基于点模式特征提取的指纹匹配技术  

Fingerprint Matching Technology Based on Point Pattern Feature Extraction

作　　者：宗兆星 刘光宇 刘彪[1] 程远 张令通 赵继强 ZONG Zhaoxing;LIU Guangyu;LIU Biao;CHENG Yuan;ZHANG Lingtong;ZHAO Jiqiang(School of Engineering,Dali University,Dali 671003,China;Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education,Shanghai Jiao Tong University,Shanghai 200030,China;Information Department,Unit 32268,PLA,Dali 671003,China)

机构地区：[1]大理大学工程学院,云南大理671003 [2]上海交通大学海洋智能装备与系统教育部实验室,上海200030 [3]中国人民解放军32268部队信息科,云南大理671003

出　　处：《枣庄学院学报》2023年第5期70-76,共7页Journal of Zaozhuang University

基　　金：国家自然科学基金资助项目(62065001);云南省地方本科高校基础研究联合专项资金项目(202101BA070001-054);海洋智能装备与系统教育部重点实验室开放基金项目(MIES-2023-02)。

摘　　要：为了准确识别指纹,采用基于点模式特征提取的指纹匹配技术。选取FVC2002指纹库中的指纹,对指纹图像进行归一化、灰度阈值分割、二值化、细化等预处理后,提取出端点、分叉点等特征点,并将其包含的指纹边缘点、断点等伪特征点去除,然后将提取的指纹特征信息同指纹库中的指纹进行匹配,测试指纹匹配率为94.12%。仿真试验结果表明,该方法具有较好的识别精度,根据试验结果可知匹配率为99.41%。In order to recognize fingerprints accurately,the fingerprint matching technology based on point pattern feature extraction is adopted.The fingerprint in FVC2002 fingerprint database is selected.After the fingerprint image is preprocessed by normalization,gray threshold segmentation,binarization and refinement,the feature points such as endpoints and bifurcation points are extracted,and the pseudo-feature points including fingerprint edge points and breakpoints are removed,and then the extracted fingerprint feature information is matched with the fingerprint in the fingerprint database.The fingerprint matching rate is 94.12%.The simulation results show that this method has good recognition accuracy,and the matching rate is 99.41%.

关 键 词：指纹匹配 特征提取 点模式 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]