| 基于空间矩的视觉图像基元特征提取方法研究 |
| |
| 引用本文： | 崔彦平. 基于空间矩的视觉图像基元特征提取方法研究[J]. 光电子．激光, 2010, 0(10): 1565-1569 |
| |
| 作者姓名： | 崔彦平 |
| |
| 作者单位： | 河北科技大学机械电子工程学院;天津大学精密测试技术及仪器国家重点实验室; |
| |
| 基金项目： | 国家自然科学基金资助项目(51075119,11002046); 教育部博士点专项科研基金资助项目(20030056017); 河北省自然科学基金资助项目(E2010000868); 河北省科学技术研究与发展计划资助项目(10212111D) |
| |
| 摘 要： | 建立了三级灰度图像边缘模型的空间矩算子。首先利用LOG(Laplacian of Gaussian)算子定位速度快的特点,确定图像像素级边缘;然后在包含边缘点的邻域内利用空间矩进行边缘的亚像素定位,由Hough变换提取直线和椭圆边缘像素点;最后采用基于最小二乘原理的直线拟合边缘提取方法,得到亚像素级被检测直线和椭圆。对空间矩算子亚像素定位算法与像面直线和椭圆亚像素提取算法的有效性和精度进行了实验研究,实验结果表明,在测量速度相当的情况下,本文提出的算法具有较高的精度和稳定性。
|
| 关 键 词： | 边缘检测 直线提取 椭圆提取 空间矩 Hough变换 最小二乘算法 |
Extraction of primitive feature of vision images based on spatial moment |
| |
| CUI Yan-ping. Extraction of primitive feature of vision images based on spatial moment[J]. Journal of Optoelectronics·laser, 2010, 0(10): 1565-1569 |
| |
| Authors: | CUI Yan-ping |
| |
| Affiliation: | CUI Yan-ping1,2,GE Xing-wei1 (1.School of Mechanical and Electronic Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,China,2.State Key Laboratory of Precision Measuring Technology and Instruments,Tianjin University,Tianjin 300072,China) |
| |
| Abstract: | A spatial moment operator of image edge model for the three-gray-level image is proposed.Firstly the Laplacian of Gaussian(LOG) operator is used to locate the edge at the level of pixel quickly,and then the spatial moment is used for subpixel location of the edge in the domain containing edge points.The beeline and ellipse edge pixel points are extracted by the Hough transform.The least square fitting edge extraction is adopted to obtain the subpixel beeline and ellipse.The validity and precision of spatial... |
| |
| Keywords: | edge detection beeline extraction ellipse extraction spatial moment Hough transform least square method |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
