基于方向图分布及中心点信息的指纹分类算法  

Fingerprint Classification Based on Both Distributed Directional Image and Core Point Information

作　　者：王晓莉[1] 齐文钊[1] 刁海南[1] 

机构地区：[1]河南科技大学电子信息工程学院,河南洛阳471003

出　　处：《微电子学与计算机》2008年第3期25-27,31,共4页Microelectronics & Computer

基　　金：国家科技型中小企业技术创新基金项目(05C26214101032)

摘　　要：在深入研究现有指纹分类算法的基础上,提出了一种基于方向图及中心点信息的指纹分类算法.不同于以往利用core点和delta点进行分类,该算法根据指纹图像的中心点位置对方向图进行区域分割,通过各区域方向码之间的计算近似实现方向滤波,由方向滤波值进行分类.指纹图像大致可分为拱型、左箕型、右箕型和漩涡型4种.该算法为匹配算法提供了指纹类型信息,实验结果表明取得了较好的效果.After investigation existing approaches to fingerprint classification, this paper introduces a novel method which is based on following both distributed directional image and core point information. Other than utilizing core and delta points that are necessary in previous classification Method, according to the location of core point, the directional image is divided into several regions. By calculating each region＇s directional code accomplishes directional filtering, thus the basic category of fingerprint is classified. Fingerprints are normally classified into four categories： arch, left loop, right loop and whorl. It successfully provides the information of fingerprint category for the matching method. Experiment results illustrate that the method can perform better.

关 键 词：指纹图像 方向图 中心点 方向图分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]