【2017年整理】零件尺寸图像检测数据处理与高精度检测方法.pdfVIP

计 算 机 系 统 应 用 2011 年 第 20 卷 第 9 期 零件尺寸图像检测数据处理与高精度检测方法① 1 1 1 1 1 2 2 黄品松 ，徐 杜 ，蒋永平 ，郭 斌 ，陈济棠 ，孔海鹏 ，梁 柱 1(广东工业大学 信息工程学院，广州 510006) 2(怀集登云汽配股份有限公司，怀集 526400) 摘 要：针对机器视觉在轴类零件尺寸检测中的应用，提出了一种利用工业中常用的标准件同时完成视觉检测 系统的图像畸变校正与系统标定的方法，有效的提高了检测精度，简化了传统系统标定的繁琐过程。该方法通 过分析图像检测中误差形成的主要来源，建立了误差方程的正规方程式，在求解正规式系数的同时完成对检测 系统的校正与标定。不但操作简单，且具有较高的检测精度。经实验证明，在检测分辨率为 3450DPI 的情况下， 检测精度可达到 4μm ，完全适用于轴类零件的高精度检测。 关键词：视觉检测；尺寸检测；畸变校正；标定；标准件 Methods of Data Processing and High Accurate Detection for Image Detection of Part Sizes 1 1 1 1 1 2 2 HUANG Pin-Song , XU Du , JIANG Yong-Ping , GUO Bin , CHEN Ji-Tang , KONG Hai-Peng , LIANG Zhu 1(Faculty of Information Engineering, Guangdong University of Technology, Guangzhou, 510006, China) 2(Huaiji Dengyun Auto Parts Co. Ltd, Guangzhou 56400, China) Abstract: For the use of Machine Vision in shaft size detection, this paper propose a method which completes the image distortion correction and system calibration by using commonly used industry standard parts. This method effectively improves the detection accuracy, simplifies the tedious process of calibration of conventional systems. By analyzing the main causes of error in image detection, the formal equation from error equation is established. Image distortion is corrected and calibrated at the same time. The coefficient of normal-type is calculated. This method is not only simple, but also effective to improve the accuracy of the image detection. The experiment proves that detection accuracy can reach 4μm at the resolution of 3450DPI, completely applicable to high-precision detection of shaft. Key words: machine visual inspection; size detection; distortion correction; calibration; standard part 图像成像时往往会由于多种原因产生难以避免的 应关系，对畸变图像进行变换校正，