摘要
为了克服指纹识别中常见的问题,本文提出一种基于指纹结构特征信息匹配的算法。该算法利用改进的Bresenham算法求得指纹分叉点间连线所穿越的脊线个数和分叉点结构特征信息,得到模板指纹和待识指纹的结构特征信息矢量数组;运用二分图的完美匹配算法,得到矢量数组的匹配度。对该匹配度进行评估,如果高于某一个阈值,则认为指纹匹配成功;否则,则认为不是同一指纹。该算法在实际应用中取得较好的效果。
To overcome structural information is the common problems in fingerprint recognition, an algorithm based on the presented in this paper. The sums through ridges and structural feature information of bifurcates are extracted by using the developed Bresenham algorithm, and the vector arrays of structural information of template fingerprint and recognized fingerprint are computed; the matching degree of vectors is gained in the way of perfect matching algorithm of bipartite graph. The matching is successful if the degree is bigger than a certain threshold, or the fingerprints are not from the same person. The algorithm takes good effect in practical applications.
出处
《光电工程》
EI
CAS
CSCD
北大核心
2006年第7期101-104,109,共5页
Opto-Electronic Engineering
基金
辽宁省自然科学基金项目:基于方向空间的数字图像边缘检测理论研究(2001101022)
关键词
指纹匹配
特征提取
穿越脊线次数
BRESENHAM算法
二分图完美匹配算法
Fingerprint matching
Feature extraction
Sums through the ridges
Bresenham algorithm
Perfect matching algorithm of bipartite graph
