摘要
轮廓线的自动匹配问题是计算机视觉、自动化和模式识别中的一个重要问题。传统的匹配方法中在特征描述部分容易出现误差,并且缺乏全局性。为此提出了基于连续函数曲率概念的周期性离散曲率函数,解决普通轮廓线勾画外形中的图形匹配问题。周期性离散曲率函数具有和原有图形相似的位移、旋转和缩放特性,具有很强的全局性。该方法具有直观和速度快的特点,并且实用可靠,可广泛地应用于类似系统。
he automatic matching method of two curves is an important issue in the fields of computer vision, automation and pattern recognition, which can be widely used in the object dynamic track, content-based image retrieval and the automatic assembly of robot. In order to solve the easy serious error and lacking global description of the traditional method, the periodic curvature function was brought forward. The function was raised based on the concept of continues curvature to match the object contour. The curvature of the continuous function not only has the unchanged character among the circumvolving, translation and zooming, but also has the global character of the curves. The feasibility of the method was verified by the experiment further. The method has the advantages of easy to realize and quick speed, and can be easily expand to the other similar systems.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2007年第17期4045-4048,共4页
Journal of System Simulation
基金
863计划项目(9934-10)
国家自然科学基金项目(60072044)
国家文物局重点项目(20040311)
关键词
周期性曲率函数
轮廓线匹配
物体复原
计算机视觉
periodic curvature function
shape matching
object reconstruction
computer vision
