基于视觉校准的环锭纺细纱条干特征在线提取方法

针对纱线高速回转、毛羽条干交织导致的条干轮廓特征难以准确提取的问题,提出了深度学习与形态学运算融合的在线提取方法,设计了图像在线采集系统与校准定焦方法,为轮廓特征提取提供高质量输入,构建了基于整体嵌套边缘检测神经网络和形态学运算的细纱条干轮廓特征提取重构模型,实现毛羽干扰下的条干轮廓在线准确提取。实验结果表明,所提方法的轮廓提取准度指标OIS-F(optimal image scale)、ODS-F(optimal dataset scale)达到了0.91,平均准确率AP达到了0.89,相对于当前方法提高了7%以上。基于提取的轮廓特征计算的条干不匀CV值,与CT3000均匀度检测仪的平均误差小于4%。     

Development of image processing based system to study yarn structure during extension

The present study describes design and development and use of an image processing system to characterize and visualize the configuration of fibers in yarn in extended mode. An especially dedicated instrument and software for data acquisition and analysis are the unique features of the system. It is capable of grabbing the images of extended yarn in two orthogonal planes. The software can acquire data from these two orthogonal planes. The three‐dimensional trajectory of whole length of different colored tracer fibers can be plotted and can be viewed at different angles. The image processing system along with multi‐colored tracer fiber technique has been used for quantitative analysis of changes in the internal structure of ring yarn on extension.     

基于机器视觉的筒子纱密度在线检测系统

为提高筒子纱密度检测自动化程度,解决传统筒子纱密度测量方法效率低、操作复杂等问题,设计了一种基于机器视觉的筒子纱密度在线检测系统。该系统由质量传感器、光电传感器、蓝色面光源、工业摄像机、传送装置和工控机组成。研究了筒子纱图像校正算法,根据透视投影理论建立了筒子纱校正模型,还原了筒子纱上下边界的直线特性,得到了理想的筒子纱侧面图像,用积分法得到筒子纱的精确体积。150个筒子纱密度检测结果表明:通过像素当量折算出筒子纱实际最大直径和体积参数,再结合高精度质量传感器的数据,最终可计算出筒子纱密度,基于机器视觉的筒子纱密度在线检测系统的检测精度和稳定性能可满足生产要求。     

An improved gray line profile method to inspect the warp–weft density of fabrics

Image processing has become a tremendous tool for various fields of applications as well as for textile manufacturing industry in recent years. Inspection of fabric density is one of the major issues for fabric manufacturers in textile industries. In this study, an image processing method comprising of linear and nonlinear techniques for automatic inspection of warp and weft yarn density of fabrics has been proposed. By avoiding common problems of linear filtering such as blurring and localization, anisotropic diffusion filtering has been applied as preprocessing operation to enhance the edge region/boundaries between adjacent yarns of the fabric images. We conjecture that given a skewed gray level image, the number of peaks in the gray line profile of the image is minimized if the image is rotated in such a way that the inter-spaces between yarns are aligned with the vertical axis. Gabor filter, an orientation-sensitive filter, is applied to the skewed image at that angle to boost the edges between inter-spaces. The number of warp and weft yarn density has been inspected by applying gray line profile method. Simulations have been done on a wide range of fabric image data set. The results have shown that nonlinear and steered filters made a contribution to the performance of the method. The number warp and weft yarn densities are determined with an accuracy rates above 90%.     

Weave pattern recognition by measuring fiber orientation with Fourier transform

An effective method based on measuring the fiber orientation of yarn floats with two-dimensional Fourier transform (2-D FFT) is proposed to recognize the weave pattern of yarn-dyed fabric in the high-resolution image. The recognition process consists of four main steps: 1. High-resolution image reduction, 2.Fabric image skew correction, 3.Yarn floats localization, 4. Yarn floats classification. Firstly, the high-resolution image is reduced by the nearest interpolation algorithm. Secondly, the skew of the fabric image is corrected based on Hough transform. Thirdly, the yarn floats in the fabric image is localized by the yarns segmentation method based on the mathematical statistics of sub-images. Fourthly, the high-resolution image is corrected and its yarns are segmented successively according to the inspection information of the reduced image. The fiber orientations are detected by 2-D FFT, and the yarn floats are classified by k-means clustering algorithm. Experimental results and discussions demonstrate that, by measuring the fiber orientation of yarn floats, the proposed method is effective to recognize the yarn floats and the weave pattern for yarn-dyed, solid color, and gray fabrics.     

基于复合条件的织物纹理模糊识别

提出一种新的基于复合条件的模糊识别方法完成对织物图像的纹理提取。首先对整个图像灰度级分析,确定行与列灰度波的标准模糊集,然后给出基于灰度大小及像素位置的复合条件隶属度计算公式,对行与列的灰度波进行模糊分类,使其转换为仅有2个灰度极值的纹理灰度波。最后将所有纹理灰度波组合还原成二值纹理织物图像,为后续密度识别、纹理均匀度识别及疵点识别等图像分析提供基础。实验与分析结果显示,本文算法通过对灰度波的模糊划分,提取仅用2个灰度值表示的织物二值纹理图像,形成具有脉冲特征的纹理灰度波,可为后续织物图像各参数分析提供简单有用的织物纹理数据模型。     

纱线毛羽骨架及长度的跟踪测量

针对现有图像法毛羽测量存在的缺陷,提出了一种用于毛羽分析和长度测量的纱线毛羽骨架跟踪算法。首先以10像素为步长,作纱线条干边缘曲线对毛羽骨架的分割线,得到毛羽起点;接着在毛羽延伸方向上对毛羽起点的上5?邻域点或下5?邻域点进行判断,得到新的毛羽路径点,进行邻域点的重复判断,直到没有毛羽路径点存在,依次记录所有毛羽点生成毛羽路径,并提出了多毛羽路径点和交叉毛羽的解决方案;最后根据2点间的距离计算出毛羽路径中相邻毛羽路径点的像素,从而得到毛羽的测量长度。对长毛羽的跟踪测量和固定分割长度测量的结果显示,毛羽骨架及长度的跟踪测量算法可将测量长度提高24.3%∽666%,测量结果较为精确。     

基于机器视觉的烟青虫和棉铃虫雌雄蛹的分类识别

为有效分类识别烟草主要害虫烟青虫和棉铃虫的雌雄蛹,进而有效监测与防治,选取两种害虫的虫蛹作为待测样本,对害虫的图像进行分析,并结合图像处理和模式识别技术,提出一种基于机器视觉的烟草主要害虫雌雄蛹分类识别方法。利用SLR相机对两种害虫的雌雄蛹进行拍摄并提取腹部末节有效区域,获得分辨率350×350的原始图像,提取其RGB空间中R通道灰度图像作为纹理特征的输入图像,并将提取的基于灰度共生矩阵对比度、角二阶矩等纹理特征指标作为虫蛹雌雄性的判别依据,将待测试蛹特征数据输入训练好的支持向量机进行识别分类。结果表明:利用该方法实现了对烟青虫和棉铃虫雌雄蛹的较有效分类,识别率分别达到87.5%和82.5%。该方法可为害虫雌雄蛹的较准确识别提供技术支持。     

应用纱线序列图像的电子织物构建

为检测纱线条干均匀性对织物外观的影响,在纱线条干图像测量的基础上,提出了一种基于纱线序列图像的电子织物的构建方法。通过建立织物组织变化模型和光照模型,将纱线直径值与基元组织点外观灰度纹理分布相结合,构建电子织物外观数学模型。实验中通过将采集的纱线序列图像进行图像分割和形态学运算等处理,获取纱线直径数据,代入到构建的织物外观数学模型中,实现基于纱线序列图像的电子织物的模拟并且相关参数可调。通过选择合理的织物结构参数,提出的电子织物模型能够真实的反映纱线条干均匀性对织物外观的影响,准确预测布面效果。     

一种新的纹理图像特征提取的方法

灰度图像的纹理反映了一个区域中像素灰度级及其局部变化的空间分布属性，用图像的局部统计特征能较好地刻画不同纹理的差异。基于这种思想，本文中首次提出了一种基于PCNN点火序列图的纹理图像特征提取的新方法。通过对PCNN的运行行为和基本特性的分析。指出PCNN的点火时刻序列图不仅包含了局部图像的灰度分布信息，更重要的是还包含了图像中相邻像素之间的几何信息，这恰是纹理图像的个性特征所在，最后给出了部分仿真实验的结果，以验证该方法的有效性。     

利用图像处理技术测定棉粘胶混纺纱的混纺比

研究棉纤维粘胶纤维混纺纱混纺比的测定方法。通过数学形态学操作对棉纤维粘胶纤维混纺纱截面图像进行预处理,并使用光斑扩散方法得到了图像中各个纤维截面的轮廓线。在对半径序列进行傅立叶变换的基础上,将幅度质心系数作为区分粘胶纤维和棉纤维的特征指标。对图像中的目标抽取特征数据,进行聚类和分类。统计各类纤维截面的像素面积,结合两种纤维的密度,计算出棉纤维粘胶纤维混纺纱的混纺比。结果表明:该法能较准确的测定出棉纤维粘胶纤维混纺纱的混纺比。     

基于卷积神经网络的机织物密度均匀性检测

针对目前基于机器视觉的机织物密度自动检测时织物检测视野小、精度低、品种适应性差的问题,提出一种基于多尺度卷积神经网络的检测方法.首先设计了一套离线图像采集系统连续采集织物图像,并建立一个包含详细织物参数的织物图像数据集;然后采用一种具有不同大小局部感受野的多尺度卷积神经网络适应不同大小的织物结构特征,定位纱线位置;最后...     

采用织物上拆解的纬纱评价无梭织造的性能

研究了不同工厂的高中低支纬纱的性能。研究了原纱和织物上拆解下来的高中低支纬纱的诸如断裂强力、强度、伸长和断裂功等性能。研究表明原纱的强度与纬纱的断裂有很大关系。原纱的强度随着纱支的增加而增加,断裂强力、伸长和断裂功随着纱支的增加而降低,而对于拆解纬纱特性和纬纱断头之间未发现这种趋势。     

应用显著性算法的纱线条干均匀度检测

针对运用图像方法进行纱线条干均匀度检测时,背景黑板、纱线毛羽以及图像噪声等对检测结果影响较大的问题,借鉴人的视觉感知机制,提出一种应用显著性算法检测纱线条干均匀度的方法。对采集到的纱线图像提取颜色和亮度特征,进行显著性分析,突出纱线条干区域,然后利用迭代阈值分割算法和区域滤波,得到准确清晰的纱线条干二值图像,基于此进行直径计算、均匀度分析和纱线疵点判定。通过边缘准确性评价可知,采用所提方法分割得到的纱线条干二值图像有着较高的分割精度。通过与Uster Classimat 5的均匀度检测结果进行比较,证明这种方法可得到准确的结果,与Used Classimat 5 的测量结果有着较好的一致性。     

纱线毛羽图像的二值化处理及其Matlab实现

文章利用CCD扫描来采集纱线灰度图像，运用计算机快速处理数据的能力以及Matlab强大的图像处理功能，采用适当的方法对纱线毛羽图像进行消噪、灰度变换、二值化处理。通过分析二值化图像的特征，分别得出带毛羽纱线和不带毛羽纱线的图像面积，进一步计算出纱线相对毛羽率。结果表明，该方法分割效果好，运算速度快，不需要购买专门的仪器，具有较高的实用价值。     

纱线条干均匀性序列图像测量方法

为了更精确、连续地评价纱线的外观条干均匀性,提出一种基于序列图像的纱线条干均匀性测量方法。通过图像采集系统获取连续的纱线序列图像;根据模糊C-均值（FCM）聚类算法将图像进行阈值分割,得到纱线条干的二值图像;设定阈值去除图像中的孤立点、毛刺点,获得清晰的纱线条干图像,并计算图像中每行纱线直径。 为验证方法的准确性,对７ 种线密度的紧密纺纯棉纱进行了条干测试,并将结果与USTER® Tester 5-S800 条干测试仪的测试结果进行了对比。结果表明：序列图像方法测得的纱线条干均匀性与USTER 条干仪的测试结果高度正相关,证明本文的方法是准确可行的。     

A two-scale attention model for intelligent evaluation of yarn surface qualities with computer vision

In this paper, an intelligent computer method for yarn surface grading is developed to analyze yarn board image and objectively evaluate yarn quality according to ASTM D2255.Both statistical features measuring the overall performance and relative features measuring salient regions are elaborately designed and selected. Statistical features are extracted to characterize the yarn body and hairiness. In relative feature extraction, a two-scale attention model is proposed and developed, which can fully imitate human attention at different observation distances for the whole and detailed yarn information. Global and individual Probabilistic Neural Networks (PNNs) are then designed for yarn quality evaluation based on eight-grade and five-grade classifications. A database, covering eight yarn densities (Ne7~ Ne80) and different surface qualities, was constructed with 296 yarn board images for the evaluation. The accuracy for eight- and five-grade global PNNs are 92.23 and 93.58%, respectively, demonstrating a good classification performance of the proposed method.     

基于平面镜成像的纱线条干三维合成校准方法

针对二维图像纱线条干均匀度检测存在信息缺失、纱线条干三维合成准确度不高等问题,在平面镜成像的三维检测系统基础上提出一种纱线条干三维合成校准方法。选用4种不同粗细的纯棉集聚纺纱线,用相机在一幅图像中采集各个纱线的多视角图像,分别用校准方法对xoz平面和xoy平面校准,再进行二值化、形态学开运算处理,得到清晰的纱线条干二值图像,根据平面镜成像系统几何关系合成纱线条干三维模型,计算纱线条干各截面上像素点个数及其变异系数,与Uster TESTER 5测得的二维直径及纱线二维直径CV值对比评价纱线条干建模精度。结果表明,三维模型纱线各截面像素点个数与二维直径相关系数在0.987以上,条干均匀度CV值与Uster法结果的极差在2.36%以内,证明校准方法可行。     

A computer vision-based system for automatic detection of misarranged warp yarns in yarn-dyed fabric. Part I: continuous segmentation of warp yarns

In textile and garment industries, misarranged warp yarns of yarn-dyed fabrics disorganize the layout of fabrics and lead to poor product quality. This series of studies aims to develop a computer vision-based system for automatic detection of misarranged color warp yarns in terms of high efficiency and good accuracy. Four main parts are included in this series of studies: warp yarn segmentation, fabric image stitching, warp regional segmentation, and yarn layout proofing. This paper proposes a continuous segmentation method of warp yarns to detect the misarranged color warp yarns for yarn-dyed fabrics automatically, which is the foundation of the developed computer vision-based system. The proposed framework consists of two main components: warp yarn segmentation and fabric image stitching. Firstly, the sequence images of a fabric stripe are captured using a designed offline image acquisition platform. Secondly, the warp yarns in the sequence images are segmented by a sub-image projection-based method successively. Thirdly, the sequence images are stitched by a yarn-template matching method based on their warp segmentation results. Finally, the continuous segmentation result of warp yarns is saved for the further processing of warp regional segmentation and color warp layout proofing. The proposed method has been evaluated on 720 fabric images of five fabric examples with plain and 2/2 twill, and experimental results show that the proposed method can realize the continuous segmentation of warp yarns in yarn-dyed fabrics with the yarn segmentation accuracy of 97.43% and image stitching accuracy of 99.53%.     

采用色纺纱图像的真实感色织物模拟

为解决色织物产品设计周期长,试织打样耗时费力的问题,提出一种采用色纺纱图像的真实感色织物的模拟方法。首先采集彩色纱线图像,运用阈值分割、形态学处理得到纱线主体,获取纱线主体的上、下边界和中心线,进而得到原始纱线图像的主体部分;接着根据椭圆模型和正弦曲线模型对纱线主体图像进行处理,得到纱线在二维织物表面中的形态;最后根据色纱循环和织物组织变换模型来改变经纬纱的覆盖关系,实现了真实感条纹型和格子型色织物的模拟。模拟结果表明：本文算法能够模拟不同种类色织物的织造过程,真实地反映织物的外观效果,且能够调整织物组织和色纱循环参数,提高了现有模拟算法的真实性和适应性。