基于DFD参数变形模型的平面足迹轮廓提取  

Footprint Boundary Extraction Based on DFD Parametrically Deformable Models

作　　者：童莉[1] 平西建[1] 马金全[1] 李磊[1] 

机构地区：[1]信息工程大学信息工程学院,郑州450002

出　　处：《计算机辅助设计与图形学学报》2007年第4期521-527,共7页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(60272004)

摘　　要：针对重压区域轮廓处于强边缘附近具有特性形状属性以及局部光滑的特点,构造基于区域模糊灰度总收益的轮廓变形优化目标函数.在此基础上,利用遗传算法实现对轮廓的离散傅里叶描述子参数模型进行优化,提取描述足迹重压区域的光滑轮廓.实验结果表明:该算法速度快,能充分保留轮廓细节和目标特定形状属性,在平面足迹重压区域轮廓提取中获得了较好的效果.As the edge of weight-bearing areas in the footprint image always locates in the vicinity of strong edge, characterized by a certain shape mode and locally in smooth, this paper presents a discrete Fourier descriptor （DFD） parametrically deformable model to describe the boundary of weight bearing area, and define an optimized function of total income of gray fuzzy consistency in the area. The solution to the optimized function is given by a genetic algorithm. Experimental results show that the weight-bearing area boundary can be extracted by the method in an effective way through maintaining the feature of the certain shape mode as well as describing the detail in the boundary curve.

关 键 词：足迹识别 轮廓提取 参数变形模型 模糊收益 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]