基于k近邻法和脊线追踪的指纹匹配算法  

Fingerprint matching algorithm based on k-nearest neighbor and ridge line tracking methods

作　　者：于明[1] 皮海龙 王岩[1] 阎刚[1] 郭迎春[1] 

机构地区：[1]河北工业大学计算机科学与软件学院,天津300401

出　　处：《吉林大学学报（工学版）》2014年第6期1806-1810,共5页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金项目(60203018)

摘　　要：首先,综合运用k近邻法和脊线追踪法,分别为叉点和端点设计了新的拓扑结构,提取脊线特征、邻域特征、细节点特征。其次,利用特征加权和坐标转换,以及半可变限界盒技术提出快速的二次匹配过程。试验结果表明:该算法运行速度快、拒识率和误识率低。A new fingerprint matching algorithm is proposed in this study. First, the k-nearest neighbor and ridge line tracking methods are used to construct new topology structures for fork point and end point, respectively, in order to extract detailed characteristics of ridge line, neighboring region and minutiae. Then, a fast secondary matching process is implemented using the techniques of feature weighting, coordinate transformation, and semi-variable bounding box. Experiment results show that the proposed algorithm can run fast and has low false reject rate and false accept rate.

关 键 词：计算机应用 指纹匹配 K近邻法 脊线追踪 半可变限界盒 二次匹配 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]