节点文献
基于视觉图像的机加工零部件亚像素边缘定位
SUBPIXEL EDGE LOCATION OF MACHINE PARTS BASED ON THE VISION IMAGES
【摘要】 首先介绍了LOG算子的快速定位方法以及二维理想图像边缘模型的空间矩亚像素细分算法的基本原理;在此基础上给出了符合实际图像采样的三级灰度图像边缘模型的空间矩算子,并推导了该算子的原理误差公式。最后利用试验对空间矩算子亚像素定位方法的有效性、精度进行了研究,并给出了该方法的亚像素定位与实测尺寸的对比结果。结果表明该方法比传统的边缘检测算子的边缘定位精度有较大提高。
【Abstract】 The Laplacian of Gaussian operator rapid localiza-tion and the principle of subpixel edge operator based ontwo-dimensional spatial moment are presented at first. A threegray levels edge model based on spatial moment is given whichis closed to practical image sampling. The error formula is de-duced. Finally, the experiment is carried out. The validity andprecision of subpixel edge spatial moment operator is studiedand the subpixel edge detection results are compared to practi-cal size. The results indicate that the subpixel edge detectionoperator based on spatial moment is much better than tradi-tional edge detection operator.
【Key words】 Laplacian of gaussian operator; Spatial moment operator; Subpixel edge localization;
- 【文献出处】 机械工程学报 ,Chinese Journal of Mechanical Engineering , 编辑部邮箱 ,2004年06期
- 【分类号】TP391.72
- 【被引频次】43
- 【下载频次】469