基于参数模板匹配的指纹中心定位  

Method for center point positioning in fingerprint images bases on template matching with parameters

作　　者：周慧灿[1] 刘琼[1] 王耀南[2] 

机构地区：[1]湖南文理学院计算机科学系,湖南常德415000 [2]湖南大学电气与信息工程学院,湖南长沙410082

出　　处：《计算机工程与设计》2007年第9期2079-2080,2137,共3页Computer Engineering and Design

基　　金：教育部博士点科研基金项目(20030532004)

摘　　要：目前广泛采用最大曲率方法实现指纹中心定位,但在指纹中心缺失情况下,该方法定位并不准确。为解决该问题,提出了一种基于相关参数模板匹配的指纹中心定位新方法,对FVC2004指纹数据库的测试表明,在指纹经过初步增强的基础上,借助最小距离判别,新方法能够对指纹中心准确定位,与最大曲率方法相比,在中心点缺失的情况下,有更高的鲁棒性。To realize center point positioning of fingerprint, method of maximum curvature is widely used at present. But it is inaccurate when the center region of fingerprint has been lost or not clear. To solve that problem, a new method for center point positioning bases on template matching with parameters is presented. A test to FVC2004 fingerprint database indicates that the basis of elementary enha- ncement and least distance discrimination, the new method can position the center of f＇mgerprint with accuracy. Compared with method of maximum curvature, it has better robustness conditioning the center region lost.

关 键 词：指纹中心定位 参数模板 最大曲率法 指纹增强 最小距离判别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]