Fingerprint indexing based on combination of novel minutiae triplet features

W. Zhou; J. Hu; S. Wang; I.R. Petersen; Mohammed Bennamoun

Fingerprint indexing based on combination of novel minutiae triplet features

W. Zhou, J. Hu, S. Wang, I.R. Petersen, Mohammed Bennamoun

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

Abstract

© Springer International Publishing Switzerland 2014. Fingerprint indexing is a process of pre-filtering the template database before matching. The most common features used for fingerprint indexing are based on minutiae triplets. In this paper, we investigated the indexing performance based on some commonly used features of minutiae triplets and proposed to combine these features with some novel features of minutiae triplets for fingerprint indexing. Experiments on FVC 2000 DB2a and 2002 DB1a show that the proposed indexing method can perform better than state-of-the-art schemes for full fingerprint indexing, meanwhile, experimental results on NIST SD 14 show that the performance is improved significantly after the new features are added to the feature space, and is fairly good even for partial fingerprint indexing.

Original language	English
Title of host publication	Lecture Notes in Computer Science
Subtitle of host publication	Network and System Security
Editors	Man Ho Au, Barbara Carminati, C.-C. Jay Kuo
Publisher	Springer International Publishing Switzerland
Pages	377-388
Volume	8792
ISBN (Electronic)	9783319116983
ISBN (Print)	9783319116976
Publication status	Published - 2014
Event	8th International Conference on Network and System Security (NSS) - China, Xi'an, China Duration: 15 Oct 2014 → 17 Oct 2014

Conference

Conference	8th International Conference on Network and System Security (NSS)
Country/Territory	China
City	Xi'an
Period	15/10/14 → 17/10/14

Cite this

@inproceedings{c7319ffca958495da8a8cf7ba5615b48,

title = "Fingerprint indexing based on combination of novel minutiae triplet features",

abstract = "{\textcopyright} Springer International Publishing Switzerland 2014. Fingerprint indexing is a process of pre-filtering the template database before matching. The most common features used for fingerprint indexing are based on minutiae triplets. In this paper, we investigated the indexing performance based on some commonly used features of minutiae triplets and proposed to combine these features with some novel features of minutiae triplets for fingerprint indexing. Experiments on FVC 2000 DB2a and 2002 DB1a show that the proposed indexing method can perform better than state-of-the-art schemes for full fingerprint indexing, meanwhile, experimental results on NIST SD 14 show that the performance is improved significantly after the new features are added to the feature space, and is fairly good even for partial fingerprint indexing.",

author = "W. Zhou and J. Hu and S. Wang and I.R. Petersen and Mohammed Bennamoun",

year = "2014",

language = "English",

isbn = "9783319116976",

volume = "8792",

pages = "377--388",

editor = "Au, {Man Ho} and Barbara Carminati and Kuo, {C.-C. Jay}",

booktitle = "Lecture Notes in Computer Science",

publisher = "Springer International Publishing Switzerland",

note = "8th International Conference on Network and System Security (NSS) ; Conference date: 15-10-2014 Through 17-10-2014",

}

Zhou, W, Hu, J, Wang, S, Petersen, IR & Bennamoun, M 2014, Fingerprint indexing based on combination of novel minutiae triplet features. in MH Au, B Carminati & C-CJ Kuo (eds), Lecture Notes in Computer Science: Network and System Security. vol. 8792, Springer International Publishing Switzerland, pp. 377-388, 8th International Conference on Network and System Security (NSS), Xi'an, China, 15/10/14.

Fingerprint indexing based on combination of novel minutiae triplet features. / Zhou, W.; Hu, J.; Wang, S. et al.
Lecture Notes in Computer Science: Network and System Security. ed. / Man Ho Au; Barbara Carminati; C.-C. Jay Kuo. Vol. 8792 Springer International Publishing Switzerland, 2014. p. 377-388.

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

TY - GEN

T1 - Fingerprint indexing based on combination of novel minutiae triplet features

AU - Zhou, W.

AU - Hu, J.

AU - Wang, S.

AU - Petersen, I.R.

AU - Bennamoun, Mohammed

PY - 2014

Y1 - 2014

N2 - © Springer International Publishing Switzerland 2014. Fingerprint indexing is a process of pre-filtering the template database before matching. The most common features used for fingerprint indexing are based on minutiae triplets. In this paper, we investigated the indexing performance based on some commonly used features of minutiae triplets and proposed to combine these features with some novel features of minutiae triplets for fingerprint indexing. Experiments on FVC 2000 DB2a and 2002 DB1a show that the proposed indexing method can perform better than state-of-the-art schemes for full fingerprint indexing, meanwhile, experimental results on NIST SD 14 show that the performance is improved significantly after the new features are added to the feature space, and is fairly good even for partial fingerprint indexing.

AB - © Springer International Publishing Switzerland 2014. Fingerprint indexing is a process of pre-filtering the template database before matching. The most common features used for fingerprint indexing are based on minutiae triplets. In this paper, we investigated the indexing performance based on some commonly used features of minutiae triplets and proposed to combine these features with some novel features of minutiae triplets for fingerprint indexing. Experiments on FVC 2000 DB2a and 2002 DB1a show that the proposed indexing method can perform better than state-of-the-art schemes for full fingerprint indexing, meanwhile, experimental results on NIST SD 14 show that the performance is improved significantly after the new features are added to the feature space, and is fairly good even for partial fingerprint indexing.

M3 - Conference paper

SN - 9783319116976

VL - 8792

SP - 377

EP - 388

BT - Lecture Notes in Computer Science

A2 - Au, Man Ho

A2 - Carminati, Barbara

A2 - Kuo, C.-C. Jay

PB - Springer International Publishing Switzerland

T2 - 8th International Conference on Network and System Security (NSS)

Y2 - 15 October 2014 through 17 October 2014

ER -