首页 > 论文 > 光学学报 > 38卷 > 8期(pp:815027--1)

基于形态学特征的机械零件表面划痕检测

Surface Scratch Detection of Mechanical Parts Based on Morphological Features

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

采用高、低角度光源组合打光方式提取感兴趣区域,构建划痕形态学的中值滤波核以获取准确的背景图像,再经背景差分后提取划痕缺陷。采用基于方向梯度的改进区域生长算法实现了同一划痕的有效连通,降低了划痕缺陷的漏检率。通过对面积、长宽比等主要特征参数的置信度分析,提出了一种多特征加权融合的划痕判定方法。结果表明,利用该方法进行划痕检测的正确率达95.7%,算法处理时间少于1.21 s,达到了工程应用的精度和效率要求。

Abstract

The region of interest (ROI) is first extracted under the combination lighting mode of high and low angle light sources and then the median filter kernel of scratch morphology is constructed to obtain the accurate background images from ROI. The scratches are extracted after the background difference. An improved region growing algorithm based on directional gradient is adopted to achieve an effective connectivity for the same scratch, which reduces the miss rate of scratch detection. By analyzing the confidence of main scratch detection parameters such as area, length-width ratio and so on, a scratch detection method based on weighted fusion of multi-features is proposed. The results show that, for this method, the accuracy of scratch detection is 95.7%, and the processing time is less than 1.21 s, which meets the accuracy and efficiency requirements for the engineering application.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/aos201838.0815027

所属栏目:“机器视觉检测与应用”专题

基金项目:国家自然科学基金(51575277)

收稿日期:2018-04-02

修改稿日期:2018-06-07

网络出版日期:2018-06-19

作者单位    点击查看

李克斌:南京航空航天大学机电学院, 江苏 南京 210016南京航空航天大学无锡研究院, 江苏 无锡 214187
余厚云:南京航空航天大学机电学院, 江苏 南京 210016南京航空航天大学无锡研究院, 江苏 无锡 214187
周申江:南京航空航天大学机电学院, 江苏 南京 210016

联系人作者:余厚云(meehyyu@nuaa.edu.cn); 李克斌(likebin@nuaa.edu.cn);

【1】Hu K, Zhang S, Xu J. Scratch detection technology for product surface based on improved contourlet transform[C]∥IOP. Materials Science and Engineering Conference Series. London: IOP Publishing Ltd., 2017: 012082.

【2】Luo J, Lin S Z, Ni J Y, et al. Morphology battery scratch detection combining GLCM and CT[J]. Journal of Computational Information Systems, 2011, 7(12): 4343-4350.

【3】Bhuvaneswari S, Subashini T S. Automatic scratch detection and in painting[C]. IEEE 9th International Conference on Intelligent Systems and Control, 2015: 7282256.

【4】Wang J G, Gao D Y. Improved morphological TOP-HAT filter optimized with genetic algorithm[C]. International Congress on Image and Signal Processing, 2009: 10955475.

【5】Li C, Yang Y Y, Xiong H L, et al. Dual-threshold algorithm study of weak-scratch extraction based on the filter and difference[J]. High Power Laser and Particle Beams, 2015, 27(7): 103-110.
李晨, 杨甬英, 熊浩亮. 等. 基于滤波差分的双阈值弱划痕提取算法[J]. 强激光与粒子束, 2015, 27(7): 103-110.

【6】Wang F. Research of image processing algorithm based on region of interest[J]. Advanced Materials Research, 2013, 798/799: 814-817.

【7】Mu W Y, Jin J, Feng H Q. Adaptive window multistage median filter for image salt-and-pepper denoising[C].IEEE International Instrumentation and Measurement Technology Conference, 2013: 1535-1539.

【8】Zhang L J, Yang D B, Xu J W, et al. Approach to extracting gear fault feature based on mathematical morphological filtering[J]. Chinese Journal of Mechanical Engineering, 2007, 43(2): 71-75.

【9】De Natale F G B, Boato G. Detecting morphological filtering of binary images[J]. IEEE Transactions on Information Forensics and Security, 2017, 12(5): 1207-1217.

引用该论文

Li Kebin,Yu Houyun,Zhou Shenjiang. Surface Scratch Detection of Mechanical Parts Based on Morphological Features[J]. Acta Optica Sinica, 2018, 38(8): 0815027

李克斌,余厚云,周申江. 基于形态学特征的机械零件表面划痕检测[J]. 光学学报, 2018, 38(8): 0815027

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF