Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2019, Vol. 53 Issue (10): 1883-1891    DOI: 10.3785/j.issn.1008-973X.2019.10.005
机械与能源工程     
摩擦片表面缺陷的视觉显著性检测算法
秦钟伟1(),陈捷1,*(),洪荣晶1,吴伟伟2
1. 南京工业大学 机械与动力工程学院，江苏 南京 211800
2. 扬州大学 机械工程学院，江苏 扬州 225009
Visual salience detection algorithm for surface defects of friction sheets
Zhong-wei QIN1(),Jie CHEN1,*(),Rong-jing HONG1,Wei-wei WU2
1. School of Mechanical and Power Engineering, Nanjing Tech University, Nanjing 211800, China
2. School of Mechanical, Yangzhou University, Yangzhou 225009, China
 全文: PDF(1757 KB)   HTML
摘要：

针对摩擦片表面缺陷高精度高效率的检测要求以及摩擦片自身复杂的表面状况，提出基于视觉显著性的检测算法. 利用图像分割，将摩擦片从背景中分离；使用高斯平滑弱化表面纹理，采用多尺度细节增强算法补偿高斯平滑中丢失的缺陷边缘信息，计算图像中目标的显著性进行强弱分化；采用连通域法和OTSU，提取缺陷区域的二值图像. 经由实验验证，该算法针对摩擦片的缺陷检测具有较强的针对性，缺陷识别率超过98%，双面检测100个摩擦片用时27 s. 从客观和主观两个方面对检测结果进行评价验证，结果表明，该算法具有较高的识别率和精确度，满足工业检测的需求.
关键词： 摩擦片;  缺陷检测;  高斯平滑;  细节增强;  显著性    
Abstract:

A detection algorithm based on visual salience was proposed according to the requirement of high precision and efficiency for detecting the surface defect of friction sheet and complex surface conditions of the friction sheets themselves. The friction sheets were separated from background by the image segmentation. The surface texture was smoothed by Gaussian Blur. The multi-scale detail enhancement algorithm was used to compensate missing defect edge information in Gaussian Blur, and the saliency of the target in this image was calculated for differentiation. The connected domain method and Otsu were utilized to extract the binary images of the defect area. The experimental results show that the algorithm has strong pertinence for the defect detection of friction sheets. The defect recognition rate is over 98%. It takes 27 s to detect 100 friction sheets on both sides. From objective and subjective aspects, the detection results prove that the algorithm has high recognition rate and accuracy to meet the demand of industrial assembly.
Key words: friction sheet    defect detection    Gaussian Blur    detail enhancement    saliency
收稿日期: 2018-08-22 出版日期: 2019-09-30
CLC:  TP 391  
通讯作者: 陈捷     E-mail: 2553230346@qq.com;article_1971@163.com.cn
作者简介: 秦钟伟(1994—)，男，硕士生，从事数字图像处理的研究. orcid.org/0000-0002-2819-3911. E-mail: 2553230346@qq.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
秦钟伟
陈捷
洪荣晶
吴伟伟

引用本文:

秦钟伟,陈捷,洪荣晶,吴伟伟. 摩擦片表面缺陷的视觉显著性检测算法[J]. 浙江大学学报(工学版), 2019, 53(10): 1883-1891.

Zhong-wei QIN,Jie CHEN,Rong-jing HONG,Wei-wei WU. Visual salience detection algorithm for surface defects of friction sheets. Journal of ZheJiang University (Engineering Science), 2019, 53(10): 1883-1891.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2019.10.005    或    http://www.zjujournals.com/eng/CN/Y2019/V53/I10/1883

图 1  缺陷检测系统构成
图 2  摩擦片待检测区域提取
图 3  摩擦片表面特征分布
图 4  滤波器窗口尺寸与标准差对图像质量的影响
图 5  图像细节增强前、后的对比图
图 6  缺陷显著性三维空间分布图
图 7  原始图与显著图灰度分布对比
图 8  摩擦片缺陷二值图
图 9  缺陷区域人工标注与算法检测结果对比
样本类型 Nnum RY RN RW RO PAC/%
划痕 30 30 0 0 0 100
龟裂 30 30 0 0 0 100
油污 20 19 1 0 1 95
无缺陷 20 0 20 0 0 100
有缺陷
（纹理检测） 		80 80 0 0 0 100
无缺陷
(纹理检测) 		20 17 3 17 0 85
有缺陷（差分） 80 71 9 0 9 89
无缺陷（差分） 20 12 8 12 0 60
表 1  本算法与同类算法的定性评估结果对比
缺陷类型 P R F
划痕 0.890 1 0.784 2 0.833 8
龟裂 0.726 3 0.900 1 0.803 9
油污 0.953 1 0.630 5 0.758 9
划痕[15] 0.864 2 0.742 1 0.798 5
龟裂[15] 0.721 7 0.768 5 0.744 4
油污[15] 0.437 6 0.651 4 0.523 5
表 2  该算法与同类算法的定量分析评估结果对比
图 10  较浅油污缺陷的显著性分布图
方法 tsum/s PAC/%
本算法 27 99
算法A 33 91
算法B 94 83
表 3  该算法与同类算法的检测效率对比
1 吴成中, 王耀南, 贺振东, 等 基于机器视觉的注射液中不溶异物检测方法研究[J]. 仪器仪表学报, 2015, 36 (7): 1451- 1461
WU Cheng-zhong, WANG Yao-nan, HE Zhen-dong, et al Research on foreign insoluble particulate detection method for medicinal solution based on machine vision[J]. Chinese Journal of Scientific Instrument, 2015, 36 (7): 1451- 1461
doi: 10.3969/j.issn.0254-3087.2015.07.002
2 MARINO F, DISTANTE A, MAZZEO P L, et al A real-time visual inspection system for railway maintenance: automatic hexagonal-headed bolts detection[J]. IEEE Transactions on Systems and Cybernetics Part C Applications and Reviews, 2007, 37 (3): 418- 428
doi: 10.1109/TSMCC.2007.893278
3 LAUSCH D, MEHL T, PETTER K, et al Classification of crystal defects in multicrystalline silicon solar cells and wafer using spectrally and spatially resolved photoluminescence[J]. Journal of Applied Physics, 2016, 119 (5): 054501
doi: 10.1063/1.4940711
4 SUN Q M, MELNIKOV A, MANDELIS A Camera-based lock-in and heterodyne carrierographic photoluminescence imaging of crystalline silicon wafers[J]. International Journal of Thermo-physics, 2015, 36 (5/6): 1274- 1280
5 颜发根, 刘建群, 陈新, 等 机器视觉及其在制造业中的应用[J]. 机械制造, 2004, 42 (483): 28- 30
YAN Fa-gen, LIU Jian-qun, CHEN Xin, et al Machine vision and its application in manufacturing[J]. Machinery, 2004, 42 (483): 28- 30
6 刘长英, 蔡文静, 王天皓, 等 汽车连杆裂解槽视觉检测技术[J]. 吉林大学学报: 工学版, 2014, 44 (4): 1076- 1080
LIU Chang-ying, CAI Wen-jing, WANG Tian-hao, et al Vision inspection technology of fracture splitting notch of auto connecting rod[J]. Journal of Jilin University: Engineering and Technology Edition, 2014, 44 (4): 1076- 1080
7 郭会文, 吴新宇, 苏士娟, 等 移动相机下基于三维背景估计的运动目标检测[J]. 仪器仪表学报, 2014, 44 (4): 1076- 1080
GUO Hui-wen, WU Xin-yu, SU Shi-juan, et al 3D background estimation for moving object detection using a single moving camera[J]. Chinese Journal of Scientific Instrument, 2014, 44 (4): 1076- 1080
8 GHOSAL S, BLYSTONE D, SINGH A K, et al An explainable deep machine vision framework for plant stress phenotyping[J]. Proceedings of the National Academy of Sciences of the United States of America, 2018, 115 (18): 4613- 4618
doi: 10.1073/pnas.1716999115
9 URBANEK J, BARSZCZ T, UHL T, et al Leak detection in gas pipelines using wavelet-based filtering[J]. Chinese Journal of Scientific Instrument, 2012, 11 (4): 405- 412
10 杨东林, 于正林 轴承钢球表面缺陷的快速检测方法[J]. 兵工学报, 2009, 30 (6): 797- 802
YANG Dong-lin, YU Zheng-lin Rapid detection method of surface defects of steel ball for bearing[J]. Acta Armamentarii, 2009, 30 (6): 797- 802
doi: 10.3321/j.issn:1000-1093.2009.06.024
11 李春颖 机器视觉在钢球表面缺陷检测中的应用[J]. 计算机与现代化, 2005, (10): 63- 65
LI Chun-ying Application of machine vision in steel ball surface fault inspection[J]. Computer and Modernization, 2005, (10): 63- 65
doi: 10.3969/j.issn.1006-2475.2005.10.020
12 JIANG L, SUN K, ZHAO F, et al. Automatic detection system of shaft part surface defect based on machine vision [C] // Automated Visual Inspection and Machine Vision. Tokyo, Japan: International Society for Optics and Photonics, 2015.
13 张静, 叶玉堂, 谢煜, 等 金属圆柱工件缺陷的光电检测[J]. 光学精密工程, 2014, 22 (7): 1871- 1876
ZHANG Jing, YE Yu-tang, XIE Yu, et al Optoelectronic inspection of detect for metal cylindrical workpieces[J]. Optics and Precision Engineering, 2014, 22 (7): 1871- 1876
14 苑玮琦, 李绍丽, 李德健 基于纹理主、旁瓣特征的雪糕棒裂缝缺陷检测[J]. 仪器仪表学报, 2017, (11): 2779- 2787
YUAN Wei-qi, LI Shao-li, LI De-jian Detection of ice cream stick crack defects based on texture mainlobe and sidelobe features[J]. Chinese Journal of Scientific Instrument, 2017, (11): 2779- 2787
doi: 10.3969/j.issn.0254-3087.2017.11.020
15 SCHOLZ-REITER B, WEIMER D, THAMER H Automated surface inspection of cold-formed micro-parts[J]. CIRP Annals - Manufacturing Technology, 2012, 61 (1): 531- 534
doi: 10.1016/j.cirp.2012.03.131
16 HE X J, YI Z D, LIU J, et al Defect detecting technology based on machine vision of industrial parts[J]. Applied Mechanics and Materials, 2014, 641-642: 1275- 1279
doi: 10.4028/www.scientific.net/AMM.641-642.1275
17 HUANG B, MA S, WANG P, et al Research and implementation of machine vision technologies for empty bottle inspection systems[J]. Engineering Science and Technology: An International Journal, 2018, 21 (1): 2049- 2052
18 YANG Y, ZHA Z J, GAO M, et al A robust vision inspection system for detecting surface defects of film capacitors[J]. Signal Processing, 2016, 124 (C): 54- 62
19 KIM Y, KOH Y J, LEE C, et al. Dark image enhancement based onpairwise target contrast and multi-scale detail boosting [C] // IEEE International Conference on Image Processing. Kuala Lumpur, Malaysia: IEEE, 2015: 1404-1408.
20 王义文, 屈冠彤, 刘献礼, 等 钢球表面缺陷的图像差分检测算法[J]. 计算机辅助设计与图形学学报, 2016, 28 (10): 1699- 1704
WANG Yi-wen, QU Guan-tong, LIU Xian-li, et al Image subtraction detection algorithm for surface defect of steel ball[J]. Journal of Computer-Aided Design and Computer Graphics, 2016, 28 (10): 1699- 1704
doi: 10.3969/j.issn.1003-9775.2016.10.011
21 单忠德, 张飞, 任永新, 等 基于机器视觉铸件布氏硬度在线检测技术研究[J]. 机械工程学报, 2017, 53 (1): 157- 164
SHAN Zhong-de, ZHANG Fei, REN Yong-xin, et al On line detection technology of the hardness of cast iron parts based on machine vision[J]. Journal of Mechanical Engineering, 2017, 53 (1): 157- 164
22 磨少清. 边缘检测及其评价方法的研究[D]. 天津: 天津大学, 2011.
MO Shao-qing. Research on edge detection and its evaluation [D]. Tianjin: Tianjin University, 2011.
23 钱晓亮, 张鹤庆, 张焕龙, 等 基于视觉显著性的太阳能电池片表面缺陷检测[J]. 仪器仪表学报, 2017, 38 (7): 1570- 1578
QIAN Xiao-liang, ZHANG He-qing, ZHANG Huan-long, et al Solar cell surface defect detection based on visual saliency[J]. Chinese Journal of Scientific Instrument, 2017, 38 (7): 1570- 1578
doi: 10.3969/j.issn.0254-3087.2017.07.002
24 贺付亮, 郭永彩, 高潮, 等 基于视觉显著性和脉冲耦合神经网络的成熟桑葚图像分割[J]. 农业工程学报, 2017, 33 (6): 148- 155
HE Fu-liang, GUO Yong-cai, GAO Chao, et al Image segmentation of ripe mulberries based on visual saliency and pulse coupled neural network[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33 (6): 148- 155
doi: 10.11975/j.issn.1002-6819.2017.06.019
25 TERADA H, IMAI H, OAKI Y Visualization and quantitative detection of friction force by self-organized organic layered composites[J]. Advanced Materials, 2018, 1801121
26 ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection [C] // IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA: IEEE, 2009: 1597-1604.
27 ANWAR S A, ABDULLAH M Z Micro-crack detection of multicrystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique[J]. Eurasip Journal on Image and Video Processing, 2014, 2014 (1): 1- 17
doi: 10.1186/1687-5281-2014-1
28 AGROUI K, PELLEGRINO M, GIOVANNI F Analysis techniques for photovoltaic modules based on amorphous solar cells[J]. Arabian Journal for Science and Engineering, 2017, 42 (1): 1- 7
doi: 10.1007/s13369-016-2269-1
29 黎明, 马聪, 杨小芹 机械加工零件表面纹理缺陷检测[J]. 中国图象图形学报, 2004, 9 (3): 318- 322
LI Ming, MA Cong, YANG Xiao-qin Detection of texture defects for machined surface[J]. Journal of Image and Graphics, 2004, 9 (3): 318- 322
doi: 10.3969/j.issn.1006-8961.2004.03.011
30 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
doi: 10.3969/j.issn.0254-3087.2016.03.022
[1] 陈杨波,伊国栋,张树有. 基于点云特征对比的曲面翘曲变形检测方法[J]. 浙江大学学报(工学版), 2021, 55(1): 81-88.
[2] 王昶,张永生,王旭,于英. 基于深度学习的遥感影像变化检测方法[J]. 浙江大学学报(工学版), 2020, 54(11): 2138-2148.
[3] 叶刚,李毅波,马逐曦,成杰. 基于ViBe的端到端铝带表面缺陷检测识别方法[J]. 浙江大学学报(工学版), 2020, 54(10): 1906-1914.
[4] 付凤杰,龚越,王殿海,马东方. 基于高清智能卡口路段行程时间的数据质量分析[J]. 浙江大学学报(工学版), 2016, 50(9): 1761-1767.
[5] 夏芬, 张龙海, 韩德志, 毕坤. 自适应书法字图像匹配和检索章[J]. 浙江大学学报(工学版), 2016, 50(4): 766-776.
[6] 周强, 赵巨峰, 冯华君, 徐之海, 李奇, 陈跃庭. 非下采样剪切波的红外偏振图像融合[J]. 浙江大学学报(工学版), 2014, 48(8): 1508-1516.
[7] 刘中, 陈伟海, 吴星明, 邹宇华, 王建华. 基于双目视觉的显著性区域检测[J]. J4, 2014, 48(2): 354-359.
[8] 彭海,赵巨峰,冯华君,徐之海,李奇,陈跃庭. 基于区域显著性的双波段图像融合方法[J]. J4, 2012, 46(11): 2109-2115.