基于机器视觉的软磨片定位测量系统  

Positioning and Measuring System of Soft Grinding Disc Based on Machine Vision

作　　者：赵宇航 胡伟[1] ZHAO Yuhang;HU Wei(School of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo 454000)

机构地区：[1]河南理工大学电气工程与自动化学院,焦作454000

出　　处：《计算机与数字工程》2024年第3期931-935,共5页Computer & Digital Engineering

摘　　要：针对软磨片外轮廓定位测量过程中,边缘较难提取,轮廓圆心与半径拟合精度较低的问题,提出通过中值滤波和灰度变换改善图像质量,使用灰度投影与灰度方差统计进行边缘筛选,利用圆心约束最小二乘法拟合外轮廓,通过高斯—牛顿法得到轮廓圆心坐标与半径,完成高精度定位和测量。通过实验对比,系统定位与测量误差保持在0.2mm以内,检测速度达到每片0.8s,在生产应用中具有实用性和高效性,提高了软磨片的检测效率和生产自动化程度。In the process of positioning and measuring the outer contour of the soft polishing plate,the edges are difficult to ex-tract,and the contour center and radius are low in accuracy.The median filter and grayscale transformation are used to improve the image quality,and the grayscale projection and grayscale variance statistics are used.Edge screening,using the center-constrained least squares method to fit the outer contour,obtain the contour center coordinates and radius through the Gauss-Newton method,and complete high-precision positioning and measurement.Through experimental comparison,the positioning and measurement er-ror of the system is kept within 0.2mm,and the detection speed reaches 0.8s per sheet.It is practical and efficient in production ap-plications,and improves the detection efficiency and production automation of soft abrasive discs.

关 键 词：灰度投影 方差 圆心约束 最小二乘法 高斯牛顿迭代法 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]