基于多方向Gabor滤波的导光板轻微线刮伤检测方法研究
|
摘要
导光板在加工、运输等生产过程,不可避免地会出现各种缺陷,特别是轻微线刮伤,利用现有算法无法准确提取缺陷区域。本文在分析导光板轻微线刮伤产生原因、成像特征的基础上,提出了一种基于多方向Gabor滤波和亚像素分析的导光板轻微线刮伤检测方法。首先,为了突出缺陷区域,设计了一个多方向的Gabor滤波器;进而,利用亚像素图像分析方法,准确将疑似缺陷区域从背景图中分割出来;最后,分析区域形状特征,准确提取轻微线刮伤缺陷。实验结果表明,该算法的运行效率和准确率高,稳定性、鲁棒性强,能够有效检测轻微线刮伤。
In the production and transportation processes of the light guide plate,various defects,in particular,slight line scratches,are inevitably caused.These defect areas cannot be accurately extracted by using the existing algorithm.In this paper,based on the analysis of the cause and imaging characteristics of the slight scratch on the light guide plate,a method for detecting the slight line scratch on the light guide plate based on multi-directional Gabor filtering and sub-pixel analysis is proposed.Firstly,in order to highlight the defect area,a multi-directional Gabor filter is designed.Furthermore,the sub-pixel image analysis method is used to accurately segment the suspected defect area from the background image.Finally,the area shape feature is analyzed to accurately extract the slight line scratch defects.The experimental results show that the algorithm has high efficiency and accuracy,strong stability and robustness,and can effectively detect slight line scratches.
In the production and transportation processes of the light guide plate,various defects,in particular,slight line scratches,are inevitably caused.These defect areas cannot be accurately extracted by using the existing algorithm.In this paper,based on the analysis of the cause and imaging characteristics of the slight scratch on the light guide plate,a method for detecting the slight line scratch on the light guide plate based on multi-directional Gabor filtering and sub-pixel analysis is proposed.Firstly,in order to highlight the defect area,a multi-directional Gabor filter is designed.Furthermore,the sub-pixel image analysis method is used to accurately segment the suspected defect area from the background image.Finally,the area shape feature is analyzed to accurately extract the slight line scratch defects.The experimental results show that the algorithm has high efficiency and accuracy,strong stability and robustness,and can effectively detect slight line scratches.
引文
[1] Wang J,Zurada J M,Wang Y,et al.Boundedness of weight elimination for BP neural networks[J].Lecture Notes in Computer Science,2014,10(1):155-165.
[2] SONG Li-mei,WANG Peng-qiang,CANG Yu-lan,et al.A non-contact real-time measurement of lamp dimension based on machine vision[J].Optoelectronics Letters,2015,11(2):145-148.
[3] WANG Yao-nan,CHEN Tie-jian,HE Zhen-dong,et al.Control methods of intelligent manufacturing equipment visual inspection[J].Control Theory & Applications,2015,32(3):273-286.王耀南,陈铁健,贺振东,等.智能制造装备视觉检测控制方法综述[J].控制理论与应用,2015,32(3):273-286.
[4] DUAN Hong-yan,SHAO Hao,ZHANG Shu-zheng,et al.An improved algorithm for image Eedge detection based on canny operator[J].Journal of Shanghai Jiaotong University,2016,50(12):1861-1865.段红燕,邵豪,张淑珍,等.一种基于Canny算子的图像边缘检测改进算法[J].上海交通大学学报,2016,50(12):1861-1865.
[5] YUAN Chun-lan,XIONG Zong-long,ZHOU Xue-hua,et al.Study of infrared image edge detection based on sobel operator[J].Laser & Infrared,2009,39(1):85-87.袁春兰,熊宗龙,周雪花,等.基于Sobel算子的图像边缘检测研究[J].激光与红外,2009,39(1):85-87.
[6] QIAO Nao-sheng,ZOU Bei-ji,DENG Lei,et al.An edge detection method based on image fusion in a noisy image[J].Journal of Optoelectronics·Laser,2012,23(11):2215-2220.乔闹生,邹北骥,邓磊,等.一种基于图像融合的含噪图像边缘检测方法[J].光电子·激光,2012,23(11):2215-2220.
[7] LIU Qiao-nan,ZHANG Ren-jie,LI Qian-qian.Detection of crosshatch-angles of cylinder liner based on improved hough transform[J].Packaging Engineering,2017,38(15):14-20.刘乔楠,张仁杰,李倩倩.基于改进的Hough变换缸套内面网纹夹角检测[J].包装工程,2017,38(15):14-20.
[8] Nguyen H N,Kam T Y,Cheng P Y.Automatic crack detection from 2D images using a crack measure-based B-spline level set model[J].Multidimensional Systems and Signal Processing,2018,29(1):213-214.
[9] Yang C D,Geng M Y.The crack detection algorithm of pavement image based on edge information[C].6th International Conference on Computer-Aided Design,Manufacturing,Modeling and Simulation,2018:1967.
[10] MA Guo-qing,HUANG Da-nian,LIU Cai.Step-edge detection filters for the interpretation of potential field data[J].Pure and Applied Geophysics,2016,173(3):795-803.
[11] Renjie Song,Ziqi Zhang,Haiyang Liu.Edge connection based canny edge detection algorithm[J].Pattern Recognition and Image Analysis,2017,27(4):740-747.
[12] ZHANG Gui-mei,SUN Xiao-xu,CHEN Bin-bin,et al.Edge detection algorithm combining fractional order derivative and Cannyoperator[J].Journal of Image and Graphics,2016,21(8):1028-1038.张桂梅,孙晓旭,陈彬彬,等.结合分数阶微分和Canny算子的边缘检测[J].中国图像图形学报,2016,21(8):1028-1038.
[13] Kim J,Um S,Min D.Fast 2D complex gabor filter with Kernel decomposition[J].IEEE Transactions on Image Processing,2018,27(4):1713-1722.
[14] Zalama Eduardo,Gomez-Garcia-Bermejo Jaime,Medina Roberto,et al.Road crack detection using visual features extracted by gabor filters[J].Computer-Aided Civil and Infrastructure Engineering,2014,29(5):342-358.
[15] YUAN Mei,BO Zhao,YU Zhou,et al.Orthogonal curved-line Gabor filter for fast fingerprint enhancement[J].Electronics Letters,2014,50(3):175-177.
[16] CHEN Yu-ming,LI Yong-zhi,ZHAO Ying-kai.Sub-pixel detection algorithm based on cubic B-spline curve and multi-scale adaptive wavelet transform[J].OPTIK,2015,127(1):11-14.
[17] ZHU Wei-bin,LIU Ming-pei,YE Shu-liang.Sub-pixel image edge detection based on neighborhood characteristic analysis for small modulus gear[J].Chinese Journal of Scientific Instrument,2018,39(3):148-156.
[18] YAO Qiang,WANG Ya-gang,ZHANG Wei,et al.Extraction algorithm of camera calibration board feature based on sub-pixel edge[J].Packaging Engineering,2018,39(11):165-170.姚强,王亚刚,张伟,等.基于亚像素边缘的摄像机标定板特征提取算法[J].包装工程,2018,39(11):165-170.
[19] LI De-long,GONG Shi-hua,WANG Zi-yue.Research on positioning algorithm of LED chips based on sub-pixel edge detection[J].Semiconductor Optoelectronics,2017,38(3):369-374.李德龙,龚时华,王子悦.基于亚像素边缘检测的LED芯片定位算法研究[J].半导体光电,2017,38(3):369-374.
[20] YANG Ren-min,ZHENG Zhou,CHEN Bin,et al.Extraction algorithm of part feature sizes based on machine vision[J].Packaging Engineering,2017,38(9):151-156.杨仁民,郑洲,陈斌,等.基于机器视觉的零件特征尺寸提取算法[J].包装工程,2017,38(9):151-156.
[2] SONG Li-mei,WANG Peng-qiang,CANG Yu-lan,et al.A non-contact real-time measurement of lamp dimension based on machine vision[J].Optoelectronics Letters,2015,11(2):145-148.
[3] WANG Yao-nan,CHEN Tie-jian,HE Zhen-dong,et al.Control methods of intelligent manufacturing equipment visual inspection[J].Control Theory & Applications,2015,32(3):273-286.王耀南,陈铁健,贺振东,等.智能制造装备视觉检测控制方法综述[J].控制理论与应用,2015,32(3):273-286.
[4] DUAN Hong-yan,SHAO Hao,ZHANG Shu-zheng,et al.An improved algorithm for image Eedge detection based on canny operator[J].Journal of Shanghai Jiaotong University,2016,50(12):1861-1865.段红燕,邵豪,张淑珍,等.一种基于Canny算子的图像边缘检测改进算法[J].上海交通大学学报,2016,50(12):1861-1865.
[5] YUAN Chun-lan,XIONG Zong-long,ZHOU Xue-hua,et al.Study of infrared image edge detection based on sobel operator[J].Laser & Infrared,2009,39(1):85-87.袁春兰,熊宗龙,周雪花,等.基于Sobel算子的图像边缘检测研究[J].激光与红外,2009,39(1):85-87.
[6] QIAO Nao-sheng,ZOU Bei-ji,DENG Lei,et al.An edge detection method based on image fusion in a noisy image[J].Journal of Optoelectronics·Laser,2012,23(11):2215-2220.乔闹生,邹北骥,邓磊,等.一种基于图像融合的含噪图像边缘检测方法[J].光电子·激光,2012,23(11):2215-2220.
[7] LIU Qiao-nan,ZHANG Ren-jie,LI Qian-qian.Detection of crosshatch-angles of cylinder liner based on improved hough transform[J].Packaging Engineering,2017,38(15):14-20.刘乔楠,张仁杰,李倩倩.基于改进的Hough变换缸套内面网纹夹角检测[J].包装工程,2017,38(15):14-20.
[8] Nguyen H N,Kam T Y,Cheng P Y.Automatic crack detection from 2D images using a crack measure-based B-spline level set model[J].Multidimensional Systems and Signal Processing,2018,29(1):213-214.
[9] Yang C D,Geng M Y.The crack detection algorithm of pavement image based on edge information[C].6th International Conference on Computer-Aided Design,Manufacturing,Modeling and Simulation,2018:1967.
[10] MA Guo-qing,HUANG Da-nian,LIU Cai.Step-edge detection filters for the interpretation of potential field data[J].Pure and Applied Geophysics,2016,173(3):795-803.
[11] Renjie Song,Ziqi Zhang,Haiyang Liu.Edge connection based canny edge detection algorithm[J].Pattern Recognition and Image Analysis,2017,27(4):740-747.
[12] ZHANG Gui-mei,SUN Xiao-xu,CHEN Bin-bin,et al.Edge detection algorithm combining fractional order derivative and Cannyoperator[J].Journal of Image and Graphics,2016,21(8):1028-1038.张桂梅,孙晓旭,陈彬彬,等.结合分数阶微分和Canny算子的边缘检测[J].中国图像图形学报,2016,21(8):1028-1038.
[13] Kim J,Um S,Min D.Fast 2D complex gabor filter with Kernel decomposition[J].IEEE Transactions on Image Processing,2018,27(4):1713-1722.
[14] Zalama Eduardo,Gomez-Garcia-Bermejo Jaime,Medina Roberto,et al.Road crack detection using visual features extracted by gabor filters[J].Computer-Aided Civil and Infrastructure Engineering,2014,29(5):342-358.
[15] YUAN Mei,BO Zhao,YU Zhou,et al.Orthogonal curved-line Gabor filter for fast fingerprint enhancement[J].Electronics Letters,2014,50(3):175-177.
[16] CHEN Yu-ming,LI Yong-zhi,ZHAO Ying-kai.Sub-pixel detection algorithm based on cubic B-spline curve and multi-scale adaptive wavelet transform[J].OPTIK,2015,127(1):11-14.
[17] ZHU Wei-bin,LIU Ming-pei,YE Shu-liang.Sub-pixel image edge detection based on neighborhood characteristic analysis for small modulus gear[J].Chinese Journal of Scientific Instrument,2018,39(3):148-156.
[18] YAO Qiang,WANG Ya-gang,ZHANG Wei,et al.Extraction algorithm of camera calibration board feature based on sub-pixel edge[J].Packaging Engineering,2018,39(11):165-170.姚强,王亚刚,张伟,等.基于亚像素边缘的摄像机标定板特征提取算法[J].包装工程,2018,39(11):165-170.
[19] LI De-long,GONG Shi-hua,WANG Zi-yue.Research on positioning algorithm of LED chips based on sub-pixel edge detection[J].Semiconductor Optoelectronics,2017,38(3):369-374.李德龙,龚时华,王子悦.基于亚像素边缘检测的LED芯片定位算法研究[J].半导体光电,2017,38(3):369-374.
[20] YANG Ren-min,ZHENG Zhou,CHEN Bin,et al.Extraction algorithm of part feature sizes based on machine vision[J].Packaging Engineering,2017,38(9):151-156.杨仁民,郑洲,陈斌,等.基于机器视觉的零件特征尺寸提取算法[J].包装工程,2017,38(9):151-156.