Fingerprint singular points extraction based on orientation tensor field and Laurent series

作     者：刘琴 彭可 刘巍 谢琴 李仲阳 兰浩 金耀 

作者机构：College of Engineering and DesignHunan Normal University Department of Computer ScienceFlorida Institute of Technology 

出 版 物：《Journal of Central South University》 (中南大学学报（英文版）)

年 卷 期：2014年第21卷第5期

页      面：1927-1934页

核心收录：

学科分类：07[理学] 08[工学] 080203[工学-机械设计及理论] 070104[理学-应用数学] 0802[工学-机械工程] 0701[理学-数学] 

基　　金：Project(11JJ3080)supported by Natural Science Foundation of Hunan Province,China Project(11CY012)supported by Cultivation in Hunan Colleges and Universities,China Project(ET51007)supported by Youth Talent in Hunan University,China 

主　　题：fingerprint extraction singular point fingerprint orientation tensor field Laurent series rotational invariance supportvector machine (SVM) 

摘      要：Singular point(SP)extraction is a key component in automatic fingerprint identification system(AFIS).A new method was proposed for fingerprint singular points extraction,based on orientation tensor field and Laurent ***,fingerprint orientation flow field was obtained,using the gradient of fingerprint *** these gradients,fingerprint orientation tensor field was ***,candidate SPs were detected by the cross-correlation energy in multi-scale Gaussian *** energy was calculated between fingerprint orientation tensor field and Laurent polynomial *** a global descriptor,the Laurent polynomial coefficients were allowed for rotational ***,a support vector machine(SVM)classifier was trained to remove spurious SPs,using cross-correlation coefficient as a feature ***,experiments were performed on Singular Point Detection Competition 2010(SPD2010)*** to the winner algorithm of SPD2010 which has best accuracy of 31.90%,the accuracy of proposed algorithm is 45.34%.The results show that the proposed method outperforms the state-of-the-art detection algorithms by large margin,and the detection is invariant to rotational transformations.