利用遗传算法对指纹的核心点进行检测  

Fingerprint Core-point Detection Using Genetic Algorithms

作　　者：毛克明[1] 王国仁[1] 金艳[1] 

机构地区：[1]东北大学信息科学与工程学院,辽宁沈阳110004

出　　处：《小型微型计算机系统》2009年第10期2001-2004,共4页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(60573089;60773219)资助

摘　　要：指纹的核心点是指纹的主要特征,对指纹匹配和指纹分类具有十分重要的作用.本文对指纹核心点的位置和方向进行了新的定义,接着提出一种新颖的基于遗传算法的方法对指纹核心点进行定位以及对核心点的方向进行估计.首先根据定义给出核心点位置和方向的打分函数并根据指纹的方向域信息确定了核心点的候选区域,接着把打分函数作为遗传算法的进化适应度函数在这个核心点候选区域内利用遗传算法对指纹核心点及其方向进行快速求极值,这样可以同时得到指纹的核心点的坐标和方向.实验结果表明本文提出的方法可以对指纹的核心点的位置和方向进行精确的定位和估计.Core-point is an essential feature in a fingerprint, and is also very important in fingerprint matching and fingerprint classification. This paper defines the fingerprint core-point and its orientation in a novel way, then a genetic algorithms （GAs） -based method is proposed to locate the position of the core-point and compute its orientation. First the orientation field information of fingerprint is used to determine the core-point candidate region, and the fitness function of core-point＇s position and orientation is devised according to the definition. Finally, GAs is used to search the position of the core-point along with its orientation in a fast way. The experimental results show that the proposed method can exactly locate the core-point and compute its orientation.

关 键 词：指纹 核心点 核心点方向 遗传算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]