计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (3): 237-241.DOI: 10.3778/j.issn.1002-8331.1505-0098

• 工程与应用 • 上一篇    下一篇

基于Halcon的阀芯尺寸亚像素级测量

唐  松,杨其华,刘刚海   

  1. 中国计量学院 质量与安全工程学院,杭州 310018
  • 出版日期:2017-02-01 发布日期:2017-05-11

Valve core size sub-pixel measurement based on Halcon

TANG Song, YANG Qihua, LIU Ganghai   

  1. College of Quality and Safety Engineering, China Jiliang University, Hangzhou 310018, China
  • Online:2017-02-01 Published:2017-05-11

摘要: 针对传统人工在检测阀芯时的低效和低精度问题,采用性能优越的机器视觉软件Halcon为平台,利用Canny算子边缘检测和双线性插值方法得到阀芯图像亚像素级边缘,结合最小二乘算法进行边缘拟合,实现对阀芯快速、稳定和较高精度的尺寸测量。实验结果表明:该检测方式可以达到亚像素级的尺寸测量,测量精度高于2‰,满足企业对测量精度要求,且测量过程比较稳定和快速。

关键词: Halcon, 亚像素, 最小二乘, 尺寸测量

Abstract: It is inefficient and imprecise to measure dimension of valve core by manual measurement. With the superior performance of machine vision software Halcon-platform, using edge detection of Canny operator to get the valve core image subpixel edge, combining with the least square method to fit the edge, to realize the dimensional measurement quickly, effectively and high-precision for valve core. Experimental results show that in certain situations in this way measuring accuracy can reach up to 2 per thousand to meet accuracy requirements, and the measurement process is stable and fast.

Key words: Halcon, sub-pixel, least square, dimensional measurement