基于低秩信息的纽扣无缺陷图像重建与缺陷检出算法
|
摘要
纽扣表面缺陷形态、大小、位置多变,导致缺陷检测成为一个具有挑战性的问题。基于缺陷图像信息空间结构相关性,提出了一种基于低秩信息的纽扣图像重建方法。该方法采用低秩约束缺陷图像矩阵,通过回归的方式重构纽扣表面无缺陷图像,并利用差影法分离带有缺陷信息的残差图像,通过局部加权自适应阈值使缺陷有效显现。所提方法将最小化残差矩阵的秩转化为最小化核范数,并通过交替方向乘子法求解回归系数,利用正样本实现图像重建。针对构建的纽扣样本测试集对算法性能进行测试,证明所提方法对于不同类别的纽扣和不同大小、形状的缺陷都是有效的,算法准确率达99%,并且该方法对于光照变化也具有一定的适应性。
Defect detection is a challenging problem due to the diversity of appearances, sizes and locations of button surface defects. A low-rank information based button image reconstruction method is proposed based on the spatial structure correlation of defect image information, in which the low-rank constrained defect image matrix is utilized to reconstruct the defect-free button surface images through regression and the background subtraction method is adopted to separate the residual images with defect information, and thus the defects can be effectively extracted through the locally weighted adaptive threshold. In addition, in this method, the minimum rank of the residual matrix is converted into the minimum nuclear norm, the regression coefficients are solved by the alternating direction multiplier method, and thus the image reconstruction is realized with positive samples. According to the performance test of the reconstructed button sample set, it is verified that the proposed method is effective for different types of buttons and different sizes and shapes of defects, and the accuracy of the algorithm is 99%.Moreover, the method has a certain adaptability to illumination variation.
Defect detection is a challenging problem due to the diversity of appearances, sizes and locations of button surface defects. A low-rank information based button image reconstruction method is proposed based on the spatial structure correlation of defect image information, in which the low-rank constrained defect image matrix is utilized to reconstruct the defect-free button surface images through regression and the background subtraction method is adopted to separate the residual images with defect information, and thus the defects can be effectively extracted through the locally weighted adaptive threshold. In addition, in this method, the minimum rank of the residual matrix is converted into the minimum nuclear norm, the regression coefficients are solved by the alternating direction multiplier method, and thus the image reconstruction is realized with positive samples. According to the performance test of the reconstructed button sample set, it is verified that the proposed method is effective for different types of buttons and different sizes and shapes of defects, and the accuracy of the algorithm is 99%.Moreover, the method has a certain adaptability to illumination variation.
引文
[1] Wang Q C, Jing J F, Zhang L, et al. Denim defect detection based on optimal Gabor filter[J]. Laser&Optoelectronics Progress, 2018, 55(7):071501.王清晨,景军锋,张蕾,等.基于最优Gabor滤波器的牛仔布缺陷检测[J].激光与光电子学进展,2018,55(7):071501.
[2] Crispin A J. Rankov V. Automated inspection of PCB components using a genetic algorithm templatematching approach[J]. International Journal of Advanced Manufacturing Technology, 2007, 35(3/4):293-300.
[3] Ghorai S, Mukherjee A, Gangadaran M, et al.Automatic defect detection on hot-rolled flat steel products[J]. IEEE Transactions on Instrumentation&Measurement, 2013, 62(3):612-621.
[4] Zhang Y Z, Xu C, Li C, et al. Wood defect detection method with PC A feature fusion and compressed sensing[J]. Journal of Forestry Research, 2015, 26(3):745-751.
[5] Gong F, Zhang X W, Sun H. Detection system for solar module surface defects based on constrained ICA model and PSO method[J]. Acta Optica Sinica,2012, 32(4):0415002.龚芳,张学武,孙浩.基于独立分量分析和粒子群算法的太阳能电池表面缺陷红外热成像检测[J].光学学报,2012, 32(4):0415002.
[6] Zhu B F, Chen W J, Li W S, et al. Liquidcrystal display defect detection based on Fourier-Mellin transform[J]. Laser Optoelectronics Progress,2017, 54(12):121502.朱炳斐,陈文建,李武森,等.基于Fourier-Mellin变换的液晶显示屏显示缺陷检测[J].激光与光电子学进展,2017, 54(12):121502.
[7] Zhou W J, Fei M R, Zhou H Y, et al. A sparse representation based fast detection method for surface defect detection of bottle caps[J]. Neurocomputing,2014, 123:406-414.
[8] Wang S, Lu S, Dong Z, et al. Dual-tree complex wavelet transform and twin support vector machine for pathological brain detection[J]. Applied Sciences,2016, 6(6):169.
[9] Zhang M, Wu J, Lin H, et al. Theapplication of one-class classifier based on CNN in image defect detection[J]. Procedia Computer Science, 2017,114:341-348.
[10] 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.
[11] Daugman J. How iris recognition works[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(1):21-30.
[12] Candès E J, Li X D, Ma Y, et al. Robust principal component analysis?[J]. Journal of the ACM, 2011,58(3):11.
[13] Hansson A, Liu Z, Vandenberghe L. Subspace system identification via weighted nuclear norm optimization[C]. 51st IEEE Conference on Decision and Control(CDC), 2012:13289538.
[14] Seki M, Fujiwara H, Sumi K. A robust background subtraction method for changing background[C].Proceedings Fifth IEEE Workshop on Applications of Computer Vision, 2000:6806457.
[15] Han Y, Yubin W U, Cao D, et al. Defect detection on button surfaces with the weighted least-squares model[J]. Frontiers of Optoelectronics, 2017, 10(2):151-159.
[2] Crispin A J. Rankov V. Automated inspection of PCB components using a genetic algorithm templatematching approach[J]. International Journal of Advanced Manufacturing Technology, 2007, 35(3/4):293-300.
[3] Ghorai S, Mukherjee A, Gangadaran M, et al.Automatic defect detection on hot-rolled flat steel products[J]. IEEE Transactions on Instrumentation&Measurement, 2013, 62(3):612-621.
[4] Zhang Y Z, Xu C, Li C, et al. Wood defect detection method with PC A feature fusion and compressed sensing[J]. Journal of Forestry Research, 2015, 26(3):745-751.
[5] Gong F, Zhang X W, Sun H. Detection system for solar module surface defects based on constrained ICA model and PSO method[J]. Acta Optica Sinica,2012, 32(4):0415002.龚芳,张学武,孙浩.基于独立分量分析和粒子群算法的太阳能电池表面缺陷红外热成像检测[J].光学学报,2012, 32(4):0415002.
[6] Zhu B F, Chen W J, Li W S, et al. Liquidcrystal display defect detection based on Fourier-Mellin transform[J]. Laser Optoelectronics Progress,2017, 54(12):121502.朱炳斐,陈文建,李武森,等.基于Fourier-Mellin变换的液晶显示屏显示缺陷检测[J].激光与光电子学进展,2017, 54(12):121502.
[7] Zhou W J, Fei M R, Zhou H Y, et al. A sparse representation based fast detection method for surface defect detection of bottle caps[J]. Neurocomputing,2014, 123:406-414.
[8] Wang S, Lu S, Dong Z, et al. Dual-tree complex wavelet transform and twin support vector machine for pathological brain detection[J]. Applied Sciences,2016, 6(6):169.
[9] Zhang M, Wu J, Lin H, et al. Theapplication of one-class classifier based on CNN in image defect detection[J]. Procedia Computer Science, 2017,114:341-348.
[10] 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.
[11] Daugman J. How iris recognition works[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(1):21-30.
[12] Candès E J, Li X D, Ma Y, et al. Robust principal component analysis?[J]. Journal of the ACM, 2011,58(3):11.
[13] Hansson A, Liu Z, Vandenberghe L. Subspace system identification via weighted nuclear norm optimization[C]. 51st IEEE Conference on Decision and Control(CDC), 2012:13289538.
[14] Seki M, Fujiwara H, Sumi K. A robust background subtraction method for changing background[C].Proceedings Fifth IEEE Workshop on Applications of Computer Vision, 2000:6806457.
[15] Han Y, Yubin W U, Cao D, et al. Defect detection on button surfaces with the weighted least-squares model[J]. Frontiers of Optoelectronics, 2017, 10(2):151-159.