细节点指纹特征提取、匹配方法研究  

A Method of Minutiae Fingerprint Feature Extraction and Matching

作　　者：蔡凡[1] CAI Fan(Minnan University of Science and Technology,Quanzhou Fujian 362700,China)

机构地区：[1]闽南理工学院,福建泉州362700

出　　处：《重庆科技学院学报（自然科学版）》2021年第2期73-77,共5页Journal of Chongqing University of Science and Technology：Natural Sciences Edition

基　　金：闽南理工学院重点科研项目“基于深度学习的困难指纹图像识别方法研究”(20KJX013);福建省中青年教师教育科研项目“基于深度学习的低分辨率指纹图像识别方法研究”(JAT190887)。

摘　　要：针对传统指纹细节点提取和匹配方法在处理低质量图像时的不足,提出改进方法。利用脊线跟踪去除伪细节特征点,对细节点特征进行位置和方向信息分析,建立配对关系,计算相似度,进而得到匹配结果。通过此方法,可有效地获取具有辨识度的指纹特征信息,避免了大量的伪特征信息,增强了指纹细节点匹配的正确率和效率,具有较高的识别率和较强的鲁棒性。Aiming at the shortcomings of traditional fingerprint minutiae extraction and matching methods in processing low-quality images,an improved method is proposed.Ridge tracking is used to remove false minutiae features,and the location and direction information of the minutiae features are analyzed to establish a pairing relationship to calculate the similarity,and then the matching results are obtained.Experimental results show that the method can effectively obtain fingerprint feature information with recognition degree,avoid a large amount of false feature information,increase the accuracy and efficiency of fingerprint minutiae matching,and has a fairly high recognition rate and strong robustness.

关 键 词：指纹 低质量图像 脊线跟踪 细节点特征 匹配 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]