应用多尺度多方向模板卷积的筒子纱缺陷检测
|
摘要
针对筒子纱不规则的纹理基元增加缺陷检测难度的问题,提出一种基于多尺度多方向模板卷积的筒子纱表面网纱缺陷检测算法。首先通过系统采集筒子纱的顶面纹理图像;其次对原图像进行OTSU阈值处理,并采用椭圆拟合确定纹理位置,利用极坐标变换将其展开;然后利用水平方向一维高斯差分算子提取边缘,通过改变高斯核的标准差获取多个尺度的边缘图像;进而将0°～180°角度区间量化成多个方向模板与各尺度的边缘图像进行卷积,并投票记录每个像素位置在各尺度下的多方向模板卷积结果的最大值;最后,选取经验阈值对最强卷积响应进行分割得到缺陷图像。实验结果表明,该方法可有效检测筒子纱表面的网纱缺陷,识别准确率达0. 96。
Aiming at the hard defect detection due to coarse and irregular texture element of cheese yarn,a novel cheese yarn surface defects detection algorithm based on multiscale multi-direction template convolution was proposed. Firstly,the image of top textile of cheese yarn was acquired by the system.Secondly,the OTSU threshold method and the ellipse circle fitting method were used to determine the position of the textile region of cheese yarn. Then,the polar coordinate transformation was used to expand the ring-shape surface to a rectangle. After that,the one-dimensional difference of Gaussian operator in horizontal direction was used to extract the edge. Multiple scale edge images were extracted by varying the standard deviation of Gauss kernel. Furthermore,the angle range of 0° to 180° was quantified into several directional template images used to convolute with edge images,then the maximum convolution result of each pixel in among all scales was elected by voting method. Finally,the defects were segmented out from the maximum correlation image by an empirical threshold according to prior information. The experiment results show that the method can effectively detect the net-yarn surface defects,and the recognition accuracy reaches 96%.
Aiming at the hard defect detection due to coarse and irregular texture element of cheese yarn,a novel cheese yarn surface defects detection algorithm based on multiscale multi-direction template convolution was proposed. Firstly,the image of top textile of cheese yarn was acquired by the system.Secondly,the OTSU threshold method and the ellipse circle fitting method were used to determine the position of the textile region of cheese yarn. Then,the polar coordinate transformation was used to expand the ring-shape surface to a rectangle. After that,the one-dimensional difference of Gaussian operator in horizontal direction was used to extract the edge. Multiple scale edge images were extracted by varying the standard deviation of Gauss kernel. Furthermore,the angle range of 0° to 180° was quantified into several directional template images used to convolute with edge images,then the maximum convolution result of each pixel in among all scales was elected by voting method. Finally,the defects were segmented out from the maximum correlation image by an empirical threshold according to prior information. The experiment results show that the method can effectively detect the net-yarn surface defects,and the recognition accuracy reaches 96%.
引文
[1]牟新刚,蔡逸超,周晓.基于机器视觉的筒子纱缺陷在线检测系统[J].纺织学报,2018,39(1):139-145.MOU Xingang,CAI Yichao,ZHOU Xiao. On-line yarn cone defects detection system based on machine vision[J]. Journal of Textile Research,2018,39(1):139-145.
[2]张志欢.复杂纹理背景的织物疵点检测与定位研究[D].武汉:武汉纺织大学,2011:11-37.ZHANG Zhihuan. Research on fabric defect detection and location of complex texture background[D].Wuhan:Wuhan Textile University,2011:11-37
[3] ARNIA F, MUNADI K. Real time textile defect detection using GLCM in DCT-based compressed images[C]//2015 6th International Conference on Modeling,Simulation,and Applied Optimtzat.[S. l.]:ICMSAO,2015:1-6.
[4] BISSI L,BARUFFA G,PLACIDI P. Automated defect detection in uniform and structed fabrics using Gabor filters and PCA[J]. Journal of Visual Communication&Image Representation,2013,24(7):838-845.
[5] NGAN H Y T,PANG C K H,YUNG S P,et al.Wavelet based methods on patterned fabric defect detection[J]. Pattern Recognition,2005,38(4):559-576.
[6]陈晓惠,郑晨,段汕,等.形态学小波域多尺度马尔可夫模型在纹理图像分割中的应用[J].中国图象图形学报,2011,16(5):761-766.CHEN Xiaohui,ZHENG Chen,DUAN Shan,et al.Application of texture image segmentation based on a multi-resolution Markov random field model in morphological wavelets domain[J]. Journal of Image and Graphics,2011,16(5):761-766.
[7] JING Junfeng,CHEN Shan,LI Pengfei. Fabric defect detection based on golden image subtraction[J].Coloration Technology,2016,133(1). DOI:10. 1111/cote.12239.
[8] HANMANDLU M,SUJATA D,CHOUDHURY D K.Fabric image defect detection by using GLCM and ROSETTA[J]. International Journal of Computer Science and Applications,2009,2(1):47-50.
[9]何薇,白瑞林,李新.基于Gabor小波和神经网络的布匹瑕疵检测[J].计算机工程与应用,2016,52(12):231-234.HE Wei,BAI Ruilin,LI Xin. Fabric defect detection based on Gabor wavelet and neural network[J].Computer Engineering and Applications, 2016,52(12):231-234.
[10] ZHANG J M,WANG X G,PALMER S. Objective grading of fabric pilling with wavelet texture analysis[J]. Textile Research Journal,2005,75(12):801-811.
[11] CAO Junjie,ZHANG Jie,WEN Zhijie. Fabric defect inspection using prior knowledge guided least squares regression[J]. Multimedia Tools&Applications,2015,76(3):1-17.
[2]张志欢.复杂纹理背景的织物疵点检测与定位研究[D].武汉:武汉纺织大学,2011:11-37.ZHANG Zhihuan. Research on fabric defect detection and location of complex texture background[D].Wuhan:Wuhan Textile University,2011:11-37
[3] ARNIA F, MUNADI K. Real time textile defect detection using GLCM in DCT-based compressed images[C]//2015 6th International Conference on Modeling,Simulation,and Applied Optimtzat.[S. l.]:ICMSAO,2015:1-6.
[4] BISSI L,BARUFFA G,PLACIDI P. Automated defect detection in uniform and structed fabrics using Gabor filters and PCA[J]. Journal of Visual Communication&Image Representation,2013,24(7):838-845.
[5] NGAN H Y T,PANG C K H,YUNG S P,et al.Wavelet based methods on patterned fabric defect detection[J]. Pattern Recognition,2005,38(4):559-576.
[6]陈晓惠,郑晨,段汕,等.形态学小波域多尺度马尔可夫模型在纹理图像分割中的应用[J].中国图象图形学报,2011,16(5):761-766.CHEN Xiaohui,ZHENG Chen,DUAN Shan,et al.Application of texture image segmentation based on a multi-resolution Markov random field model in morphological wavelets domain[J]. Journal of Image and Graphics,2011,16(5):761-766.
[7] JING Junfeng,CHEN Shan,LI Pengfei. Fabric defect detection based on golden image subtraction[J].Coloration Technology,2016,133(1). DOI:10. 1111/cote.12239.
[8] HANMANDLU M,SUJATA D,CHOUDHURY D K.Fabric image defect detection by using GLCM and ROSETTA[J]. International Journal of Computer Science and Applications,2009,2(1):47-50.
[9]何薇,白瑞林,李新.基于Gabor小波和神经网络的布匹瑕疵检测[J].计算机工程与应用,2016,52(12):231-234.HE Wei,BAI Ruilin,LI Xin. Fabric defect detection based on Gabor wavelet and neural network[J].Computer Engineering and Applications, 2016,52(12):231-234.
[10] ZHANG J M,WANG X G,PALMER S. Objective grading of fabric pilling with wavelet texture analysis[J]. Textile Research Journal,2005,75(12):801-811.
[11] CAO Junjie,ZHANG Jie,WEN Zhijie. Fabric defect inspection using prior knowledge guided least squares regression[J]. Multimedia Tools&Applications,2015,76(3):1-17.