摘要
作为指纹最重要的全局特征之一,奇异点在基于模型的方向场计算、人工合成指纹、指纹分类、指纹特征匹配等方面发挥了非常重要的作用.在指纹方向场分割的基础上提出了一种称之为方向丰富度的特征,并据此形成了一种新的指纹奇异点快速检测方法.该方法首先将指纹方向场分割为一系列互不重叠的同质区域;然后通过同质区域边缘检测及边缘端点提取实现了奇异点快速定位;最后依据奇异点处方向丰富度特性判断其类型.实验验证了文中算法的有效性.
As a global feature of fingerprints, Singular Point （SP） plays important roles in model based fingerprint orientation computing, synthesis fingerprint, fingerprint classification, fingerprint alignment and so on. This paper introduces a new feature called Orientation Abundance Degree （OAD） based on fingerprint＇s orientation segmentation, and proposes a new method for rapid detection of fingerprint＇s SP by using OAD. In this method, fingerprint＇s orientation is partitioned into a series of non-overnapping homogeneous areas firstly; then SPs are rapidly localized through edges detection of homogeneous areas and end-points extraction of edges; finally, the types of SPs are distinguished according to the characteristic of OAD. Experiments show the efficiency of the new method.
出处
《计算机学报》
EI
CSCD
北大核心
2009年第5期1037-1045,共9页
Chinese Journal of Computers
基金
国家自然科学基金(60773172)
江苏省自然科学基金(BK2008411)
中国博士后基金(20070411055)资助
关键词
指纹
奇异点
方向场
分割
fingerprint
singular point
orientation field
segmentation
