基于机器视觉的圆形垫圈尺寸测量系统设计  

Design of Measuring System for Circular Gasket Size Based on Machine Vision

作　　者：张炳星 高军伟 王建冲 刘佳浩 Zhang Bingxing;Gao Junwei;Wang Jianchong;Liu Jiahao(School of Automation,Qingdao University,Qingdao,Shandong 266071,China)

机构地区：[1]青岛大学自动化学院,山东省青岛市266071 [2]山东省工业控制技术重点实验室

出　　处：《工具技术》2023年第7期141-145,共5页Tool Engineering

基　　金：山东省自然科学基金(ZR2019MF063);山东省重点研发计划(2017GGX101115)。

摘　　要：针对传统工业检测中人工测量工件尺寸存在效率低、精度差等问题,设计了基于机器视觉的圆形垫圈尺寸测量系统。在MATLAB软件中对CCD相机进行尺寸标定,对采集的图像进行灰度处理,使用改进后的Canny自适应迭代阈值算法对图像进行边缘检测,对边缘坐标进行双线性插值并提取亚像素边缘坐标,根据最小二乘法对亚像素边缘坐标进行圆拟合,得到工件内径与外径尺寸。实验结果表明,本系统的测量精度可达到±0.02mm,可应用于圆形工件的视觉测量。In order to solve the problems of low efficiency and poor precision in traditional industrial inspection,a measuring system of circular gasket size based on machine vision is designed.The size of the CCD camera in MATLAB is calibrated,and the collected image gray is processed,by the improved Canny adaptive iteration threshold algorithm the image edge detection is processed,edge coordinates are interpolated bilinear and the subpixel edge coordinates are extracted.The inner diameter and outer diameter of the workpiece are obtained by circular fitting of subpixel edge coordinates using the least square method.Experimental results show that the measurement accuracy of the system can reach±0.02mm,which can be applied to the visual measurement of circular workpiece.

关 键 词：机器视觉 尺寸测量 边缘检测 亚像素边缘 最小二乘法 

分 类 号：TG806[金属学及工艺—公差测量技术] TH124[机械工程—机械设计及理论] TG391