An improved fingerprint indexing algorithm based on the triplet approach

Authors:
Kyoungtaek Choi;Dongjae Lee;Sanghoon Lee;Jaihie Kim
Affiliations:
Department of Electrical and Electronic Engineering, Yonsei University, Biometrics Engineering Research Center, Seoul, Korea;Department of Electrical and Electronic Engineering, Yonsei University, Biometrics Engineering Research Center, Seoul, Korea;Department of Electrical and Electronic Engineering, Yonsei University, Biometrics Engineering Research Center, Seoul, Korea;Department of Electrical and Electronic Engineering, Yonsei University, Biometrics Engineering Research Center, Seoul, Korea
Venue:
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Year:
2003

Citing 4
Cited 3

Fingerprint Image Enhancement: Algorithm and Performance Evaluation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fingerprint Matching Using Transformation Parameter Clustering

IEEE Computational Science & Engineering
Multidimensional Indexing for Recognizing Visual Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Triplet Based Approach for Indexing of Fingerprint Database for Identification

AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication

Simultaneous latent fingerprint recognition

Applied Soft Computing
Fingerprint indexing with bad quality areas

Expert Systems with Applications: An International Journal
Indexing and retrieving in fingerprint databases under structural distortions

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a triplet based fingerprint indexing algorithm which selects the candidates for identification from a large number of enrolled fingerprints. Previous triplet based indexing algorithms have three problems: quantization error, triplet matching error, the proportional increase of similarity score to the number of enrolled triplets. The proposed algorithm solves these problems as follows. First, we generate weighted indices through fuzzy membership functions based on the statistics to reduce quantization error. Second, we apply Geometric Relationships to reduce triplet matching error. Finally, we normalize similarity score to solve the last problem. We compare the proposed algorithm with the previous triplet approach and the Fingercode. Experimental results show that the average rank of the enrolled fingerprint which is identical to an input fingerprint, becomes 2.01 times less than the previous triplet method, and becomes 0.4 times less than the Fingercode.