异形冲压件轮廓视觉检测系统设计

陈海永; 李泽楠; 孙鹤旭; 欧洋; 王亚男

doi:10.3788/OPE.20162413.0229

您当前的位置：

首页 >

文章列表页 >

异形冲压件轮廓视觉检测系统设计

更新时间：2020-08-13

- 异形冲压件轮廓视觉检测系统设计
- Visual detection system design for profile of special-shaped stamping parts
- 光学精密工程 2016年24卷第10s期页码：229-236
- 作者机构：
  
  1. 河北科技大学,河北石家庄,050000
  2. 河北工业大学控制科学与工程学院天津,中国,300130
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目（No.61203275）();河北省自然科学基金资助项目（No.F2014202071）();天津市特派员科技计划资助项目（No.15JCTP
- DOI：10.3788/OPE.20162413.0229
  中图分类号： TP274;TP391.41
- 收稿日期：2016-05-28，
  
  修回日期：2016-06-12，
  
  纸质出版日期：2016-11-14
- 稿件说明：
移动端阅览
陈海永, 李泽楠, 孙鹤旭等. 异形冲压件轮廓视觉检测系统设计[J]. 光学精密工程, 2016,24(10s): 229-236

CHEN Hai-yong, LI Ze-nan, SUN He-xu etc. Visual detection system design for profile of special-shaped stamping parts[J]. Editorial Office of Optics and Precision Engineering, 2016,24(10s): 229-236
陈海永, 李泽楠, 孙鹤旭等. 异形冲压件轮廓视觉检测系统设计[J]. 光学精密工程, 2016,24(10s): 229-236 DOI： 10.3788/OPE.20162413.0229.

CHEN Hai-yong, LI Ze-nan, SUN He-xu etc. Visual detection system design for profile of special-shaped stamping parts[J]. Editorial Office of Optics and Precision Engineering, 2016,24(10s): 229-236 DOI： 10.3788/OPE.20162413.0229.

摘要

针对异形冲压件轮廓缺陷的检测难题，设计了一个零件缺陷视觉检测系统。介绍了该系统的硬件组成和工作原理。根据冲压件的不规则形状采用水平集算法结合应用模型Chan-Vese来提取零件轮廓。设置能量函数，并通过优化能量函数使轮廓曲线逐渐逼近采集图像中冲压件的轮廓边界，有效抑制了噪声干扰提高提取精度。最后，采用hu不变矩轮廓匹配算法和面积匹配算法，通过多样本hu矩参数和面积采样设置阈值实现了缺陷零件的准确识别。该缺陷识别算法具有旋转、平移不变性和较好的鲁棒性。实验结果表明，此系统可检测出占整个异形零件0.5%以上的缺陷，缺陷检测精度高，能够满足异形零件轮廓稳定可靠、高精度等检测需求。

Abstract

In order to realize the profile defect detection for the special-shaped stamping parts

a visual detection system was designed. The hardware components and working principle of the system were introduced. In this system

the profile of parts was extracted by using the level set method combined with Chan-Vese model based on its irregular shapes. In the Chan-Vese Model

energy function was set up and optimized in order to enable the profile curve approaching the profile boundary of the stamping parts in the collected image

thus effectively controlling the noise interference improving the extraction accuracy. Finally

the defect of the stamping parts was indentified according to the multi-sample hu moment parameter and areal sampling threshold which generated from the hu invariant-moment profile matching and area matching methods respectively. The defect identification method was characterized by rotation

translation invariance and good robustness. The results indicate that the system can detect defects over 0.5% of the overall part with high detection precision

and is suitable for profile defect detection demand for high stability and security as well as high precision.

关键词

Keywords

references

WEN Z, CAO J, LIU X, et al.. Fabric defects detection using adaptive wavelets[J]. International Journal of Clothing Science and Technology, 2014, 26(3):202-211.

陈文志, 张凤燕, 张然, 等. 基于电致发光成像的太阳能电池缺陷检测[J]. 发光学报, 2013, 34(8):1028-1034. CHEN W ZH, ZHANG F Y, ZHANG R. Detection based on electroluminescence imaging solar[J],Chinese Journal of Luminescence,2013, 34(8):1028-1034.(in Chinese)

朱光,朱学芳,张华坤. 复杂背景下TFT-LCD表面缺陷检测系统的设计[J]. 电子测量与仪器学报,2011, 25(12):1054-1059. ZHU G, ZHU X F, ZHANG H K. Design TFT-LCD surface defect detection system in complex background[J].Journal of Electronic Measurement and Instrument,2011, 25(12):1054-1059. (in Chinese)

TING J, HOPPER C. A general approach to defect detection in textured materials using a wavelet domain model and level sets[J].SPIE, 2005, 6001(3):309-310.

MARTÍNEZ S S, ORTEGA J G, GARCÍA J G, et al.. A machine vision system for defect characterization on transparent parts with non-plane surfaces[J]. Machine Vision and Applications, 2012, 23(1):1-13.

廖建军. 基于计算机视觉的石材轮廓提取及缺陷检测[D]. 沈阳:沈阳建筑大学, 2013. LIAO J J. Stone Contour Extraction and Defect Detection Based on Computer Vision[D].Shenyang:Shenyang Jianzhu University,2013.(in Chinese)

郭庆华,刘海霞,宋丽梅,等. 显微镜镜头的圆弧表面缺陷检测[J]. 光学精密工程, 23(10z):790-797. GUO Q H,LIU H X,SONG L M, et al.. Detection of arc surface defects in microscope lens detection system[J]. Opt. Precision Eng., 23(10z):790-797. (in Chinese)

刘慧英,王小波. 基于OpenCV的车辆轮廓检测[J]. 科学技术与工程, 2010, 10(12):2987-2991. LIU H Y, WANG X B. The vehicle's contour detection based on OpenCV[J].Science Technology and Engineering, 2010, 10(12):2987-2991. (in Chinese)

龚永义,罗笑南,黄辉,等. 基于单水平集的多目标轮廓提取[J]. 计算机学报, 2007, 30(1):120-128. GONG Y Y, LUO X N, HUANG H, et al.. Multi-objects extracted based on single level set[J].Chinese Journal of Computers,2007,30(1):120:128. (in Chinese)

CHEN Y T, TSENG D C. Medical image segmentation based on the Bayesian level set method[J].Medical Imaging and Informatics, 2007, 4987:25-34.

刘建磊,隋青美,朱文兴. 结合概率密度函数和主动轮廓模型的磁共振图像分割[J]. 光学精密工程,2014, 22(12):3435-3443. LIU J L, SUI Q M, ZHU W X. MR image segmentation based on probability density function and active contour model[J].Opt. Precision Eng., 2014, 22(12):3435-3443. (in Chinese)

ABDELSAMEA M M, GNECCO G, GABER M M. A SOM-based Chan-Vese model for unsupervised image segmentation[J]. Soft Computing, 2015:1-21.

DUAN Y, CHANG H, TAI X C. Convergent non-overlapping domain decomposition methods for variational image segmentation[J]. Journal of Scientific Computing, 2016:1-24.

汤继生. 图像不变矩的研究及应用[D].泉州:华侨大学, 2012. TANG J SH.Research and Application of Image Moment Invariants[D].Quanzhou:Huaqiao University,2012.(in Chinese)

王晶,何冰. Hu新增不变矩在零水印中的应用[J]. 计算机与数字工程, 2011, 39(1):125-128. WANG J,HE B. Application of new Hu invariant moments in zero digital watermarking[J].Computer and Digital Engineering,2011,39(1):125-128. (in Chinese)

浏览量

441

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

集成改进半监督分割方法的航空发动机短舱声衬孔检测系统

融合统计范数度量的局部区域图像分割

三耦合柔性梁振动的视觉检测与H_∞控制

SOI压阻传感器的阳极键合结合面检测

CCD视觉检测系统的整体标定