基于纹线跟踪的指纹分类方法  

Fingerprint Classification Method Based on Ridge-following

作　　者：杨小冬[1] 宁新宝[1] 詹小四[1] 庄建军[1] 

机构地区：[1]南京大学电子科学与工程系南京大学声学研究所近代声学国家重点实验室生物医学电子工程研究所,南京210093

出　　处：《计算机工程》2005年第7期170-173,共4页Computer Engineering

基　　金：南京大学重大应用研究预研项目(2001-03)

摘　　要：在深入研究现有指纹分类算法的基础上,提出了一种基于纹线跟踪的新颖指纹分类方法。不同于以往利用core点和delta点进行分类,该算法结合纹线跟踪的思想,在模式区进行纹线跟踪,得到模式区的跟踪曲线,然后再根据曲线参数进行分类,取得了较好的效果。After investigating existing approaches to fingerprint classification, this paper introduces a novel method which is based on following the ridges of the fingerprint image. Other than utilizing core and delta points that are necessary in previous classification method, it first follows the ridges in the pattern area of a fingerprint image and gets a curve which can represent the area. After that some classification work can be do according to the curve's parameters. Experiment results illustrate that the method can perform better.

关 键 词：纹线跟踪 模式区 曲线参数 分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]