Hough变换在零件形位误差检测中的应用  

Application of Hough Transformation in Detection of Parts Shape-position Error

作　　者：冯晓锋[1] 余金伟[1] 

机构地区：[1]湖南铁路科技职业技术学院,株洲412000

出　　处：《机械科学与技术》2011年第6期957-959,967,共4页Mechanical Science and Technology for Aerospace Engineering

摘　　要：为了满足精密零件高精度、高效率的加工检测要求,开展了机械零件形位误差在线检测研究,提出了一种新的检测方法。在得到零件的视觉边缘图像信息后,利用Hough变换将零件原始图像空间的给定曲线通过曲线表达形式变为参数空间一个点的原理,并结合形位误差检测方法,检测零件边缘图像上下棱边的边缘点,对检测到的边缘点应用最小二乘法进行拟合得到较精确的直线方程。通过实验将检测结果与人工检测结果比较,两者相差不大,表明该方法的有效性。In order to meet the requirement of high-precision and high efficiency in parts detection, we present an on-line detection method for parts shape-position error. As the Hough transformation can render the curve of original coordinate to a point of parameter coordinate, so after obtaining the image edge message of parts, the Hough transformation combined with the method of shape-position error detection can detect the edge points of parts image. Then, the points is fitted by using least-squares procedure and the accurate equation of the line is obtained. The experimental results are in good agreement with the artificial detection the results. It shows that this method is effective.

关 键 词：HOUGH变换 形位误差 在线检测 

分 类 号：TH161[机械工程—机械制造及自动化]