基于机器视觉的丝饼毛羽检测
|
摘要
为实现丝饼毛羽的自动检测,提出基于机器视觉的丝饼毛羽检测方法,通过寻找毛羽轮廓点中凸包位置实现丝饼毛羽检测。首先构建具有特定结构特征的卷积核,利用该卷积核对原始图像进行卷积运算,从而获取毛羽特征,并采用阈值处理对其进行二值化;然后对二值化后的毛羽进行轮廓检测,继而筛选轮廓点以减少运算时间;最后利用单方向凸包算法对满足条件的轮廓点进行检测,实现对丝饼毛羽的定位及计数。运用3类典型丝饼毛羽对检测方法进行验证,结果表明,该方法可有效地实现对丝饼毛羽准确定位并计数,且对不同背景的毛羽图片有较强的适应性。
In order to realize the automatic detection of the hairiness of yarn packages,a method for detecting the hairiness of yarn packages based on machine vision was proposed. Firstly,the convolution kernel was constructed,and the hairiness characteristics were obtained by convolving the original image with the convolution kernel,and binarization was performed using threshold processing. Secondly,the contours of the binarized hairiness were detected,and then the contour points were screened to reduce the computing time. Finally,the unidirectional convex hull detection was applied to the outline points which meet the screening conditions,and then the hairiness of the yarn packages was located and counted.Three kinds of typical yarn packages were used to verify the method. The experimental results show that the method can position and count the hairiness number of the yarn packages accurately,and has strong adaptability to the hairiness images of different backgrounds.
In order to realize the automatic detection of the hairiness of yarn packages,a method for detecting the hairiness of yarn packages based on machine vision was proposed. Firstly,the convolution kernel was constructed,and the hairiness characteristics were obtained by convolving the original image with the convolution kernel,and binarization was performed using threshold processing. Secondly,the contours of the binarized hairiness were detected,and then the contour points were screened to reduce the computing time. Finally,the unidirectional convex hull detection was applied to the outline points which meet the screening conditions,and then the hairiness of the yarn packages was located and counted.Three kinds of typical yarn packages were used to verify the method. The experimental results show that the method can position and count the hairiness number of the yarn packages accurately,and has strong adaptability to the hairiness images of different backgrounds.
引文
[1]张清华,张殿波.石墨烯与纤维的高性能化[J].纺织学报,2016,37(10):145-152.ZHANG Qinghua, ZHANG Dianbo. Graphene and enhanced fibers[J]. Journal of Textile Research,2016,37(10):145-152.
[2]高哲,蒋高明,马丕波,等.碳纤维多轴向经编复合材料的应用与发展[J].纺织学报,2013,34(12):144-151.GAO Zhe, JIANG Gaoming, MA Pibo, et al.Application and development of carbon fiber multi-axial warp-knitted fabric reinforced composites[J]. Journal of Textile Research,2013,34(12):144-151.
[3]柳素景,丁新波,韩建.羟基锡酸锌/Sb2O3对聚氯乙稀复合建筑膜材的协同阻燃性能[J].纺织学报,2015,36(10):102-106.LIU Sujing,DING Xinbo,HAN Jian. Synergic flame retardance of zinc hydroxy stannate/Sb2O3on polyvingl chloride composite building membrane[J]. Journal of Textile Research,2015,36(10):102-106.
[4]徐旻.纱线质量的全面检测与综合评定[J].棉纺织技术,2010,38(6):24-26.XU Min. Comprehensive detection and evaluation of yarn quality[J]. Cotton Textile Technology,2010,38(6):24-26.
[5] SUN T H,TSENG C C,CHEN M S. Electric contacts inspection using machine vision[J]. Image&Vision Computing,2010,28(6):890-901.
[6] PALOMARES J M,GONZALEZ J,ROS E,et al.General logarithmic image processing convolution[J].IEEE Transactions on Image Processing, 2006,15(11):3602-3608.
[7] LI B,HU J. Design and implementation of image effects based on convolution algorithm[C]//2013 5th International Conference on Computational&Information Sciences. Shiyang:IEEE,2013:144-147.
[8] GUPTA A,NAG A,SAVANI J,et al. Evolutionary approach and spline interpolation for contrast enhancement[C]//2013 IEEE 2nd International Conference on Image Information Processing. Shimla:IEEE,2013:181-186.
[9] ANGELOVA D,MIHAYLOVA L,PETROV N,et al.Extended object tracking with convolution particle filtering[C]//2012 6th IEEE International Conference Intelligent Systems. Sofia:IEEE,2012:96-101.
[10] WANG Z,ZHANG J. Classification smoothing filtering algorithm based on edge information[C]//Information Technology,Networking,Electronic and Automation Control Conference,IEEE. Chongqing:IEEE,2016:366-370.
[11] MAHMOODI S. Edge detection filter based on mumfordShah green function[J]. Siam Journal on Imaging Sciences,2012,5(1):343-365.
[12] MITCHELL H B,SCHAEFER P A. A fuzzy noisesmoothing filter[J]. International Journal of Intelligent Systems,2015,15(4):303-315.
[13] XU X, MILLER E L, CHEN D, et al. Adaptive two-pass rank order filter to remove impulse noise in highly corrupted images[J]. IEEE Transactions on Image Processing,2004,13(2):238-247.
[14] SON J W,PARK S B,KIM K J. A convolution kernel method for color recognition[C]//2007 6th International Conference on Advanced Language Processing and Web Information Technology. Luoyang:IEEE,2007:242-247.
[15] KAUR R. Modified watershed transform using convolution filtering for image segmentation[J].International Journal of Engineering Sciences&Research Technology,2014,3(8):449-454.
[16] GAO L, YAN Y, LU G. Contour-based image segmentation for on-line size distribution measurement of pneumatically conveyed particles[C]//Instrumentation and Measurement Technology Conference. Binjiang:IEEE,2011:1-5.
[17]李必栋,闫浩文,王中辉,等.坐标排序的离散点凸包生成算法[J].测绘科学,2017,42(2):14-17.LI Bidong, YAN Haowen, WANG Zhonghui, et al.Algorithm of convex hull generation for point sets based on sorted coordinates[J]. Science of Surveying and Mapping,2017,42(2):14-17.
[18]刘凯,夏苗,杨晓梅.一种平面点集的高效凸包算法[J].工程科学与技术,2017,49(5):109-116.LIU Kai,XIA Miao,YANG Xiaomei. An effective 2D convex hull algorithm[J]. Advanced Engineering Sciences,2017,49(5):109-116.
[2]高哲,蒋高明,马丕波,等.碳纤维多轴向经编复合材料的应用与发展[J].纺织学报,2013,34(12):144-151.GAO Zhe, JIANG Gaoming, MA Pibo, et al.Application and development of carbon fiber multi-axial warp-knitted fabric reinforced composites[J]. Journal of Textile Research,2013,34(12):144-151.
[3]柳素景,丁新波,韩建.羟基锡酸锌/Sb2O3对聚氯乙稀复合建筑膜材的协同阻燃性能[J].纺织学报,2015,36(10):102-106.LIU Sujing,DING Xinbo,HAN Jian. Synergic flame retardance of zinc hydroxy stannate/Sb2O3on polyvingl chloride composite building membrane[J]. Journal of Textile Research,2015,36(10):102-106.
[4]徐旻.纱线质量的全面检测与综合评定[J].棉纺织技术,2010,38(6):24-26.XU Min. Comprehensive detection and evaluation of yarn quality[J]. Cotton Textile Technology,2010,38(6):24-26.
[5] SUN T H,TSENG C C,CHEN M S. Electric contacts inspection using machine vision[J]. Image&Vision Computing,2010,28(6):890-901.
[6] PALOMARES J M,GONZALEZ J,ROS E,et al.General logarithmic image processing convolution[J].IEEE Transactions on Image Processing, 2006,15(11):3602-3608.
[7] LI B,HU J. Design and implementation of image effects based on convolution algorithm[C]//2013 5th International Conference on Computational&Information Sciences. Shiyang:IEEE,2013:144-147.
[8] GUPTA A,NAG A,SAVANI J,et al. Evolutionary approach and spline interpolation for contrast enhancement[C]//2013 IEEE 2nd International Conference on Image Information Processing. Shimla:IEEE,2013:181-186.
[9] ANGELOVA D,MIHAYLOVA L,PETROV N,et al.Extended object tracking with convolution particle filtering[C]//2012 6th IEEE International Conference Intelligent Systems. Sofia:IEEE,2012:96-101.
[10] WANG Z,ZHANG J. Classification smoothing filtering algorithm based on edge information[C]//Information Technology,Networking,Electronic and Automation Control Conference,IEEE. Chongqing:IEEE,2016:366-370.
[11] MAHMOODI S. Edge detection filter based on mumfordShah green function[J]. Siam Journal on Imaging Sciences,2012,5(1):343-365.
[12] MITCHELL H B,SCHAEFER P A. A fuzzy noisesmoothing filter[J]. International Journal of Intelligent Systems,2015,15(4):303-315.
[13] XU X, MILLER E L, CHEN D, et al. Adaptive two-pass rank order filter to remove impulse noise in highly corrupted images[J]. IEEE Transactions on Image Processing,2004,13(2):238-247.
[14] SON J W,PARK S B,KIM K J. A convolution kernel method for color recognition[C]//2007 6th International Conference on Advanced Language Processing and Web Information Technology. Luoyang:IEEE,2007:242-247.
[15] KAUR R. Modified watershed transform using convolution filtering for image segmentation[J].International Journal of Engineering Sciences&Research Technology,2014,3(8):449-454.
[16] GAO L, YAN Y, LU G. Contour-based image segmentation for on-line size distribution measurement of pneumatically conveyed particles[C]//Instrumentation and Measurement Technology Conference. Binjiang:IEEE,2011:1-5.
[17]李必栋,闫浩文,王中辉,等.坐标排序的离散点凸包生成算法[J].测绘科学,2017,42(2):14-17.LI Bidong, YAN Haowen, WANG Zhonghui, et al.Algorithm of convex hull generation for point sets based on sorted coordinates[J]. Science of Surveying and Mapping,2017,42(2):14-17.
[18]刘凯,夏苗,杨晓梅.一种平面点集的高效凸包算法[J].工程科学与技术,2017,49(5):109-116.LIU Kai,XIA Miao,YANG Xiaomei. An effective 2D convex hull algorithm[J]. Advanced Engineering Sciences,2017,49(5):109-116.