反求工程中ICT图像对称轮廓自动识别  

Auto-identification of symmetric profiles on ICT image in reverse engineering

作　　者：雷华堂[1] 熊鹰[1] 田亚铃[1] 何朝明[1] 李柏林[1] 

机构地区：[1]西南交通大学机械工程学院,四川成都610031

出　　处：《机械设计》2011年第3期19-22,共4页Journal of Machine Design

基　　金：四川省科技支撑资助项目(2009GZ0007)

摘　　要：针对机械工业产品轮廓中对称约束特征,该文提出了基于特征匹配的二维图像对称轮廓自动识别方法。基于轮廓点云数据分割和型值点方法提取特征点,研究轴对称和旋转对称图像特征点的不同分布规律,判别对称类型;采用转动惯量法和周期法求取对称轮廓特征描述参数作为轮廓整体约束优化求解参数;实例表明:文中方法能够有效地自动识别对称轮廓及其类型,提取出对称约束特征。By considering the symmetry restriction characteristics in machinery industrial product profiles,a method of two-dimensional symmetric contour auto-identification based on feature matching is presented in this paper.Firstly,the feature points are extracted based on profile cloud point data partition and by using offset method,the different distribution rules of axial symmetric and rotational symmetric images for judging the type of symmetry was studied.The symmetric profile feature description parameter was calculated by adopting rotational inertia method and periodic method,which is regarded as the parameters for solving the profile overall constraint optimization.Examples show that method in this paper can effectively identify the symmetric profiles and their types,and extract the symmetric constraint features.

关 键 词：反求工程 ICT图像 特征匹配 对称轮廓 自动识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]