基于Zernike矩亚像素的高反光金属工件缺陷检测
|
摘要
提出了一种基于Zernike矩改进的亚像素边缘提取的工件缺陷检测算法。对图像进行小波分解,并对分解的各频段信息分别利用不同算法进行预处理,重构图像后可以有效地滤除图像噪声,增强目标信息;利用改进的Zernike矩亚像素边缘提取算法定位图像边缘并提取特征信息,减小了边缘信息误差,能够更精确地分割出目标轮廓;通过计算连通区域几何参数及全局信息熵来判断是否存在缺陷。通过实验对算法进行了验证,结果表明,提出的算法可以降低金属高光噪声,有效地提取缺陷边缘,并且在环境光照变化时具有较强的稳健性,金属工件的缺陷检测精度得到提高。
This study proposes a novel subpixel edge extraction algorithm for the detection of defects in workpieces,which is based on Zernike moments.First,the target image is decomposed using a wavelet transform,and the decomposed frequency information is preprocessed by employing different algorithms.After reconstruction,the image noise can be effectively filtered out and the target information can be enhanced.Then,the proposed subpixel edge extraction algorithm is applied to locate the image edges and extract their feature information with the aim to reduce the edge information error and segment the target contour more accurately.Finally,the geometric parameters of the surrounding region and the global information entropy are calculated to determine whether there are defects.The algorithm is verified with an experiment,and the experimental results show that the proposed algorithm can reduce the metal high-light noise and extract the defect edges effectively.Moreover,the algorithm is robust even when the ambient light illumination changes,and thus improves the accuracy of metal-defect detection.
This study proposes a novel subpixel edge extraction algorithm for the detection of defects in workpieces,which is based on Zernike moments.First,the target image is decomposed using a wavelet transform,and the decomposed frequency information is preprocessed by employing different algorithms.After reconstruction,the image noise can be effectively filtered out and the target information can be enhanced.Then,the proposed subpixel edge extraction algorithm is applied to locate the image edges and extract their feature information with the aim to reduce the edge information error and segment the target contour more accurately.Finally,the geometric parameters of the surrounding region and the global information entropy are calculated to determine whether there are defects.The algorithm is verified with an experiment,and the experimental results show that the proposed algorithm can reduce the metal high-light noise and extract the defect edges effectively.Moreover,the algorithm is robust even when the ambient light illumination changes,and thus improves the accuracy of metal-defect detection.
引文
[1] Lu R S, Wu A,Zhang T D,et al.Review on automated optical(visual)inspection and its applications in defect detection[J]. Acta Optica Sinica,2018,38(8):0815002.卢荣胜,吴昂,张腾达,等.自动光学(视觉)检测技术及其在缺陷检测中的应用综述[J].光学学报,2018,38(8):0815002.
[2] Li T T,Yang F,Xu X L.Method of large-scale measurement based on multi-vision line structured light sensor[J].Chinese Journal of Lasers,2017,44(11):1104003.李涛涛,杨峰,许献磊.基于多视觉线结构光传感器的大尺度测量方法[J].中国激光,2017,44(11):1104003.
[3] Chen G F,Guan G Y,Wei X.Online stamping parts surface defects detection based on machine vision[J].Laser&Optoelectronics Progress,2018,55(1):011501.陈广锋,管观洋,魏鑫.基于机器视觉的冲压件表面缺陷在线检测研究[J].激光与光电子学进展,2018,55(1):011501.
[4] Su J H,Liu S L.Measure system of surface flaw and morphology analysis of cylindrical high precision parts[J].Laser&Optoelectronics Progress,2014,51(4):041202.苏俊宏,刘胜利.圆柱型高精密零件表面缺陷检测及形貌分析[J].激光与光电子学进展,2014,51(4):041202.
[5] Sun K Y,Jiang L X,Wang J Y,et al.Automatic visual inspection system of shaft part surface[J].Nondestructive Testing,2016,38(6):53-57,72.孙阔原,蒋理兴,王俊亚,等.轴类工件表面视觉自动检测系统[J].无损检测,2016,38(6):53-57,72.
[6] Jiang M H,Fu L H,Wang Z,et al.A new method for specular curved surface defect inspection based on reflectedpatternintegrity[J]. Journalof Measurement Science and Instrumentation,2016,7(3):221-228.姜美华,付鲁华,王仲,等.基于图案完整性的高反射曲面缺陷检测新方法[J].测试科学与仪器(英文版),2016,7(3):221-228.
[7] Min Y Z,Yue B,Ma H F,et al.Rail surface defects detection based on gray scale gradient characteristics of image[J]. Chinese Journal of Scientific Instrument,2018,39(4):220-229.闵永智,岳彪,马宏锋,等.基于图像灰度梯度特征的钢轨表面缺陷检测[J].仪器仪表学报,2018,39(4):220-229.
[8] Qiao N S.Edge detection of printed circuit board defect image[J].Acta Photonica Sinica,2016,45(4):0410001.乔闹生.印制电路板缺陷图像边缘检测[J].光子学报,2016,45(4):0410001.
[9] Guo M,Hu L L,Zhao J T.Surface defect detection method of ceramic bowl based on Kirsch and Canny operator[J].Acta Optica Sinica,2016,36(9):0904001.郭萌,胡辽林,赵江涛.基于Kirsch和Canny算子的陶瓷碗表面缺陷检测方法[J].光学学报,2016,36(9):0904001.
[10] Mirzapour F,Ghassemian H.Moment-based feature extraction from high spatial resolution hyperspectral images[J].International Journal of Remote Sensing,2016,37(6):1349-1361.
[11] Wang L,Zou L,Zhao S M.Edge detection based on subpixel-speckle-shifting ghost imaging[J].Optics Communications,2018,407:181-185.
[12] He Y B,Zeng Y J,Chen H X,et al.Research on improved edge extraction algorithm of rectangular piece[J].International Journal of Modern Physics C,2018,29(1):1850007.
[13] Kaur M,Kumar V.Fourier-Mellin moment-based intertwining map for image encryption[J].Modern Physics Letters B,2018,32(9):1850115.
[14] Nagarathinam K,Kathavarayan R S.Moving shadow detection based on stationary wavelet transform and Zernike moments[J].IET Computer Vision,2018,12(6):787-795.
[15] Li Z H,Hua Y S.Research on the placement of light source,camera and detected workpiece in surface defect detection[J]. ElectronicScienceand Technology,2018,31(5):66-68,72.李智慧,华云松.表面缺陷检测中工件与光源相机位置关系研究[J].电子科技,2018,31(5):66-68,72.
[16] Dabov K, Foi A, Katkovnik V,et al.Image denoisingbysparse3D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,16(8):2080-2095.
[17] Li H Y,Cao W G,Li S R,et al.Progressive image denoising algorithm[J]. JournalofSystem Simulation,2017,29(2):282-294.李海洋,曹伟国,李诗锐,等.渐进式图像去噪算法[J].系统仿真学报,2017,29(2):282-294.
[18] Lin S C F,Wong C Y,Jiang G,et al.Intensity and edge based adaptive unsharp masking filter for color image enhancement[J].Optik,2016,127(1):407-414.
[19] Lyvers E P, Mitchell O R,Akey M L,et al.Subpixel measurements using a moment-based edge operator[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(12):1293-1309.
[20] Wang Y Q,Hui M,Liu M,et al.Edge extraction of optical subaperture based on differential box-counting dimension method with window merge replication[J].Optical Engineering,2016,55(9):093107.
[21] Guo H R,Shao W,Zhou A W,et al.Novel defect recognition method based on adaptive global threshold for highlight metal surface[J].Chinese Journal of Scientific Instrument,2017,38(11):2797-2804.郭皓然,邵伟,周阿维,等.全局阈值自适应的高亮金属表面缺陷识别新方法[J].仪器仪表学报,2017,38(11):2797-2804.
[22] He Z D, Wang Y N,Liu J,et al.Background differencing-based high-speed rail surface defect image segmentation[J].Chinese Journal of Scientific Instrument,2016,37(3):640-649.贺振东,王耀南,刘洁,等.基于背景差分的高铁钢轨表面缺陷图像分割[J].仪器仪表学报,2016,37(3):640-649.
[23] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing,2004,13(4):600-612.
[2] Li T T,Yang F,Xu X L.Method of large-scale measurement based on multi-vision line structured light sensor[J].Chinese Journal of Lasers,2017,44(11):1104003.李涛涛,杨峰,许献磊.基于多视觉线结构光传感器的大尺度测量方法[J].中国激光,2017,44(11):1104003.
[3] Chen G F,Guan G Y,Wei X.Online stamping parts surface defects detection based on machine vision[J].Laser&Optoelectronics Progress,2018,55(1):011501.陈广锋,管观洋,魏鑫.基于机器视觉的冲压件表面缺陷在线检测研究[J].激光与光电子学进展,2018,55(1):011501.
[4] Su J H,Liu S L.Measure system of surface flaw and morphology analysis of cylindrical high precision parts[J].Laser&Optoelectronics Progress,2014,51(4):041202.苏俊宏,刘胜利.圆柱型高精密零件表面缺陷检测及形貌分析[J].激光与光电子学进展,2014,51(4):041202.
[5] Sun K Y,Jiang L X,Wang J Y,et al.Automatic visual inspection system of shaft part surface[J].Nondestructive Testing,2016,38(6):53-57,72.孙阔原,蒋理兴,王俊亚,等.轴类工件表面视觉自动检测系统[J].无损检测,2016,38(6):53-57,72.
[6] Jiang M H,Fu L H,Wang Z,et al.A new method for specular curved surface defect inspection based on reflectedpatternintegrity[J]. Journalof Measurement Science and Instrumentation,2016,7(3):221-228.姜美华,付鲁华,王仲,等.基于图案完整性的高反射曲面缺陷检测新方法[J].测试科学与仪器(英文版),2016,7(3):221-228.
[7] Min Y Z,Yue B,Ma H F,et al.Rail surface defects detection based on gray scale gradient characteristics of image[J]. Chinese Journal of Scientific Instrument,2018,39(4):220-229.闵永智,岳彪,马宏锋,等.基于图像灰度梯度特征的钢轨表面缺陷检测[J].仪器仪表学报,2018,39(4):220-229.
[8] Qiao N S.Edge detection of printed circuit board defect image[J].Acta Photonica Sinica,2016,45(4):0410001.乔闹生.印制电路板缺陷图像边缘检测[J].光子学报,2016,45(4):0410001.
[9] Guo M,Hu L L,Zhao J T.Surface defect detection method of ceramic bowl based on Kirsch and Canny operator[J].Acta Optica Sinica,2016,36(9):0904001.郭萌,胡辽林,赵江涛.基于Kirsch和Canny算子的陶瓷碗表面缺陷检测方法[J].光学学报,2016,36(9):0904001.
[10] Mirzapour F,Ghassemian H.Moment-based feature extraction from high spatial resolution hyperspectral images[J].International Journal of Remote Sensing,2016,37(6):1349-1361.
[11] Wang L,Zou L,Zhao S M.Edge detection based on subpixel-speckle-shifting ghost imaging[J].Optics Communications,2018,407:181-185.
[12] He Y B,Zeng Y J,Chen H X,et al.Research on improved edge extraction algorithm of rectangular piece[J].International Journal of Modern Physics C,2018,29(1):1850007.
[13] Kaur M,Kumar V.Fourier-Mellin moment-based intertwining map for image encryption[J].Modern Physics Letters B,2018,32(9):1850115.
[14] Nagarathinam K,Kathavarayan R S.Moving shadow detection based on stationary wavelet transform and Zernike moments[J].IET Computer Vision,2018,12(6):787-795.
[15] Li Z H,Hua Y S.Research on the placement of light source,camera and detected workpiece in surface defect detection[J]. ElectronicScienceand Technology,2018,31(5):66-68,72.李智慧,华云松.表面缺陷检测中工件与光源相机位置关系研究[J].电子科技,2018,31(5):66-68,72.
[16] Dabov K, Foi A, Katkovnik V,et al.Image denoisingbysparse3D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,16(8):2080-2095.
[17] Li H Y,Cao W G,Li S R,et al.Progressive image denoising algorithm[J]. JournalofSystem Simulation,2017,29(2):282-294.李海洋,曹伟国,李诗锐,等.渐进式图像去噪算法[J].系统仿真学报,2017,29(2):282-294.
[18] Lin S C F,Wong C Y,Jiang G,et al.Intensity and edge based adaptive unsharp masking filter for color image enhancement[J].Optik,2016,127(1):407-414.
[19] Lyvers E P, Mitchell O R,Akey M L,et al.Subpixel measurements using a moment-based edge operator[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(12):1293-1309.
[20] Wang Y Q,Hui M,Liu M,et al.Edge extraction of optical subaperture based on differential box-counting dimension method with window merge replication[J].Optical Engineering,2016,55(9):093107.
[21] Guo H R,Shao W,Zhou A W,et al.Novel defect recognition method based on adaptive global threshold for highlight metal surface[J].Chinese Journal of Scientific Instrument,2017,38(11):2797-2804.郭皓然,邵伟,周阿维,等.全局阈值自适应的高亮金属表面缺陷识别新方法[J].仪器仪表学报,2017,38(11):2797-2804.
[22] He Z D, Wang Y N,Liu J,et al.Background differencing-based high-speed rail surface defect image segmentation[J].Chinese Journal of Scientific Instrument,2016,37(3):640-649.贺振东,王耀南,刘洁,等.基于背景差分的高铁钢轨表面缺陷图像分割[J].仪器仪表学报,2016,37(3):640-649.
[23] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing,2004,13(4):600-612.