A topology-based matching algorithm for fingerprint authentication

Author

Chen, Z. ; Kuo, C.H.

Author_Institution

Nat. Chiao-Tung Univ., Hsinchu, Taiwan

fYear

1991

fDate

1-3 Oct 1991

Firstpage

84

Lastpage

87

Abstract

A proper representation of the ridge pattern on a fingerprint is addressed. The representation must be such that it supports fingerprint matching. A nonink fingerprint input device using an optical prism is considered. A ridge pattern based on a structural model of minutiae is developed. Finally, a fingerprint matching method via tree matching is given. This method is shown to be invariant under translation and rotation, and it does not depend on the use of a prespecified core point. Experimental results indicate that this matching method is quite feasible. However, minutiae associated with whorls and noisy regions are troublesome and unstable

Keywords

biometrics (access control); image recognition; optical prisms; pattern recognition equipment; topology; trees (mathematics); fingerprint authentication; minutiae; noisy regions; nonink fingerprint input device; optical prism; ridge pattern; rotation invariance; structural model; topology-based matching algorithm; translation invariance; tree matching; whorls; Authentication; Bifurcation; Bridges; Cameras; Fingerprint recognition; Fingers; Optical devices; Optical distortion; Optical sensors; Pattern matching;

fLanguage

English

Publisher

ieee

Conference_Titel

Security Technology, 1991. Proceedings. 25th Annual 1991 IEEE International Carnahan Conference on

Conference_Location

Taipei

Print_ISBN

0-7803-0120-X

Type

conf

DOI

10.1109/CCST.1991.202195

Filename

202195