用HOUGH变换改进的曲率法识别平面轮廓图元-图学学报.PDFVIP

2011 年 工 程 图 学 学 报 2011 第2 期 JOURNAL OF ENGINEERING GRAPHICS No.2 用HOUGH 变换改进的曲率法 识别平面轮廓图元 1, 2 2 伍济钢 ， 宾鸿赞 （1. 湖南科技大学机械设备健康维护湖南省重点实验室，湖南 湘潭 411201 ； 2. 华中科技大学机械科学与工程学院，湖北 武汉 430074 ） 摘 要：针对检测精度与检测速度两大指标，提出了用HOUGH 变换改进的曲率法 平面轮廓图元识别方法。开发了基于邻域值的轮廓点分类算法，采用曲率阈值法筛选轮廓点、 投影高度法判别图元属性及分类轮廓点，构建了基于 HOUGH 变换的直线图元、圆弧图元 分割与融合算法。对提出的方法分别进行了特征点检测精度与检测速度对比实验和特征点检 测能力测试实验。实验结果表明，提出的方法图元识别准确、检测速度快、通用性好。 关 键 词：计算机应用；图元识别；HOUGH 变换；平面轮廓 中图分类号：TP 391 文献标识码：A 文 章 编 号：1003-0158(2011)02-0102-05 Planar Contour Primitive Recognition Based on Curvature Improved by HOUGH Transform WU Ji-gang1, 2, BIN Hong-zan2 ( 1. Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment, Hunan University of Science and Technology, Xiangtan Hunan 411201 China; 2. School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan Hubei 430074, China ) Abstract: According to the inspection accuracy and inspection speed, a planar contour primitive recognition method based on curvature improved by HOUGH transform is proposed. A contour point classification algorithm based on neighborhood values is developed, and a curvature threshold method is selected to filter the contour points, and a projection height method is selected to distinguish the property of the primitive and classify the contour points, and the straight line primitive and arc primitive segmentation and m