基于双高斯纹理滤波模板和极值点韦伯对比度的圆柱锂电池凹坑缺陷检测

doi:10.12263/DZXB.20210240

电子学报 ›› 2022, Vol. 50 ›› Issue (3): 637-642.DOI: 10.12263/DZXB.20210240

基于双高斯纹理滤波模板和极值点韦伯对比度的圆柱锂电池凹坑缺陷检测

郭绍陶¹^,², 苑玮琦¹^,²

^1.沈阳工业大学视觉检测技术研究所, 辽宁沈阳 110870
^2.辽宁省机器视觉重点实验室, 辽宁沈阳 110870

收稿日期:2021-02-09 修回日期:2021-04-02 出版日期:2022-03-25 发布日期:2022-03-25
作者简介:郭绍陶女，1989年生于辽宁鞍山.现为沈阳工业大学视觉检测技术研究所博士研究生.主要研究方向为机器视觉检测和生物特征识别.E-mail:381592719@qq.com
苑玮琦男，1960年生于辽宁辽阳.现为沈阳工业大学教授、博士生导师.主要研究方向为机器视觉检测和生物特征识别.E-mail:yuan60@126.com
基金资助:
国家自然科学基金(61271365)

Pit Defect Detection of Cylindrical Lithium Battery Based on Double Gaussian Texture Filtering Template and Extreme Point Weber Contrast

GUO Shao-tao¹^,², YUAN Wei-qi¹^,²

^1.Computer Vision Group，Shenyang University of Technology，Shenyang，Liaoning 110870，China
^2.Key Laboratory of Machine Vision，Shenyang，Liaoning 110870，China

Received:2021-02-09 Revised:2021-04-02 Online:2022-03-25 Published:2022-03-25

摘要/Abstract

摘要：

本文针对圆柱锂电池表面图像具有亮度不均匀、金属表面反射不均、氧化锈斑和高亮噪声点等问题，提出一种基于机器视觉的解决方案.采用定义的双高斯纹理滤波模板与图像进行卷积，提取图像每列的灰度分布曲线，采用定义的极值点韦伯对比度选择曲线上突变点的阈值，根据先验知识筛选出凹坑候选区域，利用区域特征和灰度特征排除非凹坑纹理.测试结果表明，所提方法的拒真率（false rejection rate）和认假率（false accept rate）分别为5.49%和5.38%，亮度不均匀和金属表面反射不均没有对凹坑检测产生影响.

关键词: 双高斯纹理滤波模板, 极值点韦伯对比度, 圆柱锂电池, 凹坑, 灰度分布曲线, 机器视觉

Abstract:

A solution based on machine vision is proposed to solve the problems of surface image of cylindrical lithium battery, such as uneven brightness, uneven reflection on metal surface, oxidation rust spots and highlighting noise points. A defined double Gaussian texture filtering template was used to convolve with the image. The grayscale distribution curve of each column of the image was extracted. The extraction threshold of the discontinuous point on the grayscale distribution curve was calculated by using the defined extreme point Weber contrast. The candidate pit regions were screened out according to the prior knowledge. The non-pit textures were excluded by using region features and gray value features. The test results indicate the false rejection rate (FRR) and false accept rate (FAR) are 5.49 percent and 5.38 percent respectively. And the uneven brightness and uneven reflection had no effect on pit detection.

Key words: double Gaussian texture filtering template, extreme point Weber contrast, cylindrical lithium battery, pit, grayscale distribution curve, machine vision

中图分类号:

TP391.41

郭绍陶, 苑玮琦. 基于双高斯纹理滤波模板和极值点韦伯对比度的圆柱锂电池凹坑缺陷检测[J]. 电子学报, 2022, 50(3): 637-642.

GUO Shao-tao, YUAN Wei-qi. Pit Defect Detection of Cylindrical Lithium Battery Based on Double Gaussian Texture Filtering Template and Extreme Point Weber Contrast[J]. Acta Electronica Sinica, 2022, 50(3): 637-642.

图/表 8

参考文献 18

1	朱慧. 圆柱形锂电池端面缺陷检测方法研究[D]. 沈阳:沈阳工业大学, 2019.
2	HE Z D, WANG Y N, YIN F, et al. Surface defect detection for high-speed rails using an inverse P-M diffusion model[J]. Sensor Review, 2016, 36(1): 86-97.
3	CHEN T, WANG Y, XIAO C, et al. A machine vision apparatus and method for can-end inspection[J]. IEEE Transactions on Instrumentation and Measurement, 2016, 65(9): 1-12.
4	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.
	HE Zhen-dong, WANG Yao-nan, LIU Jie, et al. Background differencing-based high-speed rail surface defect image segmentation[J]. Chinese Journal of Scientific Instrument, 2016, 37(3): 640-649. (in Chinese)
5	WANG J, LI Q, GAN J, et al. Surface defect detection via entity sparsity pursuit with intrinsic priors[J]. IEEE Transactions on Industrial Informatics, 2020, 16(1): 141-150.
6	LIU L, GUO C, WANG L, et al. Nondestructive visualization and quantitative characterization of defects in silicone polymer insulators based on laser shearography[J]. IEEE Sensors Journal, 2019, 19(15): 6508-6516.
7	LI W B, LU C H, ZHANG J C. A lower envelope Weber contrast detection algorithm for steel bar surface pit defects[J]. Optics & Laser Technology, 2013, 45: 654-659.
8	苑玮琦, 郭绍陶. 圆柱型覆膜锂电池圆周面凹坑检测方法研究[J]. 仪器仪表学报, 2020, 41(2): 146-156.
	YUAN Wei-qi, GUO Shao-tao. Research on the detection method of pit on the cylindrical surface of cylindrical coated lithium battery[J]. Chinese Journal of Scientific Instrument, 2020, 41(2): 146-156. (in Chinese)
9	LIU K, WANG H, CHEN H, et al. Steel surface defect detection using a new Haar-Weibull-variance model in unsupervised manner[J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(10): 2585-2596.
10	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.
	MIN Yong-zhi, YUE Biao, MA Hong-feng, 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. (in Chinese)
11	SU B, CHEN H, ZHU Y, et al. Classification of manufacturing defects in multicrystalline solar cells with novel feature descriptor[J]. IEEE Transactions on Instrumentation and Measurement, 2019, 68: 1-14.
12	曹义亲, 刘龙标. 基于缺陷比例限制的背景差分钢轨表面缺陷检测方法[J]. 计算机应用, 2020, 40(10): 3066-3074.
	CAO Yi-qin, LIU Long-biao.Rail surface defect detection method based on background differential with defect proportion limitation[J]. Journal of Computer Applications, 2020, 40(10): 3066-3074. (in Chinese)
13	REN R, HUNG T, TAN K C. A generic deep-learning-based approach for automated surface inspection[J]. IEEE Transactions on Cybernetics, 2018,48(3): 929-940.
14	JE-KANG P, BAE-KEUN K, JUN-HYUB P, et al. Machine learning-based imaging system for surface defect inspection[J]. International Journal of Precision Engineering & Manufacturing Green Technology, 2016,3(3): 303-310.
15	GUAN S, LEI M, LU H. A steel surface defect recognition algorithm based on improved deep learning network model using feature visualization and quality evaluation[J]. IEEE Access, 2020, 8: 49885-49895.
16	CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
17	SHAKARJI C M. Least-squares fitting algorithms of the NIST algorithm testing system[J]. Journal of Research of the National Institute of Standards and Technology,1998,103(6): 633-641.
18	HUBER P J. Robust regression: asymptotics, conjectures and Monte Carlo[J]. The Annals of Statistics, 1973, 1(5): 799-821.

t T₁	0.10	0.12	0.13	0.19	0.23	0.25
3.0	0.00	0.00	0.00	0.00	0.47	1.43
3.4	0.00	0.00	0.00	0.47	0.47	1.43
3.6	0.00	0.00	0.00	0.47	0.47	1.43
3.7	0.47	0.47	0.47	0.47	0.95	1.43

t T₁	0.10	0.12	0.13	0.19	0.23	0.25
3.0	0.00	0.00	0.00	0.00	0.47	1.43
3.4	0.00	0.00	0.00	0.47	0.47	1.43
3.6	0.00	0.00	0.00	0.47	0.47	1.43
3.7	0.47	0.47	0.47	0.47	0.95	1.43

T₂/T₃	FRR/%	FAR/%
0.10/0.06	3.92	5.38
0.11/0.05	3.92	6.15
0.11/0.06	4.70	5.38
0.12/0.05	4.71	6.15
0.12/0.06	5.49	5.38
0.12/0.07	6.67	5.38

T₂/T₃	FRR/%	FAR/%
0.10/0.06	3.92	5.38
0.11/0.05	3.92	6.15
0.11/0.06	4.70	5.38
0.12/0.05	4.71	6.15
0.12/0.06	5.49	5.38
0.12/0.07	6.67	5.38

算法	FRR	FAR
文献［4］	5.74	6.36
文献［6］	8.22	15.45
文献［7］	14.46	10.91
本文	5.49	5.38

基于双高斯纹理滤波模板和极值点韦伯对比度的圆柱锂电池凹坑缺陷检测

Pit Defect Detection of Cylindrical Lithium Battery Based on Double Gaussian Texture Filtering Template and Extreme Point Weber Contrast

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 18

相关文章 5

编辑推荐

Metrics

[1]	谢佳龙, 张波涛, 吕强. 一种基于双流融合3D卷积神经网络的动态头势识别方法[J]. 电子学报, 2021, 49(7): 1363-1369.
[2]	赖锦祥, 雷亮, 阮杨, 邓凯元, 徐初东, 周金运. 基于等积环投影与Zernike矩的快速模板匹配[J]. 电子学报, 2019, 47(6): 1324-1330.
[3]	葛利跃, 张聪炫, 陈震, 黎明, 陈昊. 相互结构引导滤波TV-L1变分光流估计[J]. 电子学报, 2019, 47(3): 707-713.
[4]	覃剑, 肖婷. 基于区域复合概率的行人候选框生成[J]. 电子学报, 2018, 46(7): 1719-1725.
[5]	黄莹;王志良;涂序彦;戚颖. 一种可适应自然头动的视线追踪系统的研制及应用[J]. 电子学报, 2009, 37(4): 764-770.