Fingerprint singular points extraction based on orientation tensor field and Laurent series
来源期刊：中南大学学报(英文版)2014年第5期
论文作者：LIU Qin(刘琴) PENG Ke(彭可) LIU Wei(刘巍) XIE Qin(谢琴) LI Zhong-yang(李仲阳) 兰浩 JIN Yao(金耀)
文章页码：1927 - 1934
Key words：fingerprint extraction; singular point; fingerprint orientation tensor field; Laurent series; rotational invariance; support vector machine (SVM)
Abstract: 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 series. First, fingerprint orientation flow field was obtained, using the gradient of fingerprint image. With these gradients, fingerprint orientation tensor field was calculated. Then, candidate SPs were detected by the cross-correlation energy in multi-scale Gaussian space. The energy was calculated between fingerprint orientation tensor field and Laurent polynomial model. As a global descriptor, the Laurent polynomial coefficients were allowed for rotational invariance. Furthermore, a support vector machine (SVM) classifier was trained to remove spurious SPs, using cross-correlation coefficient as a feature vector. Finally, experiments were performed on Singular Point Detection Competition 2010 (SPD2010) database. Compared 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.
LIU Qin(刘琴)1, PENG Ke(彭可)1, LIU Wei(刘巍)2, XIE Qin(谢琴)1, LI Zhong-yang(李仲阳)1, LAN Hao(兰浩)1, JIN Yao(金耀)1
(1. College of Engineering and Design, Hunan Normal University, Changsha 410081, China;
2. Department of Computer Science, Florida Institute of Technology, Melbourne 32901-6975, USA)
Abstract: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 series. First, fingerprint orientation flow field was obtained, using the gradient of fingerprint image. With these gradients, fingerprint orientation tensor field was calculated. Then, candidate SPs were detected by the cross-correlation energy in multi-scale Gaussian space. The energy was calculated between fingerprint orientation tensor field and Laurent polynomial model. As a global descriptor, the Laurent polynomial coefficients were allowed for rotational invariance. Furthermore, a support vector machine (SVM) classifier was trained to remove spurious SPs, using cross-correlation coefficient as a feature vector. Finally, experiments were performed on Singular Point Detection Competition 2010 (SPD2010) database. Compared 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.
Key words:fingerprint extraction; singular point; fingerprint orientation tensor field; Laurent series; rotational invariance; support vector machine (SVM)
