基于机器视觉和图像处理的色织物疵点自动检测研究
|
摘要
传统的织物疵点检测依靠人工来完成,检测过程中容易受到主观因素的影响,且效率低下。随着生产工艺和技术的进步,织物疵点自动检测系统逐步代替人工检测,而成为确保织物质量的一种重要手段。但是,目前的织物疵点自动检测系统主要是针对白坯布,因此,本文基于机器视觉和图像处理技术,对应用于宽幅面、高密度色织物的疵点自动检测理论和算法进行了研究,解决了在带有图案的色织物表面进行疵点自动检测和分类的许多关键问题,这也正是本课题研究的主要目的。论文涉及了色织物疵点自动检测系统的研究现状、检测和测量硬件平台的设计、基于分数阶微分的织物图像纹理增强方法、基于能量局部二值模式的色织物疵点智能检测算法、基于组合特征和支持向量机的色织物疵点自动分类识别方法等主要内容。
第一,综述了织物疵点自动检测系统的研究进展。首先,讨论了本课题的研究意义,即应用织物疵点自动检测技术极大的提高了劳动生产率和企业利润收益。其次,调查了本课题的研究背景,对于目前世界三大商用织物疵点自动检测系统的功能和应用状况进行了简要说明,得出课题继续研究的必要性。最后,概述了本课题的国内外研究现状,根据检测对象的不同,主要分为白坯布、灰色图案织物、色织物等疵点自动检测方法。白坯布疵点自动检测算法研究较为成熟,分别为：基于空域的统计方法是把待检测织物图像分割成具有截然不同的统计特征的区域来区分疵点；基于频域的方法是利用织物中基本纹理基元(组织结构)高度的周期性类似于谱特性的规律,可以用谱方法来检测织物疵点；基于模型的方法是指织物纹理能被统计建模,疵点检测被看作这个模型的假设检验问题。灰色图案织物疵点检测方法研究较少,主要有基于模板图像匹配和利用单元重复图案窗口阈值化的方法来检测疵点。色织物疵点检测的方法要考虑色彩模型和更多的疵点种类(织造类疵点和颜色类疵点),目前只是对刚性材料(如瓷砖、木头等)的疵点检测做了一些研究,而对柔性材料(如色织布、印花布等)的疵点检测方法尚没有突破。
第二,介绍了色织物疵点自动检测系统硬件构架的设计方案。首先,给出了硬件架构的总体设计。其次,重点讨论了图像采集硬件子系统的设计,主要分为如下几方面：根据照度匹配原理,选择LED长条形阵列照明光源,并讨论了光源的正向和背向照明结构；CCD相机和图像采集卡的选择,并详细说明了选择CCD相机应考虑的因素；疵点尺寸的图像测量是不同于以往疵点检测系统的新功能,因此需要对多CCD相机系统进行标定,这里介绍了图像测量原理和CCD相机标定理论,计算出每个相机的空间精确位置和姿态参数,并结合色织物疵点测量精度的要求,通过实验确定出像素相当量。最后,介绍了色织物疵点检测FPGA(现场可编程逻辑阵列)专用开发板的接口设计和DSP(数字信号处理器)处理器的选择,这是整个硬件系统的核心处理模块；由于色织物疵点检测和识别需要处理大量数据,所以选用高性能DSP专门进行图像数据运算,而信号控制和数据传输由多通道FPGA来实现；这样就可以构建高速图像同步并行处理硬件子系统,极大提高整个系统的运行速度,使系统具有实用性。
第三,讨论了把分数阶微分应用于织物疵点图像纹理增强的方法,这属于织物疵点自动检测的图像预处理。图像增强是图像处理的重要内容,它通过适合的图像变换使所得结果易于被理解和处理,或者通过技术处理使视觉清晰度得到改善和提高,都是为图像后续有针对性的应用分析打下基础。本文中Grumwald-Letnikov分数阶微分是在Euclid测度下定义的,是通过把微分阶次从整数阶变换到了分数阶的结果。另外,织物疵点图像显然包含有十分丰富的纹理信息,而分数阶微分作为整数阶微分的一种延拓,与整数阶微分相类似,它可以实现织物图像纹理的锐化增强。通过在频域里分析分数阶微分的幅频特性,总结出分数阶微分应用于织物图像增强将使图像边缘明显突出、纹理更加清晰和图像平滑区域信息得以相对保留；基于分数阶微分动力学理论的图像纹理特征检测也被发展,通过稳定系数对图像纹理特征检测的验证分析,分数阶微分不但可以锐化图像灰度值跃变较大的边缘轮廓,而且能够锐化灰度值跃变不大的平滑区域纹理细节特征；根据图像信号的分数阶微分数值差分运算表达式的多项式系数,构建了各向同性分数阶微分的织物图像增强算子。分别对白坯布和色织布疵点图像进行分数阶微分增强实验,定性分析了分数阶微分应用于织物图像增强的有效性。对于白坯布图像还定量地得出了增强后的织物纹理边缘平均测度明显好于原始织物,从而间接地说明了用分数阶微分对织物疵点图像进行非线性增强的良好效果。
第四,设计和实现了基于能量局部二值模式的色织物疵点智能检测算法。这个算法的目的是为了实现快速、有效的利用机器视觉检测色织物疵点,并且考虑颜色和结构两类纹理信息。算法的过程为：(1)把用分数阶微分增强的色织物纹理图像从RGB空间转换到L*a*b*均匀颜色空间；(2)在这个空间里,色彩和灰度通道图像分量分别用Log-Gabor滤波器滤波后再进行融合,得到能量特征疵点图像,解决了色彩类疵点和组织结构类疵点能同时呈现在同一能量特征图像上的难题；(3)通过对色织物的能量特征图像进行分析可知,疵点通常呈现不规则、非均匀的局部较亮区域,其大小从几个像素到几十个像素不等,而色织物的背景图案在能量特征图像中呈现出规则、均匀的较亮区域,因此,需要寻找一种强有力的局部纹理描述算子,并辅以恰当的扫描比对机制,对色织物能量特征图像的疵点区域进行检测。特征图像的纹理能量谱和源于纹理分类的局部二值模式(LBP)之间的结合关系被定义为一个新的概念——能量局部二值模式算子,这个算子具有简单仿射变形的不变性；(4)依据样本图像最小重复单元图案把无疵参考图像和待检测图像分割成窗格,计算每个分割窗口的能量局部二值模式特征向量；(5)在训练阶段,对无疵参考图像进行训练学习以获取无疵窗似然估计阈值,在检测阶段,通过把检测窗似然估计值和阈值进行比较,检测出疵点窗,从而分割出疵点区域。提出的方法能够检测色彩类疵点和组织结构类疵点。通过对不同种类的色织物和不同类型的疵点进行检测验证,总的平均检测成功率达到94.09%；检测速度也足够快,适用于离线疵点检测。
最后,探讨了基于组合特征和支持向量机(SVM)的色织物疵点自动分类算法。这个算法分类的结果将使色织物疵点自动评价方法能够实现,文中主要从三个方面进行讨论：首先,介绍了组合特征集的提取。几何特征参数被定义,并基于疵点二值图像统计出疵点的几何形状特征参数,用于描述色织物疵点六个几何特征(纬长、经长、纬经长度比、周长、面积和圆度)，同时,纹理特征参数也被定义,基于疵点能量纹理图像计算出疵点的能量致理特征参数,用于描述色织物疵点的三个纹理特征(粗糙度、对比度和方向度)；把六个几何特征参数和三个纹理特征参数提取过程合并起来,组建获取九个特征的组合特征提取器,使提取的组合特征能很好的定量描述疵点表面特征的差异；这些参数被用作优化的SVM分类器的输入,以便获得符合色织提花织物中国国家标准(GB/T22851—2009)总的疵点类别(断经、筘路、断纬、稀密路、破洞和污渍)。其次,探讨了疵点图像分类采用径向基核SVM分类器实现,并对通用的SVM分类模型进行优化,使其更加适合色织物疵点的分类。对分类器的两个主要参数通过网格搜索的方法进行最优化选择,以便在应用中能取得最高的分类准确率；当组合特征集被用作SVM分类器的输入时,留一法交叉验证方案被用来防止有偏的分类。最后,用带有不同花型的三种色织物180幅疵点图像进行测试,实验表明,这些多种类样品中超过91%的疵点能被正确分类识别。与获得89.4%平均分类准确率的BP神经网络分类方案相比,本文分类算法更加鲁棒和有效。
Traditionally, fabric defect detection depends on manual work, which is easy to be affected by subjective factors in the detection process and has very low efficiency. With the development of automatic control and information technology, an automatic defect detection system gradually replaces manual testing, and has been an important means of controlling fabric quality. However, the present researches are mainly aimed at the automatic defect detection for gray fabric. Therefore, the paper studies automatic defect detection theory and algorithm based on machine vision and image processing, which is applied in broad and close yarn-dyed fabric. Many key problems are solved for detecting and classifying defects on the surface of yarn-dyed fabric with patterns. It is also the purpose of our research. The main content of the paper involves the research status of automatic detection system for fabric defect, design of detection and measure hardware platform, enhancement method of fabric textures based on fractional differentiation, intelligent detection algorithm of defects of yarn-dyed fabrics by energy-based local binary patterns, as well as yarn-dyed fabric defect characterization and classification method using combined features and support-vector-machine (SVM).
First, the paper reviews the research progress about automatic detection system of fabric defects. This section firstly expounds our research's significance, that is, application of automatic detection technology can greatly improve the labor productivity and corporate profits. The research background is then surveyed in the chapter. The characteristic and application for three commercial detection systems of fabric defects in the world are simply introduced, and the necessity of our research is concluded. According to different kinds of detecting objects, the paper lastly proposes automatic defect detection methods including gray fabric, gray pattern fabric and yarn-dyed fabric. The study on automatic detection algorithm for gray fabric is relatively mature. The statistic method in spatial domain divides a testing fabric image into differently statistical characteristic regions to segment defects; The method in frequency domain detects fabric defects by the similarity between the cyclical of basic texture primitive (organizational structure) and spectrum characteristic; Through mapping fabric textures into geometrical modeling, the model-based approaches can regard defect detection as hypothesis test for the model. The method of defect detection for gray pattern fabric which is researched less mainly comprises template-based image matching and repeating-unit-pattern-based window thresholding. The defect detection for yarn-dyed fabric needs to consider color model and more types of defects (weaving defects and color defects). There have been some algorithms for the defect detection of rigid materials, such as ceramic tile, wood, etc, but so far that of flexible materials, such as yarn-dyed fabric, print fabric, etc, has no a breakthrough.
Second, the paper introduces the design scheme of hardware architecture for automatic defect detection system of yarn-dyed fabric. The overall design of the hardware architecture is firstly presented. This chapter then focuses on the hardware subsystem design for fabric image acquisition:LED lighting source is chosen based on the principle of illumination matching, and the forward and back lighting structure plan is discussed; When CCD cameras and image acquisition cards are selected, the selection factors which should be taken into consideration are detailed; Since image measurement of defect size is a new function in our research, the CCD camera subsystem needs to be calibrated beforehand. After image measuring principle and CCD camera calibration theory are introduced, the parameters of accurate spatial position and posture for each camera are calculated. According to the requirements of measuring precision for yarn-dyed fabric defects, pixel equivalent is determined through the experiments. Finally, the FPGA (field programmable logic array) interface of special development board is designed and the DSP (digital signal processor) is selected, which is the core of the whole hardware system. Since detection and recognition needs to deal with large amounts of data, the high performance DSP is specialized in the operation of image data. Thus, signal control and data transmission are implemented by multi-channel FPGA. The synchronous parallel image processing plan greatly improves the speed of the whole system, which reveals the feasibility and practicability of hardware system design.
Third, the paper discusses the use of fractional differentiation to develop an effective enhancement method for fabric image with abundant textures, which belongs to the image pre-processing of automatic detection for fabric defects. The aim of image enhancement is to improve the visual quality of images, or to convert to a more suitable form in order to analyze and processing. The Grumwald-Letnikov (G-L) definition of fractional differentiation is in Euclidean space in the paper, and it is the results that differential order is extended from integral step-size to fractional step-size. Additionally, it should be known that there are a lot of textures in a fabric image. The fractional differentiation is a continuation of integer-order differentiation, thus similarly the fractional differential operator can also realize sharpening enhancement of image textures. By the analysis of amplitude-frequency characteristics, fractional differentiation can highlight the fabric image edges, improve the fabric textures and nonlinearly keep the details of the fabric image smooth areas; By the analysis of detection between stability coefficients and image textures in the dynamic theory, fractional differentiation not only nonlinearly enhances the contour features in the low-frequency area, but also highlights high-frequency edge features in those areas where gray changes remarkably; From the coefficients of fractional differential polynomial, isotropic operator is constructed to enhance fabric images. Through the respective experiments of defect images for gray fabric and yarn-dyed fabric, the effectiveness of enhancement for fabric texture image is proved by qualitative and quantitative methods. Based on the texture edge map of enhanced fabric image, the favorable enhancement is also confirmed indirectly by region homogeneity measure.
Fourth, the paper designs and realizes the algorithm of intelligent defect detection of yarn-dyed fabrics by energy-based local binary patterns. Its purpose is to finish fast and effective detection of defects of yarn-dyed fabric via computer vision, and to consider two kinds of texture characteristics, that is, color and structure. The algorithm process is as follows:(1) The yarn-dyed fabric image enhanced by fractional differentiation is first converted from RGB true color space to L*a*b*color space.(2) In this color space, energy-based feature images are acquired by image fusion after the Log-Gabor filter filters chromatic and brightness component images. It solves the problem that color and structure defects can be appeared in the same energy feature image.(3) Through the analysis of energy-based feature images for yarn-dyed fabrics, the defects usually are locally brighter areas that have irregularity and non-uniformity and range from several pixels to dozens of pixels. The normal patterns in the background are regular and uniform. Therefore, with the help of the appropriate mechanism of scanning and comparing, what is needed is a local operator of the textures that could be used to detect defects in the energy-based feature images. The relations between energy and the local binary pattern are defined as a new concept called energy-based local binary patterns (ELBP), and the operator has the invariability for simple affine deformation.(4) Based on the minimum repeat pattern units in the defective reference images and testing images, many windows are segmented uniformly, and the ELBP feature vectors are obtained for each definition window in the energy-based feature images.(5) The defective threshold is found by likelihood estimation in the training stage. The defective windows are detected by comparing the threshold with detection windows of tested images in the detection stage, which can segment defect area. The proposed method can detect chromatic and structural defects. Experimental results for the defect detection from several collections of yarn-dyed fabrics indicate that a detection success rate of more than94.09%is achieved for the proposed method. The speed of test is also fast, and it is suitable for off-line testing.
Finally, the paper explores 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. This section firstly introduces the extraction of combination feature set. The geometrical features are defined, such as weft length, warp length, weft length to warp length ratio, perimeter, area, and roundness, and six geometrical parameters are extracted from the binary defect images. Concurrently, three textural parameters that characterize coarseness, contrast, and directionality can be defined and extracted on the basis of the textural energy defect images. The extraction processes of two types of feature parameters can combine into the extractor of combination features. The combination feature set which outputs in the extractor can quantitatively descript the surface characteristics of yarn-dyed fabric defects. 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/T22851-2009), that are cracked-ends (slack-ends, double-ends and mix-end), reedmark, broken picks (double-pick and looped-weft), weft-crackiness, hole (float, knot and gout), and stain (burl-mark, bruise and pan-color). This chapter then discusses the radial basis kernel SVM classifier and the optimization of general SVM classification model. Since the effectiveness of the SVM classification scheme largely depends on the selection of the classifier parameters, a 'grid searching' procedure is used to determine the best selection of two parameters to achieve the highest classification accuracy in the application. When the combined feature set is used as the inputs of the SVM classifier, the LOOCV (leave-one-out cross-validation) is designed to avoid the biased classifications. The experiment samples are180fabric defect images for three types of yarn-dyed fabrics with different patterns. The cross-validation test on the yarn-dyed fabric defect classifications indicates that the defect categories of more than91%can be recognized correctly by using the SVM classification scheme. Compared with the accuracy of89.4%for BPNN, this algorithm is more robust and effective.
第一,综述了织物疵点自动检测系统的研究进展。首先,讨论了本课题的研究意义,即应用织物疵点自动检测技术极大的提高了劳动生产率和企业利润收益。其次,调查了本课题的研究背景,对于目前世界三大商用织物疵点自动检测系统的功能和应用状况进行了简要说明,得出课题继续研究的必要性。最后,概述了本课题的国内外研究现状,根据检测对象的不同,主要分为白坯布、灰色图案织物、色织物等疵点自动检测方法。白坯布疵点自动检测算法研究较为成熟,分别为：基于空域的统计方法是把待检测织物图像分割成具有截然不同的统计特征的区域来区分疵点；基于频域的方法是利用织物中基本纹理基元(组织结构)高度的周期性类似于谱特性的规律,可以用谱方法来检测织物疵点；基于模型的方法是指织物纹理能被统计建模,疵点检测被看作这个模型的假设检验问题。灰色图案织物疵点检测方法研究较少,主要有基于模板图像匹配和利用单元重复图案窗口阈值化的方法来检测疵点。色织物疵点检测的方法要考虑色彩模型和更多的疵点种类(织造类疵点和颜色类疵点),目前只是对刚性材料(如瓷砖、木头等)的疵点检测做了一些研究,而对柔性材料(如色织布、印花布等)的疵点检测方法尚没有突破。
第二,介绍了色织物疵点自动检测系统硬件构架的设计方案。首先,给出了硬件架构的总体设计。其次,重点讨论了图像采集硬件子系统的设计,主要分为如下几方面：根据照度匹配原理,选择LED长条形阵列照明光源,并讨论了光源的正向和背向照明结构；CCD相机和图像采集卡的选择,并详细说明了选择CCD相机应考虑的因素；疵点尺寸的图像测量是不同于以往疵点检测系统的新功能,因此需要对多CCD相机系统进行标定,这里介绍了图像测量原理和CCD相机标定理论,计算出每个相机的空间精确位置和姿态参数,并结合色织物疵点测量精度的要求,通过实验确定出像素相当量。最后,介绍了色织物疵点检测FPGA(现场可编程逻辑阵列)专用开发板的接口设计和DSP(数字信号处理器)处理器的选择,这是整个硬件系统的核心处理模块；由于色织物疵点检测和识别需要处理大量数据,所以选用高性能DSP专门进行图像数据运算,而信号控制和数据传输由多通道FPGA来实现；这样就可以构建高速图像同步并行处理硬件子系统,极大提高整个系统的运行速度,使系统具有实用性。
第三,讨论了把分数阶微分应用于织物疵点图像纹理增强的方法,这属于织物疵点自动检测的图像预处理。图像增强是图像处理的重要内容,它通过适合的图像变换使所得结果易于被理解和处理,或者通过技术处理使视觉清晰度得到改善和提高,都是为图像后续有针对性的应用分析打下基础。本文中Grumwald-Letnikov分数阶微分是在Euclid测度下定义的,是通过把微分阶次从整数阶变换到了分数阶的结果。另外,织物疵点图像显然包含有十分丰富的纹理信息,而分数阶微分作为整数阶微分的一种延拓,与整数阶微分相类似,它可以实现织物图像纹理的锐化增强。通过在频域里分析分数阶微分的幅频特性,总结出分数阶微分应用于织物图像增强将使图像边缘明显突出、纹理更加清晰和图像平滑区域信息得以相对保留；基于分数阶微分动力学理论的图像纹理特征检测也被发展,通过稳定系数对图像纹理特征检测的验证分析,分数阶微分不但可以锐化图像灰度值跃变较大的边缘轮廓,而且能够锐化灰度值跃变不大的平滑区域纹理细节特征；根据图像信号的分数阶微分数值差分运算表达式的多项式系数,构建了各向同性分数阶微分的织物图像增强算子。分别对白坯布和色织布疵点图像进行分数阶微分增强实验,定性分析了分数阶微分应用于织物图像增强的有效性。对于白坯布图像还定量地得出了增强后的织物纹理边缘平均测度明显好于原始织物,从而间接地说明了用分数阶微分对织物疵点图像进行非线性增强的良好效果。
第四,设计和实现了基于能量局部二值模式的色织物疵点智能检测算法。这个算法的目的是为了实现快速、有效的利用机器视觉检测色织物疵点,并且考虑颜色和结构两类纹理信息。算法的过程为：(1)把用分数阶微分增强的色织物纹理图像从RGB空间转换到L*a*b*均匀颜色空间；(2)在这个空间里,色彩和灰度通道图像分量分别用Log-Gabor滤波器滤波后再进行融合,得到能量特征疵点图像,解决了色彩类疵点和组织结构类疵点能同时呈现在同一能量特征图像上的难题；(3)通过对色织物的能量特征图像进行分析可知,疵点通常呈现不规则、非均匀的局部较亮区域,其大小从几个像素到几十个像素不等,而色织物的背景图案在能量特征图像中呈现出规则、均匀的较亮区域,因此,需要寻找一种强有力的局部纹理描述算子,并辅以恰当的扫描比对机制,对色织物能量特征图像的疵点区域进行检测。特征图像的纹理能量谱和源于纹理分类的局部二值模式(LBP)之间的结合关系被定义为一个新的概念——能量局部二值模式算子,这个算子具有简单仿射变形的不变性；(4)依据样本图像最小重复单元图案把无疵参考图像和待检测图像分割成窗格,计算每个分割窗口的能量局部二值模式特征向量；(5)在训练阶段,对无疵参考图像进行训练学习以获取无疵窗似然估计阈值,在检测阶段,通过把检测窗似然估计值和阈值进行比较,检测出疵点窗,从而分割出疵点区域。提出的方法能够检测色彩类疵点和组织结构类疵点。通过对不同种类的色织物和不同类型的疵点进行检测验证,总的平均检测成功率达到94.09%；检测速度也足够快,适用于离线疵点检测。
最后,探讨了基于组合特征和支持向量机(SVM)的色织物疵点自动分类算法。这个算法分类的结果将使色织物疵点自动评价方法能够实现,文中主要从三个方面进行讨论：首先,介绍了组合特征集的提取。几何特征参数被定义,并基于疵点二值图像统计出疵点的几何形状特征参数,用于描述色织物疵点六个几何特征(纬长、经长、纬经长度比、周长、面积和圆度)，同时,纹理特征参数也被定义,基于疵点能量纹理图像计算出疵点的能量致理特征参数,用于描述色织物疵点的三个纹理特征(粗糙度、对比度和方向度)；把六个几何特征参数和三个纹理特征参数提取过程合并起来,组建获取九个特征的组合特征提取器,使提取的组合特征能很好的定量描述疵点表面特征的差异；这些参数被用作优化的SVM分类器的输入,以便获得符合色织提花织物中国国家标准(GB/T22851—2009)总的疵点类别(断经、筘路、断纬、稀密路、破洞和污渍)。其次,探讨了疵点图像分类采用径向基核SVM分类器实现,并对通用的SVM分类模型进行优化,使其更加适合色织物疵点的分类。对分类器的两个主要参数通过网格搜索的方法进行最优化选择,以便在应用中能取得最高的分类准确率；当组合特征集被用作SVM分类器的输入时,留一法交叉验证方案被用来防止有偏的分类。最后,用带有不同花型的三种色织物180幅疵点图像进行测试,实验表明,这些多种类样品中超过91%的疵点能被正确分类识别。与获得89.4%平均分类准确率的BP神经网络分类方案相比,本文分类算法更加鲁棒和有效。
Traditionally, fabric defect detection depends on manual work, which is easy to be affected by subjective factors in the detection process and has very low efficiency. With the development of automatic control and information technology, an automatic defect detection system gradually replaces manual testing, and has been an important means of controlling fabric quality. However, the present researches are mainly aimed at the automatic defect detection for gray fabric. Therefore, the paper studies automatic defect detection theory and algorithm based on machine vision and image processing, which is applied in broad and close yarn-dyed fabric. Many key problems are solved for detecting and classifying defects on the surface of yarn-dyed fabric with patterns. It is also the purpose of our research. The main content of the paper involves the research status of automatic detection system for fabric defect, design of detection and measure hardware platform, enhancement method of fabric textures based on fractional differentiation, intelligent detection algorithm of defects of yarn-dyed fabrics by energy-based local binary patterns, as well as yarn-dyed fabric defect characterization and classification method using combined features and support-vector-machine (SVM).
First, the paper reviews the research progress about automatic detection system of fabric defects. This section firstly expounds our research's significance, that is, application of automatic detection technology can greatly improve the labor productivity and corporate profits. The research background is then surveyed in the chapter. The characteristic and application for three commercial detection systems of fabric defects in the world are simply introduced, and the necessity of our research is concluded. According to different kinds of detecting objects, the paper lastly proposes automatic defect detection methods including gray fabric, gray pattern fabric and yarn-dyed fabric. The study on automatic detection algorithm for gray fabric is relatively mature. The statistic method in spatial domain divides a testing fabric image into differently statistical characteristic regions to segment defects; The method in frequency domain detects fabric defects by the similarity between the cyclical of basic texture primitive (organizational structure) and spectrum characteristic; Through mapping fabric textures into geometrical modeling, the model-based approaches can regard defect detection as hypothesis test for the model. The method of defect detection for gray pattern fabric which is researched less mainly comprises template-based image matching and repeating-unit-pattern-based window thresholding. The defect detection for yarn-dyed fabric needs to consider color model and more types of defects (weaving defects and color defects). There have been some algorithms for the defect detection of rigid materials, such as ceramic tile, wood, etc, but so far that of flexible materials, such as yarn-dyed fabric, print fabric, etc, has no a breakthrough.
Second, the paper introduces the design scheme of hardware architecture for automatic defect detection system of yarn-dyed fabric. The overall design of the hardware architecture is firstly presented. This chapter then focuses on the hardware subsystem design for fabric image acquisition:LED lighting source is chosen based on the principle of illumination matching, and the forward and back lighting structure plan is discussed; When CCD cameras and image acquisition cards are selected, the selection factors which should be taken into consideration are detailed; Since image measurement of defect size is a new function in our research, the CCD camera subsystem needs to be calibrated beforehand. After image measuring principle and CCD camera calibration theory are introduced, the parameters of accurate spatial position and posture for each camera are calculated. According to the requirements of measuring precision for yarn-dyed fabric defects, pixel equivalent is determined through the experiments. Finally, the FPGA (field programmable logic array) interface of special development board is designed and the DSP (digital signal processor) is selected, which is the core of the whole hardware system. Since detection and recognition needs to deal with large amounts of data, the high performance DSP is specialized in the operation of image data. Thus, signal control and data transmission are implemented by multi-channel FPGA. The synchronous parallel image processing plan greatly improves the speed of the whole system, which reveals the feasibility and practicability of hardware system design.
Third, the paper discusses the use of fractional differentiation to develop an effective enhancement method for fabric image with abundant textures, which belongs to the image pre-processing of automatic detection for fabric defects. The aim of image enhancement is to improve the visual quality of images, or to convert to a more suitable form in order to analyze and processing. The Grumwald-Letnikov (G-L) definition of fractional differentiation is in Euclidean space in the paper, and it is the results that differential order is extended from integral step-size to fractional step-size. Additionally, it should be known that there are a lot of textures in a fabric image. The fractional differentiation is a continuation of integer-order differentiation, thus similarly the fractional differential operator can also realize sharpening enhancement of image textures. By the analysis of amplitude-frequency characteristics, fractional differentiation can highlight the fabric image edges, improve the fabric textures and nonlinearly keep the details of the fabric image smooth areas; By the analysis of detection between stability coefficients and image textures in the dynamic theory, fractional differentiation not only nonlinearly enhances the contour features in the low-frequency area, but also highlights high-frequency edge features in those areas where gray changes remarkably; From the coefficients of fractional differential polynomial, isotropic operator is constructed to enhance fabric images. Through the respective experiments of defect images for gray fabric and yarn-dyed fabric, the effectiveness of enhancement for fabric texture image is proved by qualitative and quantitative methods. Based on the texture edge map of enhanced fabric image, the favorable enhancement is also confirmed indirectly by region homogeneity measure.
Fourth, the paper designs and realizes the algorithm of intelligent defect detection of yarn-dyed fabrics by energy-based local binary patterns. Its purpose is to finish fast and effective detection of defects of yarn-dyed fabric via computer vision, and to consider two kinds of texture characteristics, that is, color and structure. The algorithm process is as follows:(1) The yarn-dyed fabric image enhanced by fractional differentiation is first converted from RGB true color space to L*a*b*color space.(2) In this color space, energy-based feature images are acquired by image fusion after the Log-Gabor filter filters chromatic and brightness component images. It solves the problem that color and structure defects can be appeared in the same energy feature image.(3) Through the analysis of energy-based feature images for yarn-dyed fabrics, the defects usually are locally brighter areas that have irregularity and non-uniformity and range from several pixels to dozens of pixels. The normal patterns in the background are regular and uniform. Therefore, with the help of the appropriate mechanism of scanning and comparing, what is needed is a local operator of the textures that could be used to detect defects in the energy-based feature images. The relations between energy and the local binary pattern are defined as a new concept called energy-based local binary patterns (ELBP), and the operator has the invariability for simple affine deformation.(4) Based on the minimum repeat pattern units in the defective reference images and testing images, many windows are segmented uniformly, and the ELBP feature vectors are obtained for each definition window in the energy-based feature images.(5) The defective threshold is found by likelihood estimation in the training stage. The defective windows are detected by comparing the threshold with detection windows of tested images in the detection stage, which can segment defect area. The proposed method can detect chromatic and structural defects. Experimental results for the defect detection from several collections of yarn-dyed fabrics indicate that a detection success rate of more than94.09%is achieved for the proposed method. The speed of test is also fast, and it is suitable for off-line testing.
Finally, the paper explores 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. This section firstly introduces the extraction of combination feature set. The geometrical features are defined, such as weft length, warp length, weft length to warp length ratio, perimeter, area, and roundness, and six geometrical parameters are extracted from the binary defect images. Concurrently, three textural parameters that characterize coarseness, contrast, and directionality can be defined and extracted on the basis of the textural energy defect images. The extraction processes of two types of feature parameters can combine into the extractor of combination features. The combination feature set which outputs in the extractor can quantitatively descript the surface characteristics of yarn-dyed fabric defects. 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/T22851-2009), that are cracked-ends (slack-ends, double-ends and mix-end), reedmark, broken picks (double-pick and looped-weft), weft-crackiness, hole (float, knot and gout), and stain (burl-mark, bruise and pan-color). This chapter then discusses the radial basis kernel SVM classifier and the optimization of general SVM classification model. Since the effectiveness of the SVM classification scheme largely depends on the selection of the classifier parameters, a 'grid searching' procedure is used to determine the best selection of two parameters to achieve the highest classification accuracy in the application. When the combined feature set is used as the inputs of the SVM classifier, the LOOCV (leave-one-out cross-validation) is designed to avoid the biased classifications. The experiment samples are180fabric defect images for three types of yarn-dyed fabrics with different patterns. The cross-validation test on the yarn-dyed fabric defect classifications indicates that the defect categories of more than91%can be recognized correctly by using the SVM classification scheme. Compared with the accuracy of89.4%for BPNN, this algorithm is more robust and effective.
引文
[1]Srinivasan K., Dastoor P., Radhakrishnaiah P., et al. FDAS:a knowledge-based framework for analysis of defects in woven textile structures[J]. Journal of the Textile Institute.1992, 83(3):431-448.
[2]Wijayasiri Kulatunga A.D. Analysis of Wastage Caused by Fabric Defects[M//OL]. http://www.fibre2fashion.com,2010:1-8.
[3]郑广,周万珍,马红霞,et al.基于图像距离差的织物疵点检测算法研究[J].河北科技大学学报.2006,27(3)：239-241.
[4]龚艳军.布匹疵点自动检测系统的研究和设计[D].武汉：华中科技大学,2005.
[5]Huart J., Postaire J.G. Integration of computer vision onto weavers for quality control in the textile industry[C]. in Proc. SPIE.1994:155-163.
[6]Dorrity J., Vachtsevanos G. On-line defect detection for weaving systems[C]. in Proc. IEEE Annu. Tech. Conf. Textile, Fiber, Film, Ind.1996:1-6.
[7]Rosandich R.G. Intelligent visual inspection:using artificial neural networks[M]. London, U.K.:Chapman & Hall.1997.
[8]章毓晋.图像工程(下册)——图像理解与计算机视觉[M].北京：清华大学.2000.
[9]尚会超,吴军.织物表面疵点检测算法综述[J].中原工学院学报.2008,19(1)：16-18.
[10]Nickolay B., Schicktanz K., Schmaltuss H. Automatic fabric inspection-utopia or reality?[J]. Melliand Textilberichte International Textile Reports.1993,74(1):33-37.
[11]Dockery A. Automated fabric inspection:assessing the current state of the art[M//OL]. http://www.techexchange.com,2001:1-4.
[12]Bieri M.,何志贵,黎明.策尔韦格·乌斯特公司的Fabriscan织物自动检验系统[J].国外纺织技术.2001,测试与分析卷(11)：41-42.
[13]何志贵,魏丽琼I-TEX2000型织物自动检验系统[J].国外纺织技术.2000,测试与分析卷(12)：36-37.
[14]李立轻.基于计算机视觉的织物疵点自动检测研究[D].上海：东华大学,2003.
[15]邹超.布匹疵点在线检测系统研究[D].武汉：华中科技大学,2009.
[16]付蓉,石美红,徐步高.基于窗阈值局部二值模式的织物疵点检测算法[J].计算机集成制造系统.2010,16(9)：2009-2015.
[17]Newman T.S., Jain A.K. A survey of automated visual inspection[J]. Computer Vision and Image Understanding.1995,61(2):231-262.
[18]李立轻,黄秀宝.图像处理用于织物疵点自动检测的研究进展[J].东华大学学报：自然科学版.2002,28(4)：118-122.
[19]步红刚,黄秀宝.基于计算机视觉的织物疵点检测的近期进展[J].东华大学学报：自然科学版.2006,32(3)：128-133.
[20]Kumar A. Computer-vision-based fabric defect detection:a survey[J]. IEEE Transactions on Industrial Electronics.2008,55(1):348-363.
[21]Xie X. A review of recent advances in surface defect detection using texture analysis techniques[J]. Electronic Letters on Computer Vision and Image Analysis.2008,7(3):1-22.
[22]邹超,汪秉文,孙志刚.基于机器视觉的织物疵点检测方法综述[J].天津工业大学学报.2009,28(2)：78-82.
[23]Mahajan P., Kolhe S., Patil P. A review of automatic fabric defect detection techniques[J]. Advances in Computational Research.2009,1(2):18-29.
[24]Conci A., Proena C.B. A fractal image analysis system for fabric inspection based on a box-counting method[J]. Computer Networks and ISDN systems.1998,30(20):1887-1895.
[25]Stojanovic R., Mitropulos P., Koulamas C., et al. Real-time vision-based system for textile fabric inspection[J]. Real-Time Imaging.2001,7(6):507-518.
[26]Norton-Wayne L., Bradshaw M., Sanby C. Machine vision for the automated inspection of web materials[C]. in Proc. SPIE.1993:2-17.
[27]Norton-Wayne L., Bradshaw M., Jewell A. Machine vision inspection of web textile fabric[C]. in Proc. Brit. Mach. Vis. Leeds, U.K.1992:217-226.
[28]Zhang Y.F., Bresee R.R. Fabric defect detection and classification using image analysis[J]. Textile Research Journal.1995,65(1):1-9.
[29]Chandra J.K., Banerjee P.K., Datta A.K. Neural network trained morphological processing for the detection of defects in woven fabric[J]. Journal of the Textile Institute.2010,101(8): 699-706.
[30]Lane J.S. Textile fabric inspection system[P]. Google Patents, U.S.5774177,1998.
[31]Bodnarova A., Bennamoun M., Kubik K. Defect detection in textile materials based on aspects of the HVS[C]. in Proc. IEEE SMC. San Diego, CA.1998:4423-4428.
[32]Siew L.H., Hodgson R.M., Wood E.J. Texture measures for carpet wear assessment[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1988,10(1):92-105.
[33]Tsai I. Applying an artificial neural network to pattern recognition in fabric defects[J]. Textile Research Journal.1995,65(3):123-130.
[34]Rosler R. Defect detection of fabrics by image processing[J]. Melliand Texilber.1992,73: 635-636.
[35]Ade F., Lins N., Unser M. Comparison of various filter sets for defect detection in textiles[C]. in Proc.7th Int. Conf. Pattern Recog. Montreal, QC.Canada. IEEE Computer Society Press.1984:428-431.
[36]Neubauer C. Segmentation of defects in textile fabric[C]. in Proc.11th Int.Conf. Pattern Recog.1992:688-691.
[37]Davies E.R. Machine vision:theory, algorithms, practicalities[M]. London:Academic press. 1997.
[38]Kumar A. Neural network based detection of local textile defects[J]. Pattern Recognition. 2003,36(7):1645-1659.
[39]Huang C.C., Chen I. Neural-fuzzy classification for fabric defects[J]. Textile Research Journal.2001,71(3):220-224.
[40]Kumar A., Shen H.C. Texture inspection for defects using neural networks and support vector machines[C]. in Proc. ICIP. Rochester, NY. IEEE.2002:353-356.
[41]Tsai D.M., Hsieh C.Y. Automated surface inspection for directional textures[J]. Image and Vision Computing.1999,18(1):49-62.
[42]Castellini C., Francini F., Longobardi G., et al. On-line textile quality control using optical Fourier transforms[J]. Optics and Lasers in Engineering.1996,24(1):19-32.
[43]Campbell J.G., Murtagh F. Automatic visual inspection of woven textiles using a two-stage defect detector[J]. Optical Engineering.1998,37(9):2536-2542.
[44]Bovik A.C., Clark M., Geisler W.S. Multichannel texture analysis using localized spatial filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1990,12(1):55-73.
[45]Escofet J., Navarro R., Millan M.S., et al. Detection of local defects in textile webs using Gabor filters[J]. Optical Engineering.1998,37(8):2297-2307.
[46]Kumar A., Pang G.K.H. Defect detection in textured materials using Gabor filters[J]. IEEE Transactions on Industry Applications.2002,38(2):425-440.
[47]Kumar A., Pang K.H.G. Defect detection system for quality assurance using automated visual inspection[P]. U.S. Patent 6753965,2004.
[48]Sari-Sarraf H., Goddard Jr J.S. Vision system for on-loom fabric inspection[J]. IEEE Transactions on Industry Applications.1999,35(6):1252-1259.
[49]Kim S., Lee M.H., Woo K.B. Wavelet analysis to fabric defects detection in weaving processes[C]. in Proc. IEEE Int. Symp. Ind. Electron. IEEE Press.1999:1406-1409.
[50]Cohen F.S., Fan Z., Attali S. Automated inspection of textile fabrics using textural models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1991,13(8):803-808.
[51]Brzakovic D., Bakic P., Vujovic N., et al. A generalized development environment for inspection of web materials[C]. in Proc. IEEE Int. Conf. Robot. Autom. Albuquerque, NM. 1997:1-8.
[52]Brzakovic D.P., Vujovic N.S., Liakopoulos A. Approach to quality control of texture web materials[C]. Proc. SPIE.1995:60-69.
[53]Campbell J., Fraley C., Murtagh F., et al. Linear flaw detection in woven textiles using model-based clustering[J]. Pattern Recognition Letters.1997,18(14):1539-1548.
[54]潘如如,高卫东,钱欣欣,et al.基于互相关的印花织物疵点检测[J].纺织学报.2010,31(12)：134-138.
[55]Ngan H.Y.T., Pang G.K.H., Yung N.H.C. Motif-based defect detection for patterned fabric[J]. Pattern Recognition.2008,41(6):1878-1894.
[56]Tajeripour F., Kabir E., Sheikhi A. Defect Detection in Patterned Fabrics Using Modified Local Binary Patterns[C]. in International Conference on Computational Intelligence and Multimedia Applications.2007:261-267.
[57]Bureau C.I.D.L.E.C.C. Colorimetry[R]. CIE 15:2004,3rd Edition:16-20.
[58]Ford A., Roberts A. Colour Space Conversions[M//OL]. http://www.poynton.com/PDFs /coloureq.pdf,1998.
[59]Caelli T., Reye D. On the classification of image regions by colour, texture and shape[J]. Pattern Recognition.1993,26(4):461-470.
[60]Haindl M. Texture segmentation using recursive markov random field parameter estimation[C]. in Scandinavian Conference on Image Analysis.1999:771-776.
[61]Haindl M., Havlicek V. A simple multispectral multiresolution Markov texture model[C].in International Workshop on Texture Analysis and Synthesis.2002:63-66.
[62]Menp T., Viertola J., Pietik Inen M. Optimising colour and texture features for real-time visual inspection[J]. Pattern Analysis & Applications.2003,6(3):169-175.
[63]Paschos G., Valavanis F. A color texture based visual monitoring system for automated surveillance[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews.1999,29(2):298-307.
[64]Dubuisson-Jolly M.P., Gupta A. Color and texture fusion:application to aerial image segmentation and GIS updating[J]. Image and Vision Computing.2000,18(10):823-832.
[65]Liapis S., Sifakis E., Tziritas G. Colour and texture segmentation using wavelet frame analysis, deterministic relaxation, and fast marching algorithms[J]. Journal of Visual Communication and Image Representation.2004,15(1):1-26.
[66]Tsai D.M., Lin C.P., Huang K.T. Defect detection in coloured texture surfaces using Gabor filters[J]. Imaging Science Journal.2005,53(1):27-37.
[67]Rosenfeld A., Wang C., Wu A. Multispectral Texture[J]. IEEE Transactions on Systems, Man, and Cybernetics.1982,12(1):79-84.
[68]Panjwani D.K., Healey G. Markov random field models for unsupervised segmentation of textured color images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1995,17(10):939-954.
[69]Jain A., Healey G. A multiscale representation including opponent color features for texture recognition[J]. IEEE Transactions on Image Processing.1998,7(1):124-128.
[70]Mirmehdi M., Petrou M. Segmentation of color textures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(2):142-159.
[71]Kittler J., Marik R., Mirmehdi M., et al. Detection of defects in colour texture surfaces[J]. IAPR Machine Vision Applications.1994(12):558-567.
[72]Tomoya Notsu M.M., Kensaku Fujii. An Automated Arrangement Inspection for Yarn Dyed Fabric[C]. in World Automation Congress. Kobe. TSI Press.2010:1-6.
[73]Jojic N., Frey B.J., Kannan A. Epitomic analysis of appearance and shape[C]. in IEEE International Conference on Computer Vision.2003:34-42.
[74]Xie X., Mirmehdi M. TEXEMS:Texture exemplars for defect detection on random textured surfaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2007,29(8): 1454-1464.
[75]Batchelor B. Lighting and viewing techniques[M]. Kempston:IFS Publications 1985:103-179.
[76]Beyer H.A. Performance analysis of CCD cameras for industrial inspection[C]. in Proc. SPIE.1993:40-49.
[77]Pang G., Wong R., Liu H., et al. CAVIS:A low-cost fabric defect inspection machine based on Machine Vision[C]. in Proc. Asian Textile.2001:11-16.
[78]Jain R., Kasturi R., Schunck B.G. Machine vision[M]:McGraw-Hill New York.1995.
[79]Haralick R.M., Shanmugam K., Dinstein I. Textural features for image classification[J]. IEEE Transactions on Systems, Man and Cybernetics.1973,3(6):610-621.
[80]Conners R.W., Harlow C.A. A theoretical comparison of texture algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1980(3):204-222.
[81]Lippmann R.P. An introduction to computing with neural nets[J]. IEEE ASSP Magasine. 1987,3(4):4-22.
[1]Li W.Y., Cheng L.D. An Image Measuring Method for the Fabric Defect Detection System[J]. Applied Mechanics and Materials.2013,333-335:1789-1792.
[2]王庆有.CCD应用技术[M].天津：天津大学出版社.2000：27.
[3]赵大兴.基于机器视觉的坯布表面质量检测系统研究与实现[D].沈阳：东北大学,2008.
[4]党宏社,洪英,郭琴.基于图像处理的不规则形体面积测量系统的实现[J].计算机测量与控制.2010,18(7)：1507-1508.
[5]常春国,徐运涛.应用机器视觉精确检测工件尺寸的研究[J].电子质量.2008,测试技术卷(2)：1-4.
[6]贺赛先,王新华.一个基于图像测量的工业尺寸测量系统[J].测绘通报.1997,(5)：25-27.
[7]王新新,张广秀,徐江伟.一种多线阵CCD扫描系统的标定纸及调整方法[P].201110433227.1,2013-06-26.
[8]周委,陈思平,赵文龙,et a1.基于DSP EMIF口及FPGA设计并实现多DSP嵌入式系统[J].电子技术应用.2008,(6)：39-42.
[9]高晓丁,左贺,辛文辉.基于多片DSP+FPGA结构的织物自动检测系统设计与实现[J].中国测试技术.2007,33(4)：95-98.
[10]梁义涛,傅洪亮,杨铁军.现代DSP技术及应用[M].北京：清华大学出版社.2012：6.
[11]书金辰,李刚,王臣业.零点起步——fMS320C6000系列DSP原理与应用系统设计[M].北京：机械工业出版社.2012：20.
[12]孙尧.纬编针织物疵点实时智能检测的研究[D].上海：东华大学,2010.
[1]Li W., Xue W., Cheng L. Intelligent detection of defects of yarn-dyed fabrics by energy-based local binary patterns[J]. Textile Research Journal.2012,82(19):1960-1972.
[2]Pan R., Gao W., Liu J., et al. Automatic inspection of double-system-melange yarn-dyed fabric density with color-gradient image[J]. Fibers and Polymers.2011,12(1):127-131.
[3]Bao P., Zhang L., Wu X. Canny edge detection enhancement by scale multiplication[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2005,27(9):1485-1490.
[4]Ziou D., Tabbone S. Edge detection techniques-an overview[J]. Pattern Recognition and Image Analysis 1998,8(4):537-559.
[5]Loverro A. Fractional calculus:history, definitions and applications for the engineer[R]. Department of Aerospace and Mechanical Engineering, Notre Dame, U.S.A,2004.
[6]Liu S.C., Chang S. Dimension estimation of discrete-time fractional Brownian motion with applications to image texture classification[J]. IEEE Transactions on Image Processing.1997, 6(8):1176-1184.
[7]Leu J.S., Papamarcou A. On estimating the spectral exponent of fractional Brownian motion[J]. IEEE Transactions on Information Theory.1995,41(1):233-244.
[8]Engheta N. On fractional calculus and fractional multipoles in electromagnetism[J]. IEEE Transactions on Antennas and Propagation.1996,44(4):554-566.
[9]Oldham K.B., Spanier J. The fractional calculus[M]. New York/London:Academic Press. 1974.
[10]杨柱中,周激流,晏祥玉,et a1.基于分数阶微分的图像增强[J].计算机辅助设计与图形学学报.2008,20(3)：343-348.
[11]蒲亦非,王卫星,周激流,et a1.数字图像纹理细节的分数阶微分检测及其分数阶微分滤波器实现[J].中国科学E辑：信息科学.2008,38(12)：2252-2272.
[12]杨烜,梁德群.一种基于区域一致性测度的边缘评价方法[J].中国图象图形学报.1999,4(3)：234-238.
[13]Mathieu B., Melchior P., Oustaloup A., et al. Fractional differentiation for edge detection[J]. Signal Processing.2003,83(11):2421-2432.
[1]Bennamoun M., Bodnarova A. Automatic visual inspection and flaw detection in textile materials:Past, present and future[C]. in IEEE International Conference on SMC.1998: 4340-4343.
[2]Mak K., Peng P., Yiu K. Fabric defect detection using morphological filters[J]. Image and Vision Computing.2009,27(10):1585-1592.
[3]Cho C.S., Chung B.M., Park M.J. Development of real-time vision-based fabric inspection system[J]. IEEE Transactions on Industrial Electronics.2005,52(4):1073-1079.
[4]Bu H.G., Huang X.B., Wang J., et al. Detection of Fabric Defects by Auto-Regressive Spectral Analysis and Support Vector Data Description[J]. Textile Research Journal.2010, 80(7):579-589.
[5]Shi M., Jiang S., Wang H., et al. A Simplified pulse-coupled neural network for adaptive segmentation of fabric defects[J]. Machine Vision and Applications.2009,20(2):131-138.
[6]Ozdemir S., Ercil A. Markov random fields and karhunen-loeve transforms for defect inspection of textile products[C]. in IEEE International Conference on EFTA.1996:697-703.
[7]Ngan H.Y.T., Pang G.K.H., Yung S., et al. Wavelet based methods on patterned fabric defect detection[J]. Pattern Recognition.2005,38(4):559-576.
[8]Tajeripour F., Kabir E., Sheikhi A. Fabric defect detection using modified local binary patterns[J]. EURASIP Journal on Advances in Signal Processing.2008,2008:1-12.
[9]Song K., Kittler J., Petrou M. Defect detection in random colour textures[J]. Image and Vision Computing.1996,14(9):667-683.
[10]Lin J.J. Pattern Recognition of Fabric Defects Using Case-Based Reasoning[J]. Textile Research Journal.2010,80(9):794-802.
[11]Ojala T., Pietik Inen M., M Enp T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24:971-987.
[12]Tsai D.M., Lin C.P., Huang K.T. Defect detection in coloured texture surfaces using Gabor filters[J]. Imaging Science Journal.2005,53(1):27-37.
[13]Field D.J. Relations between the statistics of natural images and the response properties of cortical cells[J]. Journal of Optical Society of American.1987,4(12):2379-2394.
[14]Bodmarova A., Bennamoun M., Kubik K. Suitability analysis of techniques for flaw detection in textiles using texture analysis[J]. Pattern Analysis & Applications.2000,3(3): 254-266.
[1]Bu H., Huang X. Recent progress of computer-vision-based fabric defects classification[J]. Journal of Donghua University (Natural Science).2006,32:143-146.
[2]Shi M., Jiang S., Wang H., et al. A Simplified pulse-coupled neural network for adaptive segmentation of fabric defects[J]. Machine Vision and Applications.2009,20(2):131-138.
[3]Yang X.Z., Pang G., Yung N. Discriminative training approaches to fabric defect classification based on wavelet transform[J]. Pattern Recognition.2004,37(5):889-899.
[4]Kondo H., Okuyama M., Saito Y. Defect classification/inspection system[P]. U.S. Patent(10/222431),2003.
[5]Balakrishnan H., Venkataraman S., Jayaraman S. FDICS:A vision-based system for the identification and classification of fabric defects[J]. Journal of the Textile Institute.1998, 89(2):365-380.
[6]Kuo C.F.J., Su T.L. Gray relational analysis for recognizing fabric defects[J]. Textile Research Journal.2003,73(5):461-465.
[7]Murino V., Bicego M., Rossi I.A. Statistical classification of raw textile defects[C]. in Proceedings of the 17th International Conference on Pattern Recognition.2004:311-314.
[8]Lin J.-J. Pattern recognition of fabric defects using case-based reasoning[J]. Textile Research Journal.2010,80(9):794-802.
[9]Ghosh A., Guha T., Bhar R.B., et al. Pattern classification of fabric defects using support vector machines[J]. International Journal of Clothing Science and Technology.2011,23(2-3): 142-151.
[10]Kuo C.F.J., Lee C.J. A back-propagation neural network for recognizing fabric defects[J]. Textile Research Journal.2003,73(2):147-151.
[11]Tarek Habib M., Rokonuzzaman M. A set of geometric features for neural network-based textile defect classification[J]. ISRN Artificial Intelligence.2012,2012:1-16.
[12]Tabassian M., Ghaderi R., Ebrahimpour R. Knitted fabric defect classification for uncertain labels based on Dempster-Shafer theory of evidence[J]. Expert Systems with Applications. 2011,38(5):5259-5267.
[13]Schmitt E., Bombardier V., Wendling L. Fuzzy rule iterative feature selection (FRIFS) with respect to the choquet integral apply to fabric defect recognition[C]. in Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems.2008: 708-718.
[14]Zhang Y., Lu Z.Y., Li J. Fabric defect classification using radial basis function network[J]. Pattern Recognition Letters.2010,31(13):2033-2042.
[15]Li W., Xue W., Cheng L. Intelligent detection of defects of yarn-dyed fabrics by energy-based local binary patterns[J]. Textile Research Journal.2012,82(19):1960-1972.
[16]AQSIQ. Yarn-dyed pattern fabric[S]. National Standards of the People's Republic of China, 2009. GB/T 22851-2009.
[17]Tamura H., Mori S., Yamawaki T. Texture features corresponding to visual perception[J]. IEEE Transactions on Systems, Man and Cybernetics.1978,8:460-473.
[18]Hsu C.W., Chang C.C., Lin C.J. A practical guide to support vector classification[M//OL]. 2010. Available from:http://www.csie.ntu.edu.tw/-cjlin/papers/guide/guide.pdf.
[19]Boser E., Guyon I., Vapnik V. A training algorithm for optimal margin classiers[C]. in Proceedings of the Fifth Annual Workshop on Computational Learning Theory.1992:144- 152.
[20]Cortes C., Vapnik V. Support-vector network[J]. Machine Learning.1995,20:273-297.
[21]Hsu C.W., Lin C.J. A comparison of methods for multiclass support vector machines[J]. IEEE Transactions on Neural Networks.2002,13(2):415-425.
[22]Chang C.C., Lin C.J. LIBSVM:a library for support vector machines[M//OL].2011. Available from:http://www.csie.ntu.edu.tw/-cjlin/papers/libsvm.pdf.
[2]Wijayasiri Kulatunga A.D. Analysis of Wastage Caused by Fabric Defects[M//OL]. http://www.fibre2fashion.com,2010:1-8.
[3]郑广,周万珍,马红霞,et al.基于图像距离差的织物疵点检测算法研究[J].河北科技大学学报.2006,27(3)：239-241.
[4]龚艳军.布匹疵点自动检测系统的研究和设计[D].武汉：华中科技大学,2005.
[5]Huart J., Postaire J.G. Integration of computer vision onto weavers for quality control in the textile industry[C]. in Proc. SPIE.1994:155-163.
[6]Dorrity J., Vachtsevanos G. On-line defect detection for weaving systems[C]. in Proc. IEEE Annu. Tech. Conf. Textile, Fiber, Film, Ind.1996:1-6.
[7]Rosandich R.G. Intelligent visual inspection:using artificial neural networks[M]. London, U.K.:Chapman & Hall.1997.
[8]章毓晋.图像工程(下册)——图像理解与计算机视觉[M].北京：清华大学.2000.
[9]尚会超,吴军.织物表面疵点检测算法综述[J].中原工学院学报.2008,19(1)：16-18.
[10]Nickolay B., Schicktanz K., Schmaltuss H. Automatic fabric inspection-utopia or reality?[J]. Melliand Textilberichte International Textile Reports.1993,74(1):33-37.
[11]Dockery A. Automated fabric inspection:assessing the current state of the art[M//OL]. http://www.techexchange.com,2001:1-4.
[12]Bieri M.,何志贵,黎明.策尔韦格·乌斯特公司的Fabriscan织物自动检验系统[J].国外纺织技术.2001,测试与分析卷(11)：41-42.
[13]何志贵,魏丽琼I-TEX2000型织物自动检验系统[J].国外纺织技术.2000,测试与分析卷(12)：36-37.
[14]李立轻.基于计算机视觉的织物疵点自动检测研究[D].上海：东华大学,2003.
[15]邹超.布匹疵点在线检测系统研究[D].武汉：华中科技大学,2009.
[16]付蓉,石美红,徐步高.基于窗阈值局部二值模式的织物疵点检测算法[J].计算机集成制造系统.2010,16(9)：2009-2015.
[17]Newman T.S., Jain A.K. A survey of automated visual inspection[J]. Computer Vision and Image Understanding.1995,61(2):231-262.
[18]李立轻,黄秀宝.图像处理用于织物疵点自动检测的研究进展[J].东华大学学报：自然科学版.2002,28(4)：118-122.
[19]步红刚,黄秀宝.基于计算机视觉的织物疵点检测的近期进展[J].东华大学学报：自然科学版.2006,32(3)：128-133.
[20]Kumar A. Computer-vision-based fabric defect detection:a survey[J]. IEEE Transactions on Industrial Electronics.2008,55(1):348-363.
[21]Xie X. A review of recent advances in surface defect detection using texture analysis techniques[J]. Electronic Letters on Computer Vision and Image Analysis.2008,7(3):1-22.
[22]邹超,汪秉文,孙志刚.基于机器视觉的织物疵点检测方法综述[J].天津工业大学学报.2009,28(2)：78-82.
[23]Mahajan P., Kolhe S., Patil P. A review of automatic fabric defect detection techniques[J]. Advances in Computational Research.2009,1(2):18-29.
[24]Conci A., Proena C.B. A fractal image analysis system for fabric inspection based on a box-counting method[J]. Computer Networks and ISDN systems.1998,30(20):1887-1895.
[25]Stojanovic R., Mitropulos P., Koulamas C., et al. Real-time vision-based system for textile fabric inspection[J]. Real-Time Imaging.2001,7(6):507-518.
[26]Norton-Wayne L., Bradshaw M., Sanby C. Machine vision for the automated inspection of web materials[C]. in Proc. SPIE.1993:2-17.
[27]Norton-Wayne L., Bradshaw M., Jewell A. Machine vision inspection of web textile fabric[C]. in Proc. Brit. Mach. Vis. Leeds, U.K.1992:217-226.
[28]Zhang Y.F., Bresee R.R. Fabric defect detection and classification using image analysis[J]. Textile Research Journal.1995,65(1):1-9.
[29]Chandra J.K., Banerjee P.K., Datta A.K. Neural network trained morphological processing for the detection of defects in woven fabric[J]. Journal of the Textile Institute.2010,101(8): 699-706.
[30]Lane J.S. Textile fabric inspection system[P]. Google Patents, U.S.5774177,1998.
[31]Bodnarova A., Bennamoun M., Kubik K. Defect detection in textile materials based on aspects of the HVS[C]. in Proc. IEEE SMC. San Diego, CA.1998:4423-4428.
[32]Siew L.H., Hodgson R.M., Wood E.J. Texture measures for carpet wear assessment[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1988,10(1):92-105.
[33]Tsai I. Applying an artificial neural network to pattern recognition in fabric defects[J]. Textile Research Journal.1995,65(3):123-130.
[34]Rosler R. Defect detection of fabrics by image processing[J]. Melliand Texilber.1992,73: 635-636.
[35]Ade F., Lins N., Unser M. Comparison of various filter sets for defect detection in textiles[C]. in Proc.7th Int. Conf. Pattern Recog. Montreal, QC.Canada. IEEE Computer Society Press.1984:428-431.
[36]Neubauer C. Segmentation of defects in textile fabric[C]. in Proc.11th Int.Conf. Pattern Recog.1992:688-691.
[37]Davies E.R. Machine vision:theory, algorithms, practicalities[M]. London:Academic press. 1997.
[38]Kumar A. Neural network based detection of local textile defects[J]. Pattern Recognition. 2003,36(7):1645-1659.
[39]Huang C.C., Chen I. Neural-fuzzy classification for fabric defects[J]. Textile Research Journal.2001,71(3):220-224.
[40]Kumar A., Shen H.C. Texture inspection for defects using neural networks and support vector machines[C]. in Proc. ICIP. Rochester, NY. IEEE.2002:353-356.
[41]Tsai D.M., Hsieh C.Y. Automated surface inspection for directional textures[J]. Image and Vision Computing.1999,18(1):49-62.
[42]Castellini C., Francini F., Longobardi G., et al. On-line textile quality control using optical Fourier transforms[J]. Optics and Lasers in Engineering.1996,24(1):19-32.
[43]Campbell J.G., Murtagh F. Automatic visual inspection of woven textiles using a two-stage defect detector[J]. Optical Engineering.1998,37(9):2536-2542.
[44]Bovik A.C., Clark M., Geisler W.S. Multichannel texture analysis using localized spatial filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1990,12(1):55-73.
[45]Escofet J., Navarro R., Millan M.S., et al. Detection of local defects in textile webs using Gabor filters[J]. Optical Engineering.1998,37(8):2297-2307.
[46]Kumar A., Pang G.K.H. Defect detection in textured materials using Gabor filters[J]. IEEE Transactions on Industry Applications.2002,38(2):425-440.
[47]Kumar A., Pang K.H.G. Defect detection system for quality assurance using automated visual inspection[P]. U.S. Patent 6753965,2004.
[48]Sari-Sarraf H., Goddard Jr J.S. Vision system for on-loom fabric inspection[J]. IEEE Transactions on Industry Applications.1999,35(6):1252-1259.
[49]Kim S., Lee M.H., Woo K.B. Wavelet analysis to fabric defects detection in weaving processes[C]. in Proc. IEEE Int. Symp. Ind. Electron. IEEE Press.1999:1406-1409.
[50]Cohen F.S., Fan Z., Attali S. Automated inspection of textile fabrics using textural models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1991,13(8):803-808.
[51]Brzakovic D., Bakic P., Vujovic N., et al. A generalized development environment for inspection of web materials[C]. in Proc. IEEE Int. Conf. Robot. Autom. Albuquerque, NM. 1997:1-8.
[52]Brzakovic D.P., Vujovic N.S., Liakopoulos A. Approach to quality control of texture web materials[C]. Proc. SPIE.1995:60-69.
[53]Campbell J., Fraley C., Murtagh F., et al. Linear flaw detection in woven textiles using model-based clustering[J]. Pattern Recognition Letters.1997,18(14):1539-1548.
[54]潘如如,高卫东,钱欣欣,et al.基于互相关的印花织物疵点检测[J].纺织学报.2010,31(12)：134-138.
[55]Ngan H.Y.T., Pang G.K.H., Yung N.H.C. Motif-based defect detection for patterned fabric[J]. Pattern Recognition.2008,41(6):1878-1894.
[56]Tajeripour F., Kabir E., Sheikhi A. Defect Detection in Patterned Fabrics Using Modified Local Binary Patterns[C]. in International Conference on Computational Intelligence and Multimedia Applications.2007:261-267.
[57]Bureau C.I.D.L.E.C.C. Colorimetry[R]. CIE 15:2004,3rd Edition:16-20.
[58]Ford A., Roberts A. Colour Space Conversions[M//OL]. http://www.poynton.com/PDFs /coloureq.pdf,1998.
[59]Caelli T., Reye D. On the classification of image regions by colour, texture and shape[J]. Pattern Recognition.1993,26(4):461-470.
[60]Haindl M. Texture segmentation using recursive markov random field parameter estimation[C]. in Scandinavian Conference on Image Analysis.1999:771-776.
[61]Haindl M., Havlicek V. A simple multispectral multiresolution Markov texture model[C].in International Workshop on Texture Analysis and Synthesis.2002:63-66.
[62]Menp T., Viertola J., Pietik Inen M. Optimising colour and texture features for real-time visual inspection[J]. Pattern Analysis & Applications.2003,6(3):169-175.
[63]Paschos G., Valavanis F. A color texture based visual monitoring system for automated surveillance[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews.1999,29(2):298-307.
[64]Dubuisson-Jolly M.P., Gupta A. Color and texture fusion:application to aerial image segmentation and GIS updating[J]. Image and Vision Computing.2000,18(10):823-832.
[65]Liapis S., Sifakis E., Tziritas G. Colour and texture segmentation using wavelet frame analysis, deterministic relaxation, and fast marching algorithms[J]. Journal of Visual Communication and Image Representation.2004,15(1):1-26.
[66]Tsai D.M., Lin C.P., Huang K.T. Defect detection in coloured texture surfaces using Gabor filters[J]. Imaging Science Journal.2005,53(1):27-37.
[67]Rosenfeld A., Wang C., Wu A. Multispectral Texture[J]. IEEE Transactions on Systems, Man, and Cybernetics.1982,12(1):79-84.
[68]Panjwani D.K., Healey G. Markov random field models for unsupervised segmentation of textured color images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1995,17(10):939-954.
[69]Jain A., Healey G. A multiscale representation including opponent color features for texture recognition[J]. IEEE Transactions on Image Processing.1998,7(1):124-128.
[70]Mirmehdi M., Petrou M. Segmentation of color textures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(2):142-159.
[71]Kittler J., Marik R., Mirmehdi M., et al. Detection of defects in colour texture surfaces[J]. IAPR Machine Vision Applications.1994(12):558-567.
[72]Tomoya Notsu M.M., Kensaku Fujii. An Automated Arrangement Inspection for Yarn Dyed Fabric[C]. in World Automation Congress. Kobe. TSI Press.2010:1-6.
[73]Jojic N., Frey B.J., Kannan A. Epitomic analysis of appearance and shape[C]. in IEEE International Conference on Computer Vision.2003:34-42.
[74]Xie X., Mirmehdi M. TEXEMS:Texture exemplars for defect detection on random textured surfaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2007,29(8): 1454-1464.
[75]Batchelor B. Lighting and viewing techniques[M]. Kempston:IFS Publications 1985:103-179.
[76]Beyer H.A. Performance analysis of CCD cameras for industrial inspection[C]. in Proc. SPIE.1993:40-49.
[77]Pang G., Wong R., Liu H., et al. CAVIS:A low-cost fabric defect inspection machine based on Machine Vision[C]. in Proc. Asian Textile.2001:11-16.
[78]Jain R., Kasturi R., Schunck B.G. Machine vision[M]:McGraw-Hill New York.1995.
[79]Haralick R.M., Shanmugam K., Dinstein I. Textural features for image classification[J]. IEEE Transactions on Systems, Man and Cybernetics.1973,3(6):610-621.
[80]Conners R.W., Harlow C.A. A theoretical comparison of texture algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1980(3):204-222.
[81]Lippmann R.P. An introduction to computing with neural nets[J]. IEEE ASSP Magasine. 1987,3(4):4-22.
[1]Li W.Y., Cheng L.D. An Image Measuring Method for the Fabric Defect Detection System[J]. Applied Mechanics and Materials.2013,333-335:1789-1792.
[2]王庆有.CCD应用技术[M].天津：天津大学出版社.2000：27.
[3]赵大兴.基于机器视觉的坯布表面质量检测系统研究与实现[D].沈阳：东北大学,2008.
[4]党宏社,洪英,郭琴.基于图像处理的不规则形体面积测量系统的实现[J].计算机测量与控制.2010,18(7)：1507-1508.
[5]常春国,徐运涛.应用机器视觉精确检测工件尺寸的研究[J].电子质量.2008,测试技术卷(2)：1-4.
[6]贺赛先,王新华.一个基于图像测量的工业尺寸测量系统[J].测绘通报.1997,(5)：25-27.
[7]王新新,张广秀,徐江伟.一种多线阵CCD扫描系统的标定纸及调整方法[P].201110433227.1,2013-06-26.
[8]周委,陈思平,赵文龙,et a1.基于DSP EMIF口及FPGA设计并实现多DSP嵌入式系统[J].电子技术应用.2008,(6)：39-42.
[9]高晓丁,左贺,辛文辉.基于多片DSP+FPGA结构的织物自动检测系统设计与实现[J].中国测试技术.2007,33(4)：95-98.
[10]梁义涛,傅洪亮,杨铁军.现代DSP技术及应用[M].北京：清华大学出版社.2012：6.
[11]书金辰,李刚,王臣业.零点起步——fMS320C6000系列DSP原理与应用系统设计[M].北京：机械工业出版社.2012：20.
[12]孙尧.纬编针织物疵点实时智能检测的研究[D].上海：东华大学,2010.
[1]Li W., Xue W., Cheng L. Intelligent detection of defects of yarn-dyed fabrics by energy-based local binary patterns[J]. Textile Research Journal.2012,82(19):1960-1972.
[2]Pan R., Gao W., Liu J., et al. Automatic inspection of double-system-melange yarn-dyed fabric density with color-gradient image[J]. Fibers and Polymers.2011,12(1):127-131.
[3]Bao P., Zhang L., Wu X. Canny edge detection enhancement by scale multiplication[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2005,27(9):1485-1490.
[4]Ziou D., Tabbone S. Edge detection techniques-an overview[J]. Pattern Recognition and Image Analysis 1998,8(4):537-559.
[5]Loverro A. Fractional calculus:history, definitions and applications for the engineer[R]. Department of Aerospace and Mechanical Engineering, Notre Dame, U.S.A,2004.
[6]Liu S.C., Chang S. Dimension estimation of discrete-time fractional Brownian motion with applications to image texture classification[J]. IEEE Transactions on Image Processing.1997, 6(8):1176-1184.
[7]Leu J.S., Papamarcou A. On estimating the spectral exponent of fractional Brownian motion[J]. IEEE Transactions on Information Theory.1995,41(1):233-244.
[8]Engheta N. On fractional calculus and fractional multipoles in electromagnetism[J]. IEEE Transactions on Antennas and Propagation.1996,44(4):554-566.
[9]Oldham K.B., Spanier J. The fractional calculus[M]. New York/London:Academic Press. 1974.
[10]杨柱中,周激流,晏祥玉,et a1.基于分数阶微分的图像增强[J].计算机辅助设计与图形学学报.2008,20(3)：343-348.
[11]蒲亦非,王卫星,周激流,et a1.数字图像纹理细节的分数阶微分检测及其分数阶微分滤波器实现[J].中国科学E辑：信息科学.2008,38(12)：2252-2272.
[12]杨烜,梁德群.一种基于区域一致性测度的边缘评价方法[J].中国图象图形学报.1999,4(3)：234-238.
[13]Mathieu B., Melchior P., Oustaloup A., et al. Fractional differentiation for edge detection[J]. Signal Processing.2003,83(11):2421-2432.
[1]Bennamoun M., Bodnarova A. Automatic visual inspection and flaw detection in textile materials:Past, present and future[C]. in IEEE International Conference on SMC.1998: 4340-4343.
[2]Mak K., Peng P., Yiu K. Fabric defect detection using morphological filters[J]. Image and Vision Computing.2009,27(10):1585-1592.
[3]Cho C.S., Chung B.M., Park M.J. Development of real-time vision-based fabric inspection system[J]. IEEE Transactions on Industrial Electronics.2005,52(4):1073-1079.
[4]Bu H.G., Huang X.B., Wang J., et al. Detection of Fabric Defects by Auto-Regressive Spectral Analysis and Support Vector Data Description[J]. Textile Research Journal.2010, 80(7):579-589.
[5]Shi M., Jiang S., Wang H., et al. A Simplified pulse-coupled neural network for adaptive segmentation of fabric defects[J]. Machine Vision and Applications.2009,20(2):131-138.
[6]Ozdemir S., Ercil A. Markov random fields and karhunen-loeve transforms for defect inspection of textile products[C]. in IEEE International Conference on EFTA.1996:697-703.
[7]Ngan H.Y.T., Pang G.K.H., Yung S., et al. Wavelet based methods on patterned fabric defect detection[J]. Pattern Recognition.2005,38(4):559-576.
[8]Tajeripour F., Kabir E., Sheikhi A. Fabric defect detection using modified local binary patterns[J]. EURASIP Journal on Advances in Signal Processing.2008,2008:1-12.
[9]Song K., Kittler J., Petrou M. Defect detection in random colour textures[J]. Image and Vision Computing.1996,14(9):667-683.
[10]Lin J.J. Pattern Recognition of Fabric Defects Using Case-Based Reasoning[J]. Textile Research Journal.2010,80(9):794-802.
[11]Ojala T., Pietik Inen M., M Enp T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24:971-987.
[12]Tsai D.M., Lin C.P., Huang K.T. Defect detection in coloured texture surfaces using Gabor filters[J]. Imaging Science Journal.2005,53(1):27-37.
[13]Field D.J. Relations between the statistics of natural images and the response properties of cortical cells[J]. Journal of Optical Society of American.1987,4(12):2379-2394.
[14]Bodmarova A., Bennamoun M., Kubik K. Suitability analysis of techniques for flaw detection in textiles using texture analysis[J]. Pattern Analysis & Applications.2000,3(3): 254-266.
[1]Bu H., Huang X. Recent progress of computer-vision-based fabric defects classification[J]. Journal of Donghua University (Natural Science).2006,32:143-146.
[2]Shi M., Jiang S., Wang H., et al. A Simplified pulse-coupled neural network for adaptive segmentation of fabric defects[J]. Machine Vision and Applications.2009,20(2):131-138.
[3]Yang X.Z., Pang G., Yung N. Discriminative training approaches to fabric defect classification based on wavelet transform[J]. Pattern Recognition.2004,37(5):889-899.
[4]Kondo H., Okuyama M., Saito Y. Defect classification/inspection system[P]. U.S. Patent(10/222431),2003.
[5]Balakrishnan H., Venkataraman S., Jayaraman S. FDICS:A vision-based system for the identification and classification of fabric defects[J]. Journal of the Textile Institute.1998, 89(2):365-380.
[6]Kuo C.F.J., Su T.L. Gray relational analysis for recognizing fabric defects[J]. Textile Research Journal.2003,73(5):461-465.
[7]Murino V., Bicego M., Rossi I.A. Statistical classification of raw textile defects[C]. in Proceedings of the 17th International Conference on Pattern Recognition.2004:311-314.
[8]Lin J.-J. Pattern recognition of fabric defects using case-based reasoning[J]. Textile Research Journal.2010,80(9):794-802.
[9]Ghosh A., Guha T., Bhar R.B., et al. Pattern classification of fabric defects using support vector machines[J]. International Journal of Clothing Science and Technology.2011,23(2-3): 142-151.
[10]Kuo C.F.J., Lee C.J. A back-propagation neural network for recognizing fabric defects[J]. Textile Research Journal.2003,73(2):147-151.
[11]Tarek Habib M., Rokonuzzaman M. A set of geometric features for neural network-based textile defect classification[J]. ISRN Artificial Intelligence.2012,2012:1-16.
[12]Tabassian M., Ghaderi R., Ebrahimpour R. Knitted fabric defect classification for uncertain labels based on Dempster-Shafer theory of evidence[J]. Expert Systems with Applications. 2011,38(5):5259-5267.
[13]Schmitt E., Bombardier V., Wendling L. Fuzzy rule iterative feature selection (FRIFS) with respect to the choquet integral apply to fabric defect recognition[C]. in Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems.2008: 708-718.
[14]Zhang Y., Lu Z.Y., Li J. Fabric defect classification using radial basis function network[J]. Pattern Recognition Letters.2010,31(13):2033-2042.
[15]Li W., Xue W., Cheng L. Intelligent detection of defects of yarn-dyed fabrics by energy-based local binary patterns[J]. Textile Research Journal.2012,82(19):1960-1972.
[16]AQSIQ. Yarn-dyed pattern fabric[S]. National Standards of the People's Republic of China, 2009. GB/T 22851-2009.
[17]Tamura H., Mori S., Yamawaki T. Texture features corresponding to visual perception[J]. IEEE Transactions on Systems, Man and Cybernetics.1978,8:460-473.
[18]Hsu C.W., Chang C.C., Lin C.J. A practical guide to support vector classification[M//OL]. 2010. Available from:http://www.csie.ntu.edu.tw/-cjlin/papers/guide/guide.pdf.
[19]Boser E., Guyon I., Vapnik V. A training algorithm for optimal margin classiers[C]. in Proceedings of the Fifth Annual Workshop on Computational Learning Theory.1992:144- 152.
[20]Cortes C., Vapnik V. Support-vector network[J]. Machine Learning.1995,20:273-297.
[21]Hsu C.W., Lin C.J. A comparison of methods for multiclass support vector machines[J]. IEEE Transactions on Neural Networks.2002,13(2):415-425.
[22]Chang C.C., Lin C.J. LIBSVM:a library for support vector machines[M//OL].2011. Available from:http://www.csie.ntu.edu.tw/-cjlin/papers/libsvm.pdf.