Improved phase-only correlation method for low quality fingerprint matching

Authors:
Muhammad Younus Javed;Muhammad Sohaib Hamid
Affiliations:
College of Electrical and Mechanical Engineering, National University of Sciences and Technology, Rawalpindi, Pakistan;College of Electrical and Mechanical Engineering, National University of Sciences and Technology, Rawalpindi, Pakistan
Venue:
ACST'06 Proceedings of the 2nd IASTED international conference on Advances in computer science and technology
Year:
2006

Citing 3
Cited 0

Fingerprint Image Enhancement: Algorithm and Performance Evaluation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fingerprint Matching Using Feature Space Correlation

ECCV '02 Proceedings of the International ECCV 2002 Workshop Copenhagen on Biometric Authentication
Handbook of Fingerprint Recognition

Handbook of Fingerprint Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an improved Phase-Only Correlation (POC) method for efficient matching of fingerprints that are either very poor in quality or represent partial fingerprints. Unlike the conventional matching techniques that depend upon the feature-based similarity criteria (i.e. minutiae and core-point), the POC based techniques use the phase spectrum of fingerprint image which is highly robust against image degradation. In this paper new modifications have been proposed in the implementation of POC approach particularly for improving its matching performance for low quality and partial fingerprints. The developed fingerprint matching system makes use of image segmentation, surface-data normalization, surrounding elimination and common-region extraction resulting into highly robust and efficient identification of low quality fingerprints.