Intrinsic coordinates for fingerprints based on their longitudinal axis
Author:
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 500-504
Abstract
Image alignment is an important step in the fingerprint recognition process. In order to obtain that Euclidean motion, its rotation and both translational components need to be determined. We propose a novel method to obtain this information by extracting the fingerprints' longitudinal axes from their orientation fields. A model-based approach allows to additionally fix a horizontal axis, thereby defining an intrinsic coordinate system. We evaluated the robustness of this method on the NIST Special Database 4.Keywords
This publication has 10 references indexed in Scilit:
- Global Models for the Orientation Field of Fingerprints: An Approach Based on Quadratic DifferentialsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Impact of Singular Point Detection on Fingerprint Matching Performance2006
- Orientation feature for fingerprint matchingPattern Recognition, 2006
- Fingerprint warping using ridge curve correspondencesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Fingerprint Reference-Point DetectionEURASIP Journal on Advances in Signal Processing, 2005
- Segmentation of Fingerprint Images Using Linear ClassifierEURASIP Journal on Advances in Signal Processing, 2004
- Localization of corresponding points in fingerprints by complex filteringPattern Recognition Letters, 2003
- Systematic methods for the computation of the directional fields and singular points of fingerprintsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- An Intrinsic Coordinate System for Fingerprint Matching2001
- A model for interpreting fingerprint topologyPattern Recognition, 1993