基于光照投影的起球织物图像的采集、预处理和毛球分割

采用一种新的图像分析方法进行织物起球等级的分析。先获取一系列起球织物切面光照投影图，利用LOG边缘检测算子和线性插值提取每帧图像中织物的轮廓线高度数据，并拼接成一幅反映织物三维轮廓高度的距离图像，最后对该距离图像进行预处理和基于自适应阈值法的毛球分割。     

Evaluation of Fabric Pilling Using Light Projection and Image Analysis Techniques

A new instrument based on light projection and image analysis techniques for assessing fabric pilling is presented. This system can automatically detect the pills from the successive sections of the fabric surface, which can make up for the limitation of both the gray level image -analysis techniques and laser triangulab'on techniques. The test of a large number of worsted wool fabric samples shows that it can objectively characterize the degree of pilling by using fuzzy sets and has good accordance with human visual inspection.     

起球对兔羊毛针织物损伤的影响

本文讨论了起球对兔羊毛针织物损伤的影响。通过实验我们发现掉毛和掉球从兔羊毛针织物表面移去了大量纤维,造成织物损伤。用球的增长机理解释了起球大大超过初始绒毛量的现象,从而说明起球不只是影响兔羊毛针织物的美观,更是一种磨损机理。     

应用图像分析技术评估织物起球等级

探讨了应用图像分析技术对织物起球进行客观的等级评估.首先介绍了应用Wold分解纹理模型从织物图像中分离出毛球信息,然后对提取的毛球信息进行阈值化处理,再以毛球的面积百分比、总数和分布等三个特征指标对起球等级进行客观评估.运用上述技术途径对素色、印花及色织的简单与复杂组织等7种织物样品进行起球等级的客观评估,结果与专家的人工主观评定极为吻合.     

用图像分析技术评价织物起球

首先采用图像分析技术对起球织物的图像进行预处理;其次以织物起球总面积M和起球形态S等指标定量地综合评价织物的起球状况;最后以针织物为例,通过实验验证此方法的可行性.     

评价织物悬垂美感的图像信息处理系统

介绍了用计算机图像信息处理系统,分析处理织物的悬垂投影照片的方法,获取了客观评价织物悬垂美感形态的特征参数.     

基于LOG算子的起球织物切面轮廓线提取

LOG算子对起球织物切面轮廓线的提取进行了分析。首先介绍LOG算子的基本思想和离散LOG算子的构造，然后比较了LOG算子和经典算子边缘检测的效果及如何选定LOG算子的平滑程度，最后利用零交叉检测和线性插值提取轮廓线的高度。实验征明这种方法是非常有效的。     

兔羊毛机织物起球特点与影响因素探讨

起球是影响织物服用性能的主要因素之一。本文采用YG502型园轨迹织物起毛起球仪,对50/50兔羊毛机织物进行磨球,并通过投影显微镜观察磨球次数与球体结构形态、球体密度和数量的关系,同时,就起球的影响因素,包括茸毛高度、定型程度、以及化学树脂整理剂及柔软剂进行研究。显微镜观察发现,50/50兔羊毛机织物球体中2/3以上纤维是兔毛纤维,而球芯则以较粗的羊毛纤维为多。为综合考虑球体大小、数量和纤维纠缠密度对感官的影响,提出了起球程度评价指标——等价面积值,其较传统五级分类法更为客观,准确。 对织物起球过程的研究表明,由茸毛转为球体的临界磨球次数为10～20次;磨球20～200次是球体大量形成时期;之后球体形成减少;磨球1000次以后落球开始。此规律可由起球曲线反映。试样经优化处理后,其起球曲线变化趋势基本不变,但绝对值与相对变化率均较原样对应值为小。 本研究显示定形与起球关系不明显;降低绒毛高度、添加一定浓度的树脂对减少起球效果明显,柔软剂的添加则可增加起球机会。此实验结果对生产上正确应用剪毛工艺、树脂和柔软剂添加与保持优良织物外观和手感的关系处理具有重要的指导意义。     

Assessing the Pilling of Fabric by Image Analysis

In this paper, firstly, the image of pilling was pre - pro-cessed by image analysis technique, which based on the image's gray- scale statistical characters or mathemati-cal morphology. Then, the pilling of fabric was assessed synthetically by the size of pilling A,number of pilling N and morphology of pitting S. At the end, we tested the practicability of this method by testing knitgoods as a sample, and the result was satisfiable.     

基于熵和变异度的织物疵点图像分割方法

针对现有织物疵点图像分割方法对光照不均匀敏感的问题,提出了一种基于局部熵和变异度的织物疵点图像分割方法。首先对织物图像进行局部熵和变异度计算,提取疵点的类边缘和区域信息;然后基于人工神经网络脉冲耦合（PCNN ）的区域生长法分割织物疵点图像。通过对T ILDA数据库中的疵点图像和基于线阵CCD在线检测的织物疵点图像进行测试,并与已有的相关方法进行对比实验和评价。结果表明,该方法不仅能有效地抑制光照不均匀和复杂背景干扰的影响,而且分割质量有了明显改进。     

基于图像距离差的织物疵点检测算法研究

将机器视觉与数字图像处理技术引入到织物疵点检测中,提出了一种织物疵点检测算法———图像距离差算法,即图像采集、图像处理、疵点识别等。该算法可使用户根据织物的类型,自行设置相应的疵点检测控制参数,能够检测出30多种常见的疵点,实验证明该算法具有识别正确率高、误识率低、识别速度快等优点。     

应用微机图像处理技术测试织物悬垂性研究——织物悬垂图像测试方法

探索用图像处理技术测试织物的悬垂性能.这部分重点介绍采用伪中值滤波去除原始图像的噪声,选用流动阈值法作目标与背景分离,通过特征参数提取获得现有织物悬垂仪所能得到的各项悬垂性指标,并给出目标图像的某些悬垂形态与三维信息,为进一步建立用主客观相结合的评价织物悬垂性方法提供现代技术手段.     

快速富里叶变换在织物结构分析中的应用

在计算机图像处理和横式识别领域，快速富氏变换（ＦＦＴ）技术起着非常重要的作用．织物（此文只论及机织物）的结构是由相同单元规则地排列而成的，呈现很强的周期性．这使得ＦＦＴ技术在分析织物结构特征中特别有效．本文讨论如何应用ＦＦＴ去识别织物组织、纱线密度、纬纱倾斜度等其它结构参数．     

基于自适应正交小波的机织物密度自动检测的研究

为了将计算机视觉应用于织物经纬密自动检测，提出了建立机织物自适应小波分解滤波器并研究了织物密度自动检测的方法。应用织物自适应滤波器对织物灰度图像进行小波分解，就可使分解后的子图像能很好地分别包含织物的纬向和经向纹理信息，从而可将织物子图像二值化后，根据其黑白交替变化规律，计算出织物的经纬纱密度。实验结果证明自动检测和人工测量相比，误差在3％以内。     

基于图像分析的织物悬垂轮廓提取

采用国际通用的伞式法,利用图像分析技术开发了测试织物动静态悬垂的测试系统。根据输入图像灰度分布的双峰特性构造了表征灰度密度分布的理论解析表达式模型。根据实际得到的灰度密度分布利用最优化的方法得到了灰度密度,分布理论解析式的6个系数。根据得到的灰度密度分布理论表达式,从理论上计算出织物悬垂图像轮廓提取的阈值。     

基于体视学原理砂土孔隙组构的图像分析

基于体视学原理定量描述孔隙组构的数学框架,采用归一化思想重新定义组构张量,提出了砂土孔隙组构描述的新方法.该方法用平面张量的第二不变量定义幅值参量来描述孔隙各向异性的大小,用其分量定义方向参量来描述各向异性方向,用这两个标量描述平面孔隙分布规律.采用多种图像处理技术消除砂样SEM图的一些干扰因素,优化得到清晰的二值化图像.砂样SEM图像分析表明:不同角度的平行测试线可以用于测量平均孔隙率,但无法测定其平面孔隙分布,环形测试线则可较好描述孔隙的空间分布规律.新方法用两个标量来描述平面孔隙分布,随孔隙空间几何关系变化,自然退化为现有张量的描述形式.图像分析验证了新方法描述的合理性.     

基于织物自适应正交小波的疵点检测

应用织物自适应正交小波对织物疵点的检测和识别进行了分析,首先介绍了织物图像的小波分解算法和紧支撑正交小波,在此基础上提出了织物自适应小波的构造,由自适应小波对织物图像分解,然后对分解后的纬向和经向子图像提取特征,由特征什检测和识别疵点。实验证明了该方法对素色织物的常见疵点具有快速、准确的检测效果。     

A New Method for Measuring the Stitch Length of Weft Knitted Fabric in a Static Environment

It is essential to measure the stitch length of weft knitted fabric in a static environment for economy and improving productivity. The image inputted was dealt with the digital image processing techniques： the paper carried out the transformation of grey scale; then removed impurities with filtering; the characteristic of the stitch structure was abstracted by using the Fourier transform technique. To obtain the stitch length more accurately, we should establish ageometric medal of the stitch lined on the digital image processing, which provides a way to transform the stitch length in the two-dimenslon space into a three-dimension space. This study provides a new methed for measuring the stitch length without damaging the fabric.     

Automatic Assessment of Fabric Smoothness Grade Using Double CCD Grating Projection

Automatically assessing fabric smoothness grade is very important in the evaluation of fabric appearance. A system for objectively evaluating the fabric smoothness grade based on a grating projection unit and double colored CCD (short form of charge coupled device) was constructed in this paper. Two images captured by different CCD compensated each other which reduced the influence of noises. The application of the four-step phase-shifting method enabled the calculation of the exact phase in a point easy and quick. A large amount of 3D points with three coordinates X, Y and Z were obtained precisely making the definition and calculation of fabric smoothness characters easy. Then four parameters which intuitively denoted the fabric smoothness degree were obtained. Finally, a proper neural network was built, which successfully performed the fabric smoothness classification. The experimental results show that the system is applicable for all the fabric whatever pattern or color. The experimental grades provided by this grating projection system are also highly consistent with the subjective results.     

VARIATION OF WOVEN FABRIC GEOMETRY——Non-uniform Flattening of Yarns

In previous research much effort has been devoted to the geometry of woven fabrics and relat-ed problems under the assumption of constant yarn configuration in fabric.This paper will first re-port that image crimp (yarn crimp measured by an image analysis method) seems larger than actualvalue.From the explanation of this result,the variation of yarn configuration in woven fabric dueto the non-uniform flattening is revealed.The significance of this actual structure of woven fabricsis discussed.It is believed that the variation of yarn configuration is very important for fabric per-formance,and may be an advantage for fabric quality.