基于小波变换和阈值分割的织物疵点边缘检测

The edge detection of fabric defects is the base of geometrical features extraction and the essential process of the fabric defects identification, This paper proposed a method for fabric defects edge detection based on discrete stationary wavelet transform （DSWT） and optimal threshold segmentation algorithm （OTSA）. Firstly, the background of fabric defects picture was removed, then it was executed through DSWT and enhanced by the Laplacian operator. Finally, the edge detection was carded out with both OTSA and morphological operation. By contrast, this method is better than the classic ones, and is effective to fabric defect edge detection.     

织物图像增强矩阵特征模型的建立

针对目前缺乏有效显现织物特征的成熟模型,使织物疵点识别效果不佳的现状,提出一种新的织物图像特征模型,即增强矩阵特征模型.该特征模型以图像的灰度值为基础,引入一种新的增强矩阵.该矩阵由根据织物图像梯度变化生成的矩阵算子组成,可对像素灰度值进行变换计算以放大或缩小图像局部特征,使图像的特征显现更加层次分明.通过采用MatL...     

应用单演小波分析的织物疵点检测

为了解决现有织物疵点检测算法对种类繁多的疵点形式尤其是对微弱纹理变化疵点的适应性较弱问题,提出以单演小波分析工具为基础的织物疵点检测算法。通过拉普拉斯分数阶算子与多重调和样条构建各向同性拉普拉斯小波后,对其进行Riesz变换构建Riesz–拉普拉斯小波,实现了织物图像的单演小波分析。对单演小波分析结果中的多分辨率方向与振幅子带,分别设计了最优响应子带判断标准以及最优响应子带分割方法。实验结果表明,本文提出的检测算法可有效分割不同织物纹理中的多种类疵点,分割结果可反映疵点位置与轮廓,对342幅实验样本图像实现了97.37%的检出率,具有较好的自适应性与鲁棒性。     

基于小波神经网络的帘子布疵点智能识别技术

针对帘子布疵点图像特征,提出了将小波变换和人工神经网络技术应用在帘子布疵点检测上.在融合图像灰度的基础上,经小波变换后再提取分解子图像的特征值,利用BP神经网络进行图像分类.结果表明:对帘子布常见疵点如油污、破洞、抽经、断纬等能比较准确地识别.     

纹理织物疵点窗口跳步形态学法检测

针对纹理织物疵点自动检测时因生产速度快造成的织物抖动以及检测速度难以匹配问题,提出窗口跳步形态学法纹理织物疵点检测算法。使用该算法对图像进行窗口分割及预处理后,首先对纹理织物图像的纹理特征进行分析,然后设计形态学算子进行腐蚀操作,最后使用连通域分析来确定疵点大小及位置。仿真实验及工厂实际应用表明,该算法可有效克服工业生产中纹理织物抖动造成的图像明暗不均,可检测出纹理织物中存在的破洞、经纬疵点、污渍、断线、折痕和结头等各种疵点,而且检测速度明显优于快速傅里叶变换特征点算法以及传统形态学检测算法。实时检测速度超过80 m/min,疵点检测精度为0.1 mm,满足实际生产需求。     

基于神经网络的织物疵点识别技术

因织物组织繁多,表面特征各异,很难建立一个统一的织物疵点识别模型。为了解决这一问题,实现自动验布,提出采用双层神经网络和小波变换来识别织物疵点的方法。先对正常织物进行训练,得到织物的特征,应用第1层简单BP网络来分辨正常织物和疵点。然后对疵点图像进行二维离散小波变换,并去除织物本身的特征,利用已训练的BP网络进行具体疵点识别。试验证明,这种方法的准确性较高,速度快,基本接近自动验布系统的要求。     

基于离散粒子群算法的织物疵点特征选择

为提高识别织物疵点的准确率,提出基于离散粒子群算法(Bpso)进行织物疵点特征选择的方法.首先收集织物疵点图像并进行预处理,提取常用的纹理特征构成候选特征.然后采用BPSO对这些候选特征进行选择,得到优选特征和冗余特征.最后分别在这3类特征下训练支持向量机并进行织物疵点识别测试.结果表明,优选特征的疵点识别准确率大大高...     

Fabric defect detection based on the saliency map construction of target-driven feature

In inspection of fabric surface quality in production line, small defects have to be detected in a large background. In this paper, a new method is put forward to detect fabric surface defect by target-driven features. First of all, surface defect feature of fabric is analyzed; and then, area feature of and number feature of defects are used as tasks, which drive to enhance saliency of defective regions and to form feature saliency maps; finally, by using threshold segmentation, fusion, and filtering, fabric defect is gained from the feature saliency maps. Experiments show that the detection algorithm, compared with classic defect algorithm, can achieve accurate segmentation of the surface defects, better anti-noise ability, higher detection accuracy, which has a strong applicability on the fabric defect detection, and provides the possibility for realizing automatic detection of textile industrial product surface defect.     

应用积分图的织物瑕疵检测快速算法

为解决现有基于图像处理的织物瑕疵检测算法实时性较差、正确率偏低等问题,提出一种包含学习和检测2个阶段的瑕疵检测算法。通过对无瑕疵模板图像的梯度能量特征及其分布特性的学习,自适应获得检测阶段所需的参数。一方面利用积分图原理将任意大小的图像块内的求和运算化简为三次加法运算,快速提取织物图像的梯度能量特征,实现织物瑕疵的实时检测,另一方面利用核函数拟合特征参数分布,结合均值漂移法求解分布峰值获得自适应的瑕疵判定阈值参数,实现织物瑕疵的准确分割。通过实验将本文算法与现有基于局部二值模式特征、小波特征、规则带特征等算法进行对比,针对包含3种纹理6类瑕疵的织物图像数据集的测试结果显示,本文算法平均处理时间为56ms,正确率为97%。     

应用局部纹理特征的无监督织物瑕疵检测算法

针对当前算法对种类繁多瑕疵,尤其是经纬向瑕疵适应差问题,提出一种应用局部纹理特征的无监督织物瑕疵检测算法。这种算法采用无监督检测方案,检测过程中不需要参考样本。在检测过程中,首先根据瑕疵稀少性特点,直接从整体织物图像中获取表征局部织物纹理的局部二值模式直方图特征;然后利用机织物经纬交织特点对局部织物图像沿经纬向投影,并在此基础上提取特征;最后计算所提取特征的瑕疵异常图,并对其进行权重方式融合后实施阈值分割,实现瑕疵检测。实验结果表明,所提出的投影特征能有效表征局部织物纹理,与局部二值模式特征结合使用能有效检测织物瑕疵。     

Adaptive detection of weft‐knitted fabric defects based on machine vision system

This paper describes a machine vision system for the detection of weft‐knitted fabric defects based on an adaptive pulse‐coupled neural network (PCNN) and Ridgelet transform. In order to classify defects according to their different texture features, two methods are implemented: an improved PCNN method to segment the defects such as hole and dropped stitch from background image and a Ridgelet transform method based on wavelet analysis to identify the defect such as course mark. In implementing the PCNN model, necessary parameters of PCNN model such as linking coefficient, connection weight, and iteration number are automatically calculated in accordance with the spatial distance of neurons, mean, and variance value of whole image, and the cross‐entropy criterion. The function of Ridgelet transform is to identify the straight line marks and fit the regression equation for simulating the course mark in the image. The Ridgelet transform model can be simplified as the combination of Radon and wavelet transforms. The parameters of detected line are acquired by wavelet analysis in Fourier semicircle region. The experiment materials were several plain and interlocked weft‐knitted fabrics with hole, dropped stitch, and course mark defects. The fabric images were captured by an area‐scan camera with a resolution of 600 × 800 pixels, and signal processing was controlled by a digital signal processing multiprocessor on the inspection machine. The validation tests proved that the system performed well.     

织物疵点图像消噪方法的比较

织物疵点图像的消噪是疵点识别和分类的重要预处理步骤。采用中值滤波、Wiener滤波和小波阈值化消噪3种方法对织物疵点图像进行消噪处理。在采用中值滤波和Wiener滤波时,同时选用3×3和5×5滤波器进行消噪;在采用小波阈值化消噪时,计算图像全局阈值,同时采用软、硬阈值消噪方法,对疵点图像进行消噪。通过实验比较,采用小波阈值化方法消噪时,疵点图像边缘清晰,峰值信噪比显著提高,其效果明显好于中值滤波和Wiener滤波;采用小波阈值化消噪后的疵点图像可在特征提取和识别中使用。     

小波分析在织物缺陷检测中的应用

对于织物缺陷的检测，可以使用多种不同的图像处理技术．而具有多分辨特性的小波变换是一种分析图像的新方法，它的变尺度特性与人类视觉中的空间频率多通道相吻合．使用小波分析的方法对3种织物缺陷进行检测分类．首先将织物图像进行3层小波分解，然后把小波分解后的图像灰度值作为特征参数输入到BP神经网络进行检测识别，实验结果表明，用这种方法识别织物缺陷识别率可达到98％。     

基于小波特征和SVM的织物疵点识别

针对常见织物疵点具有方向性,利用传统空间域特征识别方法不能有效定位局部疵点区域且当样本较少时分类率低的问题,为有效定位疵点且提高分类率,提出了水平和垂直方向上小波域特征,利用能有效解决小样本分类问题的支持向量机进行分类识别;并对利用图像灰度共生矩阵特征及小波域特征的分类结果进行了比较。仿真实验结果表明,所选特征不仅能对织物疵点区域进行水平和垂直方向上的定位,而且得到了较高的正确分类率。     

Development of a machine vision system: real-time fabric defect detection and classification with neural networks

In this study, a machine vision system is developed to achieve fabric inspection and defect classification processes automatically. The system consists of an image acquisition hardware and an image processing software. A simple and portable system was designed so that it can be adapted easily to all types of the fabric inspection machines. The software of the system consists of defect detection and classification algorithms. The defect detection algorithm is based on wavelet transform, double thresholding binarization, and morphological operations. It was applied real time via a user interface prepared by using MATLAB^® program. The defect classification approach is based on gray level co-occurrence matrix and feed forward neural network. Five commonly occurring defect types, warp lacking, weft lacking, soiled yarn hole, and yarn flow, were detected and classified. The defective and defect-free regions of the fabric were detected with an accuracy of 93.4% and the defects are classified with 96.3% accuracy rate.     

丝织物疵点智能化判别

主要对平纹、斜纹和缎纹组织丝织物的一些常见疵点，如档疵、缺纬、缺经、重纬、油污等进行了智能化判别。先用SONY数码相机在黑色的背景下对疵点进行了拍照得到了图像数据，然后用一系列图像预处理法，如直方图处理变换增加了织物图像的对比度、用计算得到的阈值对织物进行了二值化处理、滤波方法消除二值化处理后图像噪声等，从织物纹理分离出疵点部分，得到了可以分析的织物疵点图像。用灰度统计法对预处理得到的织物疵点图像进行了分析，得到了织物各疵点基本特征值信息。织物疵点智能化判别是用BP神经网络进行的，首先对BP神经网络进行了训练，然后将灰度统计法得到的疵点特征值信息输入到BP神经网络，对疵点进行了分类。     

Warp-knitted fabric defect segmentation based on non-subsampled Contourlet transform

Differing from the traditional Contourlet transform, the non-subsampled Contourlet transform (NSCT) is proposed to apply in warp-knitted fabric defect segmentation. First, the Laplacian pyramid is used to achieve the decomposition of original fabric image. Second, the high frequency directional sub-band coefficients are extracted by means of the non-subsampled directional filter bank. Then, choose the best high frequency sub-band coefficient at every level based on regional energy maxima and reconstruct the image. Finally, the legible defect profile is obtained by adaptive threshold method and morphological processing. The experimental results including the common defects, such as broken warp, width barrier and oil, show that the NSCT could attain the correct segmentation on directional defect and regional defect. This method fits the directional changes of warp-knitted fabric defect. It provides a new way to detect warp-knitted fabric defects automatically.     

基于遗传规划的织物自适应正交小波基的构造和优化

 为了实现机织物疵点的自动检测,文章在构造织物自适应正交小波库的基础上,运用遗传规划算法,将构造的小波库作为群体规模,对遗传规划算法四种不同的适应度函数进行优选后,从群体规模中优化出与织物纹理相匹配的小波基。研究结果表明,以织物纹理波动为适应度函数得到的小波基与织物的匹配性较好。试验验证了该方法对相关疵点检测的有效性,并采用窗口分割法对织物疵点进行定位,表明采用遗传规划算法结合适应度函数优选的方法,能够找到与织物纹理相适应的最优小波基,实现织物疵点的自动检测。     

织物褶皱多尺度灰度共生矩阵分析

为建立一套客观、稳定、高效的织物褶皱评价系统,文章提出一种多尺度图像特征提取方法。首先,通过3层小波变换对织物二维图像进行分解,得到其高频系数;对原图及三个尺度下的小波系数分别生成灰度共生矩阵,并对这四个尺度的灰度共生矩阵提取对比度、相关性、角二阶矩、同质性及熵值表征织物褶皱变化;最后通过支持向量机对输入特征进行分类。结果表明,结合小波变换的灰度共生矩阵方法比单独使用灰度共生矩阵分类准确率高,说明多尺度的图像特征能够更加全面地描述织物褶皱变化。     

基于自适应离散小波变换的混合特征畸变织物疵点识别

 本文通过构造自适应正交小波识别混合特征畸变织物疵点。首先确定所设计小波的优化目标，然后采用二通道方法准确重建正交滤波器(Quadrature Mirror Filter, QMF)的结构实现方式，推导出目标函数，并通过目标函数选择具体的优化方法，建立起优化目标和QMF系数间的函数关系；最后采用构造出的自适应正交小波对3种类型的混合特征畸变疵点进行识别，通过两层离散小波分解，验证该方法的可行性。