测试法和交叉检验法对特征参数在识别中的作用进行了研究，筛选出用于识别的截面特征集合；并在此基础上，对网络隐层节点数目和激活函数类型进行优选。
本文以棉麻纤维为研究对象，系统研究纺织纤维自动检测的相关技术，获得了一系列成果。首先改进树脂包埋技术，缩短包埋时间，为纤维截面分析提供低变形、高分离度的光学显微镜半薄切片，保证截面图像质量，基本满足实际检测工作的需要；根据纺织纤维光学显微图像的自身特点，确定自动聚焦算法，为自动显微镜的研制和应用奠定基础；对Freeman链码进行改进，引入方向链码概念，可以更精确地描述纤维截面的轮廓特征，而且将二维图像特征提取转化为一维信号分析，方便随后的截面特征分析工作；利用小波变换具有多尺度分析的特点，对轮廓细节特征进行提取，准确反映截面轮廓特征变化；充分利用纤维图像中的灰度信息，增加分析信息来源，提高纤维识别率；最后将神经网络技术应用到纤维判别，利用其自学习、自组织的特性应对天然纤维截面特征参数分布波动的问题。上述技术不仅仅只适用于纤维成分分析工作，还可以推广到纤维品质检测、纤维成形技术、纺纱工艺过程质量控制以及纺织材料结构检测等领域，具有广阔的应用前景。
The feature extraction and determination of cotton and bast fiber is researched in this thesis. A series of automated determining technology in textile fibers is studied, which include microscopical sample preparing technology, image automatic photographing technology, the object contour describing technology, the image segmented technology, feature extraction technology and fiber identification technology.
The determination of fiber contents is very important in textile industry, national and international trade. The chemical dissolving analysis is no use for these textiles containing two or more fiber types of similar chemical structure. The only way is microscopical analysis, and the determination of fiber content in cotton/blast fiber blends is typical in this identification type.
Microscopical analysis is based on manual determining, which results in much time-consuming, high testing-cost. The identification result can be easily influenced by subjective emotion and eye strain for long time work. The automatic determination of fiber contents can shorten inspection period, heighten testing efficiency, lighten technical labor intension, eliminate artificial disturb, ensure results consistency and objectivity.
The slicing technology of fiber directly influences the difficulty and correctness of automatic identification. The procedure of preparing the longitudinal slices is simply introduced. A uniform and fairly fiber suspension is obtained through quick boiling, the noticing part of which is to avoid the fiber overlapping and crossing. The improved methacrylate resin embedding is used in fiber cross-section slices. This method reduces the polymerized shrinkage, uneven polymerization and embedding time. The embedding method is fit for research and fast testing. The hollowness and circularity measuring from the slices of hollow polyester fiber and kapok proved this method has best form-keeping. The slice from resin embedding has little deformation, low touching and thin thickness. These will facilitate the automated image testing system.
The automatic photograph ensures the automated image-digitalizing. This technology is made up of auto-focus technology, multi-focus image fusion and image stitching, the core of which is auto focusing algorithm. In the part of auto-focusing, several focusing algorithms are discussed: the sum of the absolute of value of gray difference(SMD), the gray scale variance, the Tengrad operator, the Lapal operator and the gray scale entropy. The unbiased ness, uniqueness, single meanings, anti-noise performance and simplicity of these algorithms is compared, and the SMD is selected for coarse focusing algorithm based on the focusing curve. The adaptive local sub-area algorithm is applied in the fiber longitudinal section image, and the gray variation around the contour is applied in the cross sectional focusing. The practical focusing procedure is analyzed, and the relativity between locations of focal planes of different visual fields is used to decide the pre-location of focusing procedure. The pre-location method which shortens the focus distance and the improved focusing tactic increase focusing speed.
At the use of the info of multi-focus image from auto-focusing procedure and coarse focusing image, the images from the image series are segmented into background(no object), sharp area(the object focusing) and blur area(the object defocusing). The background of the fusion image is obtained from the average of backgrounds of series images, and the object area of the fusion image is obtained through the sharp area substituting blur area and combining with border processing.
In microscopically image analysis, several images is stitched together to form an entirely image for the limitation of visual field. The algorithm is based on template matching principle. The stitched template and area is defined from the relationship between neighboring images. The two areas are processed by median filter and gradient operator in order to escape from the influence of noise and image gray level difference, which ensures the correctness of location and join.
The character of object contour is the focus of fiber image recognizing. The feature extraction of 2-D image is converted into the analysis of 1-D signal by the use of chain code describing method for the contour, which facilitates the following feature analysis of shape. The border smoothing is used to decrease the influence of image noise. The concept of direction chain code is introduced, which is the sum of differential chain code cumulativeness to increase the ability of direction expression, anti-noise and anti-rectilinear-sampling. Depended on the direction chain code curve from artificial contour, the method of detecting corner is studied. Aiming at longitudinal image, the start point of border-tracing, the ends and cross part of fibers is decided on the directional chain code. The middle axis can be quickly decided on the character of longitudinal shape. The touching cross-section can be divided into two basic touching type, serial touching and shunt touching. The algorithm to judge touching cross-section and the different separating algorithm for different touching types is brought forward. The lumen and cross-section border of the typical fiber/ramie fiber is described by the direction chain code, and the character of these curves is concluded.
If the contour is described by the chain code, this means that the 2-D image analysis can be converted into 1-D signal proceeding, so the signal analyzing technique can be used to extract features of fiber contour. The contour signal can be taken for the buildup of envelop signal and detail signal. The wavelet transform have multi-scale analysis on signal through dilation and translation transform, which is suitable for detecting the transient abnormal phenomena and its component. The principle of wavelet transform, multi-resolution analysis and 1 -D Mallat fast method is simply introduced. The reason for the surge of directional chain code curve is analyzed, and the curve is denoised by the multi-level wavelet transform. The envelop signal is obtained from the contour curve by the multi-scale analysis, and then the detail signal is gotten. This method is validated on the crack model, concavity model and corner model. The correlativity between lumen and cross-sectional border is calculated, and the coefficient is used to discriminated cotton/bast fibers.
In the part of distinguishment of longitudinal modality, the distinguishing algorithms which have been studied are simply introduced. A fast algorithm of measuring fiber widths is put forward based on the fiber longitudinal character. The gray level variation is used to decide natural convolution and lumen of cotton. The gray projecting method is used to extract the cross markings and cracks, which converts 2-D feature extraction into the 1-D gray curve analysis. The difficulty of extraction of the cross markings and cracks on curly fiber is solved by the image transform, and a fast improved deciding method based on fiber middle axis is put forward. The flow of deciding fiber type on the longitudinal feature is built up.
The neutral network is used to determine the fiber types to answer for the unsteadiness of natural fibers feature. The distributing of cross-sectional character parameter is investigated, and the elementary statistics rule is obtained. After the principle and trait of neutral network is introduced, the three-level BP neutral network is formed for fiber determining. The effect of feature in fiber determining is researched on steady testing method and cross testing method, from which the determine set of cross-sectional feature is screened out. Based on these work, the hide-layer nodes number and activating function is choose.
This thesis focuses on the determination of cotton/blast fiber. The determining technologies are systemically researched. First the embedding resin is improved, and the embedding time is shortened. The little deforming and high separating half-thin microscopy slide is provided, which ensures the cross-sectional image quality and satisfies the practical testing task. The auto-focusing algorithm is decided by the character of microscopical image of textile fiber, which is the foundation of auto-microscope. The Freeman chain code is improved and the concept of direction chain code is introduced. The new code describes the contour of fiber cross-sectional more precisely. The feature extraction of 2-D image is converted into the analysis of 1-D signal, which facilitate the following feature analysis of shape. The detail feature is extracted from the multi-resolution analysis of wavelet transform, which indicated the character more truly. The gray level info is fully made use of to increase the analysis source and the determining correctness. The cross-sectional image is differentiated by the artificial neutral network, of which the self-study and self-organize is fit for the unsteadiness of the natural fiber cross-sectional feature. All above technology is not just fit for fiber content analyzing, but also can be used in fiber quality inspect, fiber forming technology, the quality control of spinning procedure and the testing of textile material structure, which has extensively applied fields.
引文
1. R. L. Barker. Determination of Fiber Cross-sectional Circularity from Measurement Made in A Longitudinal View. J. Engr. Ind, 1979, 101: 59～64
2. J. D. Berlin. Measuring the Cross-sectional Area of Cotton Fibers with An Image Analyzer. Textile Res. J, 1981, 51: 109～113
3. D. D. Thilbodeaux. Cotton Fiber Maturity by Image Analysis. Textile Res. J., 1986, 56: 130～139
4. Matic-Leigh R., Cauthen D. A. Determining Cotton Fiber Maturity by Image Analysis. Textile Res. J., 1994, 64(9): 534～543
5. Boylston E. K., Thibodeaux D. P., Evans J. P. Applying Microscopy to the Development of a Reference Method for Cotton Fiber Maturity. Textile Res. J., 1993, 632): 80～86
6. B. Xu. Characterizing Fiber Crimp by Image Analysis: Definitions, Algorithms and Techniques. Textile Res. J., 1992, 62(2) 73～80
7. B. Xu. Fiber Cross～sectional Shape Analysis Using Image Processing Techniques. Textile Res. J, 1993, 63(12): 717～730
8. B. Xu. Fiber Image Analysis, Part Ⅰ: Fiber Image Enhancement. J. Textile Inst., 1996, 87(2): 274～283
9. B. Xu. Fiber Image Analysis, Part Ⅱ: Measurement of General Geometric. J. Textile Inst., 1996, 87(2): 284～295
10. B. Xu and B. Pourdeyhimi. Evaluation Maturity of Cotton Fiber Using Image Analysis: Definition and Algorithm. Textile Res. J., 1994, 64(6): 330～335
11. Huang Y., Xu B. Image Analysis for Cotton Fibers—Part Ⅰ: Longitudinal Measurment. Textile Res. J, 2002, 72(8): 713～720
12. B. P. Baxter and M. A. Brims. Description and Performance of the Optical Fiber Diameter Analyzer (OFDA). J. Textile Inst. 1992, 83(4): 507～526
13．费玉忠，余序芬．羊毛细度快速图像测试法探讨．上海纺织科技，1997，(5)：54～56
14．黄成伟，蔡弋等．基于图像识别的动物纤维细度快速测量算法．清华大学学报：自然科学版，2002，42(11)：1477～1479，1483
15．于伟东，谭东梅．化纤异形度的计算机数字图像处理．纺织学报，1994，15(5)：225～227
16．吴兆平，余序芬．三叶型纤维异形度自动测量新方法．纺织学报，1995，16(4)：234～236
17．吴兆平，余序芬．V字型纤维异形度自动测量新方法．纺织学报，1995，16(5)：225～227
18．李增和，于伟东．毛从卷曲特征的图像频谱分析．中国纺织大学学报，2000，26(3)：97～101
19. EI-Alfy M. D., Blakey P. R. The Identification of Animal Fibers by Means of Plaasmaetching and the Scanning Electron Microscope. J. vextile Inst., 1980, 71: 168～170
20. F. J. Wortman, Gabriels Wortmann, W. Arns. Quantitative Fiber Mixture Analysis by Scanning Electron Microsopy Part Ⅰ: Blends of Mohair and Cashmere with Sheep's Wool. Textile Res. J., 1986, 61(7): 442～446
21. F. J. Wortman, Gabriels Wortmann, W. Arns. Quantitative Fiber Mixture Analysis by Scanning Electron Microsopy Part Ⅱ: Blends of Wool with Angora Rabbit Hair. Textile Res. J., 1989, 61(2): 73～80
22. F. J. Wortman, Gabriels Wortmann, W. Arns. Quantitative Fiber Mixture Analysis by Scanning Electron Microsopy Part Ⅲ: Round Traial on Mohair/Wool Blends. Textile Res. J., 1991, 61(7): 371～374
23. D. Robson. Cuticuar Scale Measurement Using Image Analysis Techniques. Textile Res. J., 1989, 12: 713～717
24. D. Robson. Animal Fiber Analysis Using Imaging Techniques Part Ⅰ: Scale Pattern Data. Textile Res. J., 1997, 8: 747～752
25. D. Robson. Animal Fiber Analysis Using Imaging Techniques Part Ⅱ: Addition of Scale Height Data. Textile Res. J., 2000, 70(2): 116～120
26. C. A. Glasbey, D. Hitchcock, A. J. F. Russel, H. Redden. Towards the Automatic Measurement of Cashmere-fiber Diameter by Image Analysis. J. Textile Inst., 1994, 85(3): 301～307
27. F. H. SHE, L. X. Kong, S. Nahavandi, A. Z. Kouzani. Intelligent Animal Fiber Classification with Artificial Neural Networks. Textile Res. J., 2002, 72(7): 594～600
28. Kenneth D. Langley, Esra Coskuntuna. Distinguishing Between New and Recycled Cashmere with Fisher's Discrimination Analysis. Textile Res. J., 2000, 70(2): 181～184
29．吴兆平，余序芬．羊毛细度与横截面几何参量的微机图象分析．上海工程技术大学学报，1995，9(3)：6～10
30．王晓红．纺织纤维图像分析与识别理论及其应用．中国纺织大学博士论文，1999
31．杨建忠，王荣武．羊绒与羊毛纤维表面形态的图像处理与识别．毛纺科技，2002，(5)：12～15
32．北京商检局．《山羊绒与其他动物纤维CAT鉴别方法的研究》技术报告及附件，1996
33．周剑平，封举富．电镜羊绒毛图象自动识别方法研究．中国图象图形学报，2001，6(10)：979～983
34. Hecking L. T., Sullivan J. L., Mealy. Determination of Fiber Content in Cotton/Bast Fiber Blends Using an Image Analysis System. AATCC. Book of Papers, 1992: 107～109
35．李艰．图像处理技术在纺织上的应用与研究—丝毛纤维的自动识别及非织造布结构分析．中国纺织大学博士论文，1998
36．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
37．许鹤群．混纺纱截面图像的识别和分析．中国纺织大学学报，1992，19(1)：67～71
38．余序芬，吴兆平．数学形态学边缘检测法对棉麻自动识别的应用．中国纺织大学学报，1996，22(5)：66～72
39．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
40．徐同祥，上条正义．关于混纺织物中棉，苎麻纤维识别的图象处理研究．苏州丝绸工学院学报，2000，20(4)：14～20
41．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
42. A. Watanabe, S. Kurosaki. Analysis of Blended Irregularity in Gill Sliver by Image Processing. Proc.8 th. Int. Wool Textile Res. Cont., 1990, 3: 359～368
43. A. Watanable, S. Kurosaki. Analysis of Blended Irregularity in Yarns Using Image Processing Part 1: Fundamental of Investigation of Model Yarns. Textile Res. J., 1992, 62(11): 690～696
44. A. Watanabe, S. Kurosaki. Analysis of Blended Irregularity in Yarns Using Image Processing Part 2: Applying the System to Actual Yarns. Textile Res. J., 1992, 62(12): 729～735
45. A. Watanabe, S. Kurosaki. Analysis of Blended Irregularity in Yarns Using Image Processing Part 3: Evaluation of Blended Irregularity by Line Sense and Its Application to Actual Blended Yams. Textile Res. J., 1995, 65(7): 392～399
46. M. J. Alagha. The Use of An Image Analysis Technique for Assessing the Structure Parameters of Friction Spun Yams. J. Textile Inst., 1994, 85(3): 382～388
47．季仲元，黄爱萍．用图像分析法测量纱线的细度．纺织学报，1992，13(10)：445～447
48. Y. E. Zhang, R. R. Bresee, Fabric Defect Detection and Classification Using Image Analysis. Textile Res. J., 1995, 65(1): 1～9
49. W. J. Jaspe, H. Potlapalli. Image Analysis of Mispicks in Woven Fabrics. Textile Res. J., 1995, 65(11): 683～692
50．李立轻，黄秀宝．基于织物自适应正交小波的疵点检测．东华大学学报：自然科学版，2001，27(4)：82～87
51．李立轻，黄秀宝．用于疵点检测的织物自适应正交小波的实现．东华大学学报：自然科学版，2002，28(2)：77～81
52．李立轻，黄秀宝．图象处理用于织物疵点自动检测的研究进展．东华大学学报：自然科学版，2002，28(4)：118～122
53. A. Konda. J. Textile March. Soc. Japan, 1998, 36, (3): 96～101
54. R. B. Ramgular. The Objective Assessment of Fabric Pilling Part 1: Methodology. J. Textile Inst., 1993, 84(2): 221～223
55. R. B. Ramgular. The Objective Assessment of Fabric Pilling Part 2: Experimental Work. J. Textile Inst., 1994, 85(3): 397～401
56．陈霞，徐增波．应用光照投影和图像分析技术评估织物起球等级．纺织标准与质量，2002，(3)：21～23
57. B. Xu, J. D. Reed. Instrumental Evaluation of Fabrics Wrinkle Recovery. J. Textile Inst., 1995, 86(1): 129～135
58. Y. J. Na, B. Pourdeyhimi. Assessing Wrinkling Using Image Analysis and Replicate Standards. Textile Res. J., 1995, 65(3): 149～157
59. S. A. H. Ravandi. Fourier Transform Analysis of Plain Woven Fabric Appearance. Textile Res. J., 1995, 65(11): 676～683
60. B. Xu. Identifying Fabric Structures with Fast Fourier Transform Techniques. Textile Res. J., 1996, 66(8): 496～506
61．曾秀茹，王善元．利用计算机图像处理与分析技术评定双绉织物绉效应．丝绸，1996，(7)：14～17
62. R. H. Gong, A. Newton. Image～analysis Techniques Part 1: The Measurement of Pore-size Distribution. J. Textile Inst., 1992, 83(2): 253～268
63. B. Pourdeyhimi. Pore Size Characterization in Nonwoven Fabrics. INDA Journal of Nonwoven Res., 1992, 5(4): 24～36
64. B. Pourdeyhimi. Pore Characterization in Nonwoven Fabrics: Shape Consideration. INDA Journal of Nonwoven Res., 1993, 6(1): 26～30
65. X. C. Huang. Characterizing Nonwoven Web Structure Using Image Analysis Techniques Part 1: Pore Analysis in Thin Webs. INDA Journal of Nonwoven Res., 1992, 5(1): 23～34
66．渊莺，王善元．模拟熔喷纤网的孔径分布及其对过滤性能的影响．中国纺织大学学报，2000，26(5)：73～77
67. X. C. Huang. Characterizing Nonwoven Web Structure Using Image Analysis Techniques Part 2: Fiber Orientation Analysis in Thin Webs. INDA Journal of Nonwoven Res., 1992, 5(2): 36～45
68. T. R. Wan, G. A. V. Leaf. A New Objective Method for Assessing Fiber Arrangement in Fibrous Webs. J. Textile Inst., 1995, 65(1): 41～48
69. B. Xu. Measuring Structural Characteristics of Fiber Segment in Nonwoven Fabrics. Textile Res. J., 1995, 65(1): 41～48
70. B. Xu. Determining Fiber Orientation Distribution in Nonwovens with Hough Transform Techniques. Textile Res. J., 1997, 67(8): 563～571
71. R. H. Gong, A. Newton. Image～analysis Techniques Part 2: The Measurement of Fiber Orientation in Nonwoven Fabrics. J. Textile Inst., 1996, 87(2): 371～388
72. B. Pourdeyhimi. Assessing Fiber Orientation in Nonwoven Fabrics. INDA Journal of Nonwoven Res., 1992, 5(4): 29～36
73. B. Pourdeyhimi. Measuring Fiber Orientation in Nonwoven Fabrics Part 1: Simulation. Textile Res. J., 1996, 66(11): 713～722
74. B. Pourdeyhimi. Measuring Fiber Orientation in Nonwoven Fabrics Part 2: Direct Tracking, Textile Res. J., 1996, 66(12): 747～753
75. B. Pourdeyhimi. Measuring Fiber Orientation in Nonwoven Fabrics Part 3: Fourier Transform, Textile Res. J., 1997, 67(2): 143～151
76. B. Pourdeyhimi. Measuring Fiber Orientation in Nonwoven Fabrics Part 4: Flow Field Analysis, Textile Res. J., 1997, 67(3): 181～187
77．马志友．用溶解—吸光法测定麻棉混纺纱的混纺比．棉纺织技术，2002，30(5)：486～487
78．孙中爱．纤维鉴别新方法．中国纤检，1997，(1)：15～17
79．孙中爱．纤维鉴别新方法续一．中国纤检，1997，(2)：22～23
80．孙中爱．纤维鉴别新方法续二．中国纤检，1997，(3)：15-17
81．李青山．纺织纤维鉴别手册(M)．北京：中国纺织出版社，1996
82．姚穆．纺织材料学(第二版)(M)．北京：中国纺织出版社，1990
83．孙焕良，赵立宁，傅仓生等．苎麻韧皮纤维细胞超微结构研究．中国麻作，1997，19(1)：4～6
84．张传雄．纤维素纤维特征参数的提取及识别研究．东华大学硕士论文，2004
85．赵健．麻棉混纺比测试方法分析．四川纺织科技，1995，(4)：19~21
86．陈晓青．麻棉混纺比定量分析方法的探讨．纺织标准与质量，1998，(2)：32～33
87．方兆平．麻棉混纺比显微镜法控制误差范围的实践．中国纤检，2002，(4)：31～32
88．沈瑞庆，毛雅珍，郭维婵．麻棉混纺比显微镜法的误差分析．纺织标准与质量，1993，(3)：28～31
89．褚乃清，李丽霞．提高麻棉混纺比测定准确度的方法．印染，2000，(9)：31～32
90. Boylston EK, Hinojosa O, Hebert JJ. A quick embedding method for light and electron microscopy of textile fibers. The Biotechnical and Histochemical Journal, 1991, 66(3): 122～124
91．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(40)：101～104．
92. The Textile Institute Manchester. Identification of Textile Materials. London: Manara Printing Services, 1985
93．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
94. 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
95．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
96．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
97．李正理．植物制片技术．北京：科学出版社，1987
98．庄楚强，吴亚森．应用数理统计基础．广州：华南理工大学出版社，1999
99．章毓晋．图像工程(上册)—图像处理和分析．北京：清华大学出版社，1999
100．奥林巴斯显微镜说明书．日本奥林巴斯株式会社，2001
101．佟首峰，阮锦，郝志航．CCD图像传感器降噪技术的研究．光学精密工程，2000，8(2)：140～145
102．刘丽梅，孙玉荣，李莉．中值滤波技术发展研究．云南师范大学学报，2004，24(1)：23～27
103．高建贞，任明武，杨静宇．一种快速实用的灰度校正算法．中国图象图形学报(A辑)，2002，7(6)：548～552
104．金淑英，包更生，马洪超，申屠海港．海底视像图像的灰度不均匀校正方法的研究．武汉测绘科技大学学报，25(6)：531～536
105. Otsu. A Threshold Selection Method from Gray-Level Histogram. IEEE Transon SMC-9, 1979 62～66
106. JN Kapur, PK Sahoo, AKC Wong. A new method for gray-level picture thresholding using the entropy of the histogram. In: Computer Graphics Image Processing, 1985, 29: 273～285
107. CHEIN-I CHANG, KEBO CHEN, JIANWEI WANG and MARK L. G. ALTHOUSE, ARELATIVE ENTROPY-BASED APPROACH TO IMAGE THRESHOLDING, Pattern Recognition, Vol. 27. No.9 pp. 1275-1289, 1994
108．Kenneth．R．Castlmen．数字图像处理．北京：电子工业出版社，1998．
109．吴振峰，左洪福，邱根良等．显微镜一种新的聚焦算法．数据采集与处理，2000，15(3)：351～354
110．康宗明，张利，谢攀．一种基于能量和熵的自动聚焦算法．电子学报，2003，31(4)：552～555
111．任四刚，李见为，谢利利．基于灰度差分法的自动调焦技术．光电工程，2003，30(2)：53～55
112．干敏梁，刘玉平．图像采集的自动化．南京航空航天大学学报，1998，30(2)：224～228
113．夏明革，何友，欧阳文等．基于小波分析的图像融合述评．红外与激光工程，2003，32(2)：177～181
114．杨烜，杨万海，裴继红．基于小波分解的不同聚焦点图像融合方法．电子学报，2001，29(6)：846～848
115．陶观群，李大鹏，陆光华．基于小波变换的不同融合规则的图像融合研究．红外与激光工程，2003，32(2)：173～202
116．李树涛，王耀南，张昌凡．基于视觉特性的多聚焦图像融合．电子学报，2001，29(12)：1699～1701
117．章毓晋．图像工程(下册)—图像理解与计算机视觉．北京：清华大学出版社，1999
118. H. Freeman. On the encoding of arbitrary geometric configurations. IRE Trans Electronics and Computers, 1961. 16: 260-268
119．周焰，王祖喜，陈振羽，李德华．一种曲线平滑的自适应方法．计算机工程，2000，26(4)：13～15
120．丁明，陆宗骐．基于平均链码的曲率分割法．山东生物医学工程．2000，19(1)：17～19
121．陆宗骐，童韬．链码和在边界形状分析中的应用中国图像图形学报(A辑)．2002，7(12)：1323～1328
122．王英惠，吴维勇，赵汝嘉．平面轮廓的分段与识别技术．计算机辅助设计与图形学学报，2002，14(12)：1142~1151
123．吴维勇，王英惠，周晏．平面轮廓识别与分段技术的研究与快速实现．工程图学学报，2003，(4)：14～19
124．程正兴．小波分析算法与应用．西安：西安交通大学出版社，1998
125．成礼智，王红霞，罗永．小波的理论与应用．北京：科学出版社，2004
126．启文．小波变换与分数傅里叶变换理论及应用．哈尔滨：哈尔滨工业大学出版社，2001
127．程正兴，林勇平小波分析在图像处理中的应用．工程数学学报，2001，18(3)：57～84
128．董长虹主编．Matlab小波分析工具箱原理及应用．北京：国防工业出版社，2004
129．吴湘淇．信号、系统与信号处．北京：电子工业出版社 1996
130．王旭，王宏，王文辉．人工神经网元络原理与应用．沈阳：东北大学出版社，2000
131．邵军力，张景，魏长华．人工智能基础．北京：电子工业出版社，2000
132．戴葵．神经网络实现技术．长沙：国防科技大学出版社．1998
133. Barrett GR, Clapp TG, Trrus KJ. An online fabric classification technique using a wavelet-based neural network approach.Textile Res.J.,1996,66(8) :521～528．
134． Thiemer R.Fiber recognition by neurochip.Chemical Fibers International,2000,50(2) :40～42．
135． Steenlandt W Van,Collet D,Sette S,et al.Automatic assessment of carpet wear using image analysis and neural networks.Textile Res.J.,1996,66(9) :555～561
136． Tsai I-Shou ,Lin Chuang-Hua,Lin Jeng-Jong.Applying an artificial neural network to pattern recognition in fabric defects.Textile Res.J.,1995,65(3) :123～130．
137． Hu MC,Tsai IS.Fabric inspection based on best wavelet packet bases.Textile Res.J.,2000,70(8) :662～670
138． Chen Pei-Wen,Liang Tsair-Chun.Classifying textile faults with a back2propagation neural network using power spectra.Textile Res.J.,1998,68(2) :121～126
139． Tsai I-Shou,Hu Ming-Chuan.Automatic inspection of fabric defects using an artificial neural network technique.Textile Res.J.,1996,66(7) :474～482．
2. J. D. Berlin. Measuring the Cross-sectional Area of Cotton Fibers with An Image Analyzer. Textile Res. J, 1981, 51: 109～113
3. D. D. Thilbodeaux. Cotton Fiber Maturity by Image Analysis. Textile Res. J., 1986, 56: 130～139
4. Matic-Leigh R., Cauthen D. A. Determining Cotton Fiber Maturity by Image Analysis. Textile Res. J., 1994, 64(9): 534～543
5. Boylston E. K., Thibodeaux D. P., Evans J. P. Applying Microscopy to the Development of a Reference Method for Cotton Fiber Maturity. Textile Res. J., 1993, 632): 80～86
6. B. Xu. Characterizing Fiber Crimp by Image Analysis: Definitions, Algorithms and Techniques. Textile Res. J., 1992, 62(2) 73～80
7. B. Xu. Fiber Cross～sectional Shape Analysis Using Image Processing Techniques. Textile Res. J, 1993, 63(12): 717～730
8. B. Xu. Fiber Image Analysis, Part Ⅰ: Fiber Image Enhancement. J. Textile Inst., 1996, 87(2): 274～283
9. B. Xu. Fiber Image Analysis, Part Ⅱ: Measurement of General Geometric. J. Textile Inst., 1996, 87(2): 284～295
10. B. Xu and B. Pourdeyhimi. Evaluation Maturity of Cotton Fiber Using Image Analysis: Definition and Algorithm. Textile Res. J., 1994, 64(6): 330～335
11. Huang Y., Xu B. Image Analysis for Cotton Fibers—Part Ⅰ: Longitudinal Measurment. Textile Res. J, 2002, 72(8): 713～720
12. B. P. Baxter and M. A. Brims. Description and Performance of the Optical Fiber Diameter Analyzer (OFDA). J. Textile Inst. 1992, 83(4): 507～526
13．费玉忠，余序芬．羊毛细度快速图像测试法探讨．上海纺织科技，1997，(5)：54～56
14．黄成伟，蔡弋等．基于图像识别的动物纤维细度快速测量算法．清华大学学报：自然科学版，2002，42(11)：1477～1479，1483
15．于伟东，谭东梅．化纤异形度的计算机数字图像处理．纺织学报，1994，15(5)：225～227
16．吴兆平，余序芬．三叶型纤维异形度自动测量新方法．纺织学报，1995，16(4)：234～236
17．吴兆平，余序芬．V字型纤维异形度自动测量新方法．纺织学报，1995，16(5)：225～227
18．李增和，于伟东．毛从卷曲特征的图像频谱分析．中国纺织大学学报，2000，26(3)：97～101
19. EI-Alfy M. D., Blakey P. R. The Identification of Animal Fibers by Means of Plaasmaetching and the Scanning Electron Microscope. J. vextile Inst., 1980, 71: 168～170
20. F. J. Wortman, Gabriels Wortmann, W. Arns. Quantitative Fiber Mixture Analysis by Scanning Electron Microsopy Part Ⅰ: Blends of Mohair and Cashmere with Sheep's Wool. Textile Res. J., 1986, 61(7): 442～446
21. F. J. Wortman, Gabriels Wortmann, W. Arns. Quantitative Fiber Mixture Analysis by Scanning Electron Microsopy Part Ⅱ: Blends of Wool with Angora Rabbit Hair. Textile Res. J., 1989, 61(2): 73～80
22. F. J. Wortman, Gabriels Wortmann, W. Arns. Quantitative Fiber Mixture Analysis by Scanning Electron Microsopy Part Ⅲ: Round Traial on Mohair/Wool Blends. Textile Res. J., 1991, 61(7): 371～374
23. D. Robson. Cuticuar Scale Measurement Using Image Analysis Techniques. Textile Res. J., 1989, 12: 713～717
24. D. Robson. Animal Fiber Analysis Using Imaging Techniques Part Ⅰ: Scale Pattern Data. Textile Res. J., 1997, 8: 747～752
25. D. Robson. Animal Fiber Analysis Using Imaging Techniques Part Ⅱ: Addition of Scale Height Data. Textile Res. J., 2000, 70(2): 116～120
26. C. A. Glasbey, D. Hitchcock, A. J. F. Russel, H. Redden. Towards the Automatic Measurement of Cashmere-fiber Diameter by Image Analysis. J. Textile Inst., 1994, 85(3): 301～307
27. F. H. SHE, L. X. Kong, S. Nahavandi, A. Z. Kouzani. Intelligent Animal Fiber Classification with Artificial Neural Networks. Textile Res. J., 2002, 72(7): 594～600
28. Kenneth D. Langley, Esra Coskuntuna. Distinguishing Between New and Recycled Cashmere with Fisher's Discrimination Analysis. Textile Res. J., 2000, 70(2): 181～184
29．吴兆平，余序芬．羊毛细度与横截面几何参量的微机图象分析．上海工程技术大学学报，1995，9(3)：6～10
30．王晓红．纺织纤维图像分析与识别理论及其应用．中国纺织大学博士论文，1999
31．杨建忠，王荣武．羊绒与羊毛纤维表面形态的图像处理与识别．毛纺科技，2002，(5)：12～15
32．北京商检局．《山羊绒与其他动物纤维CAT鉴别方法的研究》技术报告及附件，1996
33．周剑平，封举富．电镜羊绒毛图象自动识别方法研究．中国图象图形学报，2001，6(10)：979～983
34. Hecking L. T., Sullivan J. L., Mealy. Determination of Fiber Content in Cotton/Bast Fiber Blends Using an Image Analysis System. AATCC. Book of Papers, 1992: 107～109
35．李艰．图像处理技术在纺织上的应用与研究—丝毛纤维的自动识别及非织造布结构分析．中国纺织大学博士论文，1998
36．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
37．许鹤群．混纺纱截面图像的识别和分析．中国纺织大学学报，1992，19(1)：67～71
38．余序芬，吴兆平．数学形态学边缘检测法对棉麻自动识别的应用．中国纺织大学学报，1996，22(5)：66～72
39．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
40．徐同祥，上条正义．关于混纺织物中棉，苎麻纤维识别的图象处理研究．苏州丝绸工学院学报，2000，20(4)：14～20
41．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
42. A. Watanabe, S. Kurosaki. Analysis of Blended Irregularity in Gill Sliver by Image Processing. Proc.8 th. Int. Wool Textile Res. Cont., 1990, 3: 359～368
43. A. Watanable, S. Kurosaki. Analysis of Blended Irregularity in Yarns Using Image Processing Part 1: Fundamental of Investigation of Model Yarns. Textile Res. J., 1992, 62(11): 690～696
44. A. Watanabe, S. Kurosaki. Analysis of Blended Irregularity in Yarns Using Image Processing Part 2: Applying the System to Actual Yarns. Textile Res. J., 1992, 62(12): 729～735
45. A. Watanabe, S. Kurosaki. Analysis of Blended Irregularity in Yarns Using Image Processing Part 3: Evaluation of Blended Irregularity by Line Sense and Its Application to Actual Blended Yams. Textile Res. J., 1995, 65(7): 392～399
46. M. J. Alagha. The Use of An Image Analysis Technique for Assessing the Structure Parameters of Friction Spun Yams. J. Textile Inst., 1994, 85(3): 382～388
47．季仲元，黄爱萍．用图像分析法测量纱线的细度．纺织学报，1992，13(10)：445～447
48. Y. E. Zhang, R. R. Bresee, Fabric Defect Detection and Classification Using Image Analysis. Textile Res. J., 1995, 65(1): 1～9
49. W. J. Jaspe, H. Potlapalli. Image Analysis of Mispicks in Woven Fabrics. Textile Res. J., 1995, 65(11): 683～692
50．李立轻，黄秀宝．基于织物自适应正交小波的疵点检测．东华大学学报：自然科学版，2001，27(4)：82～87
51．李立轻，黄秀宝．用于疵点检测的织物自适应正交小波的实现．东华大学学报：自然科学版，2002，28(2)：77～81
52．李立轻，黄秀宝．图象处理用于织物疵点自动检测的研究进展．东华大学学报：自然科学版，2002，28(4)：118～122
53. A. Konda. J. Textile March. Soc. Japan, 1998, 36, (3): 96～101
54. R. B. Ramgular. The Objective Assessment of Fabric Pilling Part 1: Methodology. J. Textile Inst., 1993, 84(2): 221～223
55. R. B. Ramgular. The Objective Assessment of Fabric Pilling Part 2: Experimental Work. J. Textile Inst., 1994, 85(3): 397～401
56．陈霞，徐增波．应用光照投影和图像分析技术评估织物起球等级．纺织标准与质量，2002，(3)：21～23
57. B. Xu, J. D. Reed. Instrumental Evaluation of Fabrics Wrinkle Recovery. J. Textile Inst., 1995, 86(1): 129～135
58. Y. J. Na, B. Pourdeyhimi. Assessing Wrinkling Using Image Analysis and Replicate Standards. Textile Res. J., 1995, 65(3): 149～157
59. S. A. H. Ravandi. Fourier Transform Analysis of Plain Woven Fabric Appearance. Textile Res. J., 1995, 65(11): 676～683
60. B. Xu. Identifying Fabric Structures with Fast Fourier Transform Techniques. Textile Res. J., 1996, 66(8): 496～506
61．曾秀茹，王善元．利用计算机图像处理与分析技术评定双绉织物绉效应．丝绸，1996，(7)：14～17
62. R. H. Gong, A. Newton. Image～analysis Techniques Part 1: The Measurement of Pore-size Distribution. J. Textile Inst., 1992, 83(2): 253～268
63. B. Pourdeyhimi. Pore Size Characterization in Nonwoven Fabrics. INDA Journal of Nonwoven Res., 1992, 5(4): 24～36
64. B. Pourdeyhimi. Pore Characterization in Nonwoven Fabrics: Shape Consideration. INDA Journal of Nonwoven Res., 1993, 6(1): 26～30
65. X. C. Huang. Characterizing Nonwoven Web Structure Using Image Analysis Techniques Part 1: Pore Analysis in Thin Webs. INDA Journal of Nonwoven Res., 1992, 5(1): 23～34
66．渊莺，王善元．模拟熔喷纤网的孔径分布及其对过滤性能的影响．中国纺织大学学报，2000，26(5)：73～77
67. X. C. Huang. Characterizing Nonwoven Web Structure Using Image Analysis Techniques Part 2: Fiber Orientation Analysis in Thin Webs. INDA Journal of Nonwoven Res., 1992, 5(2): 36～45
68. T. R. Wan, G. A. V. Leaf. A New Objective Method for Assessing Fiber Arrangement in Fibrous Webs. J. Textile Inst., 1995, 65(1): 41～48
69. B. Xu. Measuring Structural Characteristics of Fiber Segment in Nonwoven Fabrics. Textile Res. J., 1995, 65(1): 41～48
70. B. Xu. Determining Fiber Orientation Distribution in Nonwovens with Hough Transform Techniques. Textile Res. J., 1997, 67(8): 563～571
71. R. H. Gong, A. Newton. Image～analysis Techniques Part 2: The Measurement of Fiber Orientation in Nonwoven Fabrics. J. Textile Inst., 1996, 87(2): 371～388
72. B. Pourdeyhimi. Assessing Fiber Orientation in Nonwoven Fabrics. INDA Journal of Nonwoven Res., 1992, 5(4): 29～36
73. B. Pourdeyhimi. Measuring Fiber Orientation in Nonwoven Fabrics Part 1: Simulation. Textile Res. J., 1996, 66(11): 713～722
74. B. Pourdeyhimi. Measuring Fiber Orientation in Nonwoven Fabrics Part 2: Direct Tracking, Textile Res. J., 1996, 66(12): 747～753
75. B. Pourdeyhimi. Measuring Fiber Orientation in Nonwoven Fabrics Part 3: Fourier Transform, Textile Res. J., 1997, 67(2): 143～151
76. B. Pourdeyhimi. Measuring Fiber Orientation in Nonwoven Fabrics Part 4: Flow Field Analysis, Textile Res. J., 1997, 67(3): 181～187
77．马志友．用溶解—吸光法测定麻棉混纺纱的混纺比．棉纺织技术，2002，30(5)：486～487
78．孙中爱．纤维鉴别新方法．中国纤检，1997，(1)：15～17
79．孙中爱．纤维鉴别新方法续一．中国纤检，1997，(2)：22～23
80．孙中爱．纤维鉴别新方法续二．中国纤检，1997，(3)：15-17
81．李青山．纺织纤维鉴别手册(M)．北京：中国纺织出版社，1996
82．姚穆．纺织材料学(第二版)(M)．北京：中国纺织出版社，1990
83．孙焕良，赵立宁，傅仓生等．苎麻韧皮纤维细胞超微结构研究．中国麻作，1997，19(1)：4～6
84．张传雄．纤维素纤维特征参数的提取及识别研究．东华大学硕士论文，2004
85．赵健．麻棉混纺比测试方法分析．四川纺织科技，1995，(4)：19~21
86．陈晓青．麻棉混纺比定量分析方法的探讨．纺织标准与质量，1998，(2)：32～33
87．方兆平．麻棉混纺比显微镜法控制误差范围的实践．中国纤检，2002，(4)：31～32
88．沈瑞庆，毛雅珍，郭维婵．麻棉混纺比显微镜法的误差分析．纺织标准与质量，1993，(3)：28～31
89．褚乃清，李丽霞．提高麻棉混纺比测定准确度的方法．印染，2000，(9)：31～32
90. Boylston EK, Hinojosa O, Hebert JJ. A quick embedding method for light and electron microscopy of textile fibers. The Biotechnical and Histochemical Journal, 1991, 66(3): 122～124
91．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(40)：101～104．
92. The Textile Institute Manchester. Identification of Textile Materials. London: Manara Printing Services, 1985
93．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
94. 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
95．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
96．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
97．李正理．植物制片技术．北京：科学出版社，1987
98．庄楚强，吴亚森．应用数理统计基础．广州：华南理工大学出版社，1999
99．章毓晋．图像工程(上册)—图像处理和分析．北京：清华大学出版社，1999
100．奥林巴斯显微镜说明书．日本奥林巴斯株式会社，2001
101．佟首峰，阮锦，郝志航．CCD图像传感器降噪技术的研究．光学精密工程，2000，8(2)：140～145
102．刘丽梅，孙玉荣，李莉．中值滤波技术发展研究．云南师范大学学报，2004，24(1)：23～27
103．高建贞，任明武，杨静宇．一种快速实用的灰度校正算法．中国图象图形学报(A辑)，2002，7(6)：548～552
104．金淑英，包更生，马洪超，申屠海港．海底视像图像的灰度不均匀校正方法的研究．武汉测绘科技大学学报，25(6)：531～536
105. Otsu. A Threshold Selection Method from Gray-Level Histogram. IEEE Transon SMC-9, 1979 62～66
106. JN Kapur, PK Sahoo, AKC Wong. A new method for gray-level picture thresholding using the entropy of the histogram. In: Computer Graphics Image Processing, 1985, 29: 273～285
107. CHEIN-I CHANG, KEBO CHEN, JIANWEI WANG and MARK L. G. ALTHOUSE, ARELATIVE ENTROPY-BASED APPROACH TO IMAGE THRESHOLDING, Pattern Recognition, Vol. 27. No.9 pp. 1275-1289, 1994
108．Kenneth．R．Castlmen．数字图像处理．北京：电子工业出版社，1998．
109．吴振峰，左洪福，邱根良等．显微镜一种新的聚焦算法．数据采集与处理，2000，15(3)：351～354
110．康宗明，张利，谢攀．一种基于能量和熵的自动聚焦算法．电子学报，2003，31(4)：552～555
111．任四刚，李见为，谢利利．基于灰度差分法的自动调焦技术．光电工程，2003，30(2)：53～55
112．干敏梁，刘玉平．图像采集的自动化．南京航空航天大学学报，1998，30(2)：224～228
113．夏明革，何友，欧阳文等．基于小波分析的图像融合述评．红外与激光工程，2003，32(2)：177～181
114．杨烜，杨万海，裴继红．基于小波分解的不同聚焦点图像融合方法．电子学报，2001，29(6)：846～848
115．陶观群，李大鹏，陆光华．基于小波变换的不同融合规则的图像融合研究．红外与激光工程，2003，32(2)：173～202
116．李树涛，王耀南，张昌凡．基于视觉特性的多聚焦图像融合．电子学报，2001，29(12)：1699～1701
117．章毓晋．图像工程(下册)—图像理解与计算机视觉．北京：清华大学出版社，1999
118. H. Freeman. On the encoding of arbitrary geometric configurations. IRE Trans Electronics and Computers, 1961. 16: 260-268
119．周焰，王祖喜，陈振羽，李德华．一种曲线平滑的自适应方法．计算机工程，2000，26(4)：13～15
120．丁明，陆宗骐．基于平均链码的曲率分割法．山东生物医学工程．2000，19(1)：17～19
121．陆宗骐，童韬．链码和在边界形状分析中的应用中国图像图形学报(A辑)．2002，7(12)：1323～1328
122．王英惠，吴维勇，赵汝嘉．平面轮廓的分段与识别技术．计算机辅助设计与图形学学报，2002，14(12)：1142~1151
123．吴维勇，王英惠，周晏．平面轮廓识别与分段技术的研究与快速实现．工程图学学报，2003，(4)：14～19
124．程正兴．小波分析算法与应用．西安：西安交通大学出版社，1998
125．成礼智，王红霞，罗永．小波的理论与应用．北京：科学出版社，2004
126．启文．小波变换与分数傅里叶变换理论及应用．哈尔滨：哈尔滨工业大学出版社，2001
127．程正兴，林勇平小波分析在图像处理中的应用．工程数学学报，2001，18(3)：57～84
128．董长虹主编．Matlab小波分析工具箱原理及应用．北京：国防工业出版社，2004
129．吴湘淇．信号、系统与信号处．北京：电子工业出版社 1996
130．王旭，王宏，王文辉．人工神经网元络原理与应用．沈阳：东北大学出版社，2000
131．邵军力，张景，魏长华．人工智能基础．北京：电子工业出版社，2000
132．戴葵．神经网络实现技术．长沙：国防科技大学出版社．1998
133. Barrett GR, Clapp TG, Trrus KJ. An online fabric classification technique using a wavelet-based neural network approach.Textile Res.J.,1996,66(8) :521～528．
134． Thiemer R.Fiber recognition by neurochip.Chemical Fibers International,2000,50(2) :40～42．
135． Steenlandt W Van,Collet D,Sette S,et al.Automatic assessment of carpet wear using image analysis and neural networks.Textile Res.J.,1996,66(9) :555～561
136． Tsai I-Shou ,Lin Chuang-Hua,Lin Jeng-Jong.Applying an artificial neural network to pattern recognition in fabric defects.Textile Res.J.,1995,65(3) :123～130．
137． Hu MC,Tsai IS.Fabric inspection based on best wavelet packet bases.Textile Res.J.,2000,70(8) :662～670
138． Chen Pei-Wen,Liang Tsair-Chun.Classifying textile faults with a back2propagation neural network using power spectra.Textile Res.J.,1998,68(2) :121～126
139． Tsai I-Shou,Hu Ming-Chuan.Automatic inspection of fabric defects using an artificial neural network technique.Textile Res.J.,1996,66(7) :474～482．