基于BP神经网络织物疵点检测识别

根据疵点的特征对简单的织物疵点进行识别,先采用直方图均衡化、小波分解、二值化等方法对织物图像进行一系列的预处理,然后提取出织物疵点的特征值,再利用3层BP神经网络对织物疵点进行训练识别分类,试验结果表明识别率达95％。     

基于人工神经网络的织物疵点检测

根据疵点的特征对常见织物疵点进行了简单的划分。采用直方图均衡化、二值化、中值滤波、腐蚀和膨胀等方法对织物图像进行一系列的预处理，对织物疵点的特征参数进行提取，利用人工BP神经网络来判别疵点的类别并进行分类。结果表明，利用BP神经网络识别织物疵点并进行分级是行之有效的。     

基于小波变换和BP神经网络的织物疵点检测

探讨基于小波变换和BP神经网络的织物疵点检测技术。为准确检测织物疵点,采用小波变换对预处理后的织物图像进行分解,小波分解后不同的子图像反应了织物的不同细节信息,从小波分解后的水平细节子图像和垂直细节子图像中提取特征参数,特征参数的提取采用灰度共生矩阵法,将提取到的特征参数送入训练过的BP神经网络,进行检测疵点,达到疵点织物融合、形态学和阈值处理并显示疵点的目标。实验证明:该方法行之有效。认为:寻找更适合的方法提取更有效的特征值和改进神经网络可以提高识别效率。     

基于图像线灰度和BP神经网络的织物疵点检测

探讨织物疵点自动检测的方法。通过对4种常见织物疵点的图像进行线灰度曲线分析和处理,提取疵点图像的特征值,送入BP神经网络进行识别,从而实现织物疵点的检测。试验结果表明,该方法取得了较好的检测效果,织物疵点识别率达到93%以上。认为,此法能够有效识别出织物中的几类常见疵点,应进一步研究,以提高其识别准确率。     

基于PSO-BP神经网络的织物疵点分类方法

将粒子群优化算法运用于BP神经网络的训练,更合理地确定神经网络的连接权重和阈值,提高解决实际问题的能力。同时将PSO-BP神经网络的模型用于织物疵点的分类中。采用正交小波变换的方法对织物图像进行单层分解,并提取水平和垂直2个方向的子图像,分别代表织物的纬向和经向纹理,然后计算其经、纬向的能量、方差、熵等特征值,做为神经网络的输入值。将PSO-BP神经网络与BP神经网络分类的结果相比较,表明PSO-BP神经网络能够取得较好的效果。     

织物疵点自动识别技术在毛纺中的应用

为了实现自动验布，摆脱人工验布的种种缺点，介绍了采用神经网络和图像处理技术识别织物疵点的准确性和可行性，把疵点主要分为破洞、断经、断纬、油渍、筘路等5类，使用灰度统计量法对疵点图像进行处理，然后应用BP网络对其进行分类识别。实验证明该方法的准确性高、速度快，符合自动验布系统的要求。同时文章还讨论了该技术在毛纺企业的应用前景。     

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.     

基于灰度分布梯度的织物疵点检测算法

针对织物疵点检测算法实用性差的问题,提出一种基于灰度分布梯度检测算法,通过对纹理织物相邻像素灰度差异和单位距离的商来判断纹理是否异变。在对灰度试样提高对比度和二值化图像预处理,并根据织物组织结构确定检测窗口的基础上,把试样分解成经向和纬向2个子图并得到各自方向的能量统计值,从中提取跃迁比等4种特征值,综合各类疵点对方向特征值的不同敏感程度检测出疵点。该算法简便,实时性好,特别适合方向性疵点及块状疵点的检测。     

基于褶皱特征参数的男西装袖弊病类别的自动识别

为实现自动判别男西装袖的弊病类型，提出了一种将图像处理技术与BP神经网络相结合的判别方法。首先收集不同弊病类型的男西装袖图像，借用MATLAB平台，对图像进行灰度化、灰度增强、二值化等预处理，绘制褶皱部位的灰度曲线图；然后基于灰度曲线图以及二值化图提取褶皱宽度、褶皱深度和褶皱斜率等3个特征参数；最后将提取的特征参数和对应的弊病类型输入到BP神经网络中训练和识别，对男西装袖弊病图像的类型进行分类。结果显示，提出的方法对袖弊病类型的判别具有较高的准确率与稳定性。     

基亏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。在融合罔像灰度的基础上,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。     

基于深度信念网络的织物疵点检测

为提高织物疵点检测精度和效率,提出了一种基于深度信念网络的织物疵点检测方法。用改进的受限玻尔兹曼机模型对深度信念网络进行训练,完成模型识别参数的构建。利用同态滤波方法对图像进行预处理,使疵点图像更加清晰,同时抑制了背景图像。以Python语言,基于TensorFlow框架构建深度信念网络模型,对织物疵点图像进行处理得到学习样本,确定模型激活函数后,分析了各模型参数对织物疵点检测准确率的影响规律,得到激活函数为Relu, Dropout值为0.3,预训练学习率为0.1,微调学习率为0.000 1,批训练个数为64时,模型参数值达到最优。最后,利用在无缝内衣机上采集到的各类疵点图像,对深度信念网络织物疵点检测模型进行验证。结果表明：所提出的织物疵点检测方法能够快速、有效地对织物疵点进行检测和分类识别,准确率达到98%。     

基于改进的加权中值滤波与K-means聚类的织物缺陷检测

为检测纹理织物在生产过程中产生的各种疵点,提出一种基于改进的加权中值滤波与K-means聚类相结合的纹理织物疵点检测方法。首先利用改进的加权中值滤波对纹理织物图像进行预处理,以减少纹理信息对疵点检测产生的影响,同时通过联合直方图动态数据分配权重和像素,减少寻求中位数的时间来有效地缩短检测时间,提高了执行速度;然后采用K-means算法对滤波后的织物图像进行聚类,计算织物图像疵点和非疵点的聚类中心,进而实现图像疵点区域的分割。实验结果表明,该方法可有效地检测出方格、点形、星形、平纹、斜纹等多类型纹理织物的疵点,并显著提高检测速度。     

Knitted fabric structure recognition based on deep learning

In knitted fabric structure recognition, the recognition rate is influenced by uneven light, fabric hairiness, fabric rotation, fabric thickness variation, yarn deviation, and loop deformation. To solve this problem, a method for recognizing knitted fabric structure based on deep learning is proposed. Firstly, sample images of fabrics are captured and a knitted fabric structure image database is established. Secondly, based on deep convolution neural network and transfer learning, the bvlc_reference_caffenet model trained by AlexNet is used as the pre-trained network. Then the pre-trained parameters of the network are transferred to the target data-set and the network is trained. Finally, the knitted fabric structure is recognized by the trained network. Experiment results show that the proposed recognition method is robust, which can overcome the influence of fabric rotation, fabric hairiness and uneven light, and achieves a high recognition rate.     

基于人工神经网络的织物疵点聚类分析

本文提出了一种基于人工神经网络的织物疵点分类方法。首先利用灰度共生矩阵提取织物疵点图像的纹理特征参数;然后阐述前馈BP神经网络的拓扑结构,并提出该网络的具体训练过程;最后利用人工神经网络对真实织物疵点样本进行分类,实验采用五类织物样本,网络训练完成后得到实际分类的疵点数据,并利用该数据进行织物疵点分类,分类的准确率达到100%,从而验证了该方法的可行性。     

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.     

Yarn-dyed woven defect characterization and classification using combined features and support vector machine

In this paper, we present a novel defect evaluation method that uses combined features and modified support vector machine (SVM) classifiers to characterize and classify the defects of yarn-dyed fabrics. Yarn-dyed fabric images are preprocessed, and nine parameters are defined in the combined feature extractors. Based on binary and textural energy images for defect regions, yarn-dyed fabric defect features can be described, such as weft length, warp length, weft length to warp length ratio, perimeter, area, roundness, coarseness, contrast, and directionality. These parameters are also used as the inputs of optimized SVM classifiers to obtain overall defect classes in accordance with the Chinese National Standard of Yarn-dyed Pattern Fabrics (GB/T 22851 – 2009). The effectiveness of this evaluation method is tested by 180 selected defect images of yarn-dyed fabrics that have different patterns. The cross-validation tests on the yarn-dyed fabric defect classifications indicate that the defect categories of more than 91% of these diversified samples can be recognized correctly by using the SVM classification scheme. Furthermore, the extracted defect parameters provide useful information for textile and clothing manufacturing to grade yarn-dyed fabrics.     

Identification of fabric defects based on discrete wavelet transform and back-propagation neural network

Detection of fabric defects can be considered as a texture segmentation and identification problem, since textile faults normally have textural features that are different from features of the original fabric. A feasible approach for the recognition of fabric defects based on discrete wavelet transform and back-propagation neural network is proposed in this article, the indispensable processes of which are defect image preprocessing, wavelet transform, feature extraction, principal component analysis of the extracted feature parameters, and defect identification. Under the experimental condition, the average recognition accuracy of defects and nondefects are 99.2% and 100%, respectively. Experimental results show the advantages with high identification correctness and high inspection speed.     

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。